Changelog

Updates and improvements to Pathmode. We ship regularly.

September 11, 2026

Features

Sign up with an email link, with no password to choose

Signing up used to mean Google or a two-field form with a password to invent. Confirming your address by email is now mandatory either way, so the password had stopped earning its place: one more thing to invent, one more thing to forget, one more credential for us to hold. The signup door is Google plus one button now, and the email door opens only when you ask for it. We send a link, and clicking it creates the account. Sign-in is unchanged, so accounts that already have a password keep the door they already use.

Name your own workspace

The workspace name used to be invented from your email address, so janne+a10@ arrived as Janne A10's Workspace and the only way to say otherwise was to hunt through settings afterwards. Signup asks now. That derived name is offered as the default, and the URL follows what you type until you edit the URL by hand. A URL genuinely held by someone else says so, rather than quietly appending a random suffix to a name you chose.

A new workspace opens on one thing to do, and an agent finishes it

A new workspace now arrives holding a single intent: Connect your coding agent. It is a real IntentSpec rather than a card, which is the whole point, because an agent can read an intent. It is marked done when an agent actually reads it with your workspace key, so setup is proven by the product working rather than by a checkbox. Copying the command does not count, and neither does opening the page in a browser. If a teammate runs the agent, or you have no repository ready yet, the step stays open behind you instead of reading as failed.

The teammate handoff has a page of its own, and it keeps

Inviting the teammate who runs your coding agent used to happen in a panel on the workspace home, and once you closed it there was nowhere to see what had come of it. It is a page now, with three stages that update while you watch: Invitation sent, Teammate joined, Repository connected. You can start the brief while they connect. Leave the page, refresh it, or come back a week later and the handoff is still there: the invitation remembers what it was for, and your workspace home carries a row showing where it stands, with View handoff to reopen it and Invite again if the invitation expired or was cancelled. Repository connected counts only a setup that came from that exact invitation, by the person who accepted it, with a credential a coding agent has actually used. A key someone minted earlier does not stand in for your teammate's connection, and when their credential lapses the row says so and names who has to renew it. Older invitation links keep working exactly as they did.

Removed

•The example product. A new workspace used to arrive holding Acme HR: a fictional product with three intents and ten evidence items. It answered "what is this?" while the question a new account actually holds is "what do I do now?", and four intents on the first screen give you no way to tell which one is yours. Demo workspaces still seed it deliberately, and workspaces created before this keep theirs

Improvements

•The welcome email waits until you confirm your address, and describes the workspace you actually land in instead of evidence that was never there
•Asking for an email link with an address that already signs in with Google now opens that account, instead of minting a second one with an empty workspace beside it
•Correcting a typo in your address sends the new link immediately. The one-minute wait between links is per address now, so the corrected address is no longer silenced by the request you were correcting
•The check-your-email screen has a way back, which is what a mistyped address needs: the link never arrives, and there was nothing on that page to click
•A workspace name the URL rules reject returns you to the naming form with the reason and with what you typed still in it, instead of an error screen with no way forward
•Confirming a signup in a second browser tab no longer ends on "Failed to create workspace". Both tabs land in the one workspace that was created
•The check-your-email screen no longer promises a scan that does not run on that path
•The signup page no longer previews what happens after signup while you are still deciding whether to sign up. What it costs stays on the page, because that is a question you hold before creating anything

September 9, 2026

Features

Creating an account now connects your repository

A new account used to land on an empty workspace. It now opens with one question: who runs the coding agent in your repository. Answer I run it and you go straight to connecting the repository and getting the one-time setup command. Answer someone else runs it and you hand that setup to them. If you have no repository ready yet, you start from a brief instead. The repository keeps the spec your agent reads; Pathmode keeps the evidence and the judgment behind it.

Hand the setup to the teammate who runs the agent

If you make the product calls and someone else operates the coding agent, you can now invite them for exactly that. The invitation says what they are being asked to do, and accepting it takes them to repository connection rather than a workspace page that explains nothing. Your own screen says plainly that an invitation is not yet a connection, and tells you when their agent actually launches. You do not have to wait to start writing.

Try the readiness gate before creating anything

The second option on the home page is now a preflight rather than a walkthrough. It runs the same six deterministic checks Pathmode applies to every spec, in your browser, on a failing example, a repaired one, or a spec you paste in. Nothing is uploaded and no account is needed. The gate is local and has no memory, so when you want private evidence, decisions attributed to the person who made them, and review by a teammate who never opens a terminal, connecting a repository is what adds them.

Improvements

•A question you deliberately left open now reads differently from one you never reviewed, both on screen and in the file your agent receives
•The pre-signup decision review no longer offers to accept every suggestion at once; each call is yours to take, edit, or leave open
•Working through a product decision now continues straight to creating the account and reviewing the proposal, without a separate workspace step in between
•Signing up from a decision that never named a product no longer fails at the last step
•The Pathmode wordmark on the preflight page returns to the home page instead of doing nothing
•Every brief now records which part of the product it was started from

September 8, 2026

Features

Review the intent instead of writing the whole spec

Every intent now opens as a proposal built for product review. Start with a short description and choose Draft with agent, or open a proposal an agent created through the API. The review leads with the problem, intended outcome, trade-offs, success measures, and the questions that still need your judgment; implementation details remain available without taking over the page.

Agent additions stay visible until you review them

Claims and sections added by the agent are marked Suggested until you keep, edit, or remove them. Keeping the remaining suggestions is one action, while individual claims can still be handled on their own. Editing a suggestion makes the wording yours. This marker is a review state, not a permanent record of who accepted an individual claim; whole-proposal authorization remains a separate, recorded decision.

Authorize the proposal the implementation agent will use

Agent-originated intents require an explicit human decision before implementation. For repository-owned intents, authorization names the exact revision under review, and a later revision asks for a fresh decision. Request changes from the same surface, follow the repository agent's response, and review the resulting proposal before the build continues.

Improvements

•Workspace and Product Home now lead with proposals that need a decision, drafts with suggestions to review, and work waiting on an agent
•Intent rows distinguish Review proposal, Review suggestions, Review revised proposal, and Waiting for agent from delivery status
•The conversation editor remains available for discussion and deeper editing, while the proposal is now the primary intent surface
•Agent-written outcomes and edge cases keep stable identities, so their suggestion and evidence references survive ordinary saves

September 3, 2026

Features

Know what backs every claim, and who judged it

An IntentSpec no longer reports how much evidence is attached to it. It reports, claim by claim, what each one rests on. The objective, every outcome, every constraint and every edge case now shows Backed, Unreviewed, Assumption or No evidence, and expanding a claim shows the exact items behind it with their tier, origin, source and the person who reviewed them. Use as backing is one action: it reviews the signal and anchors it to that exact claim, stamped with the reviewer and the time. Only Use as backing turns a captured, unreviewed signal into backing for a claim; a signal you type yourself is already reviewed by you. The Evidence Inbox offers exactly Use as backing, Keep unreviewed and Dismiss, Browse is the flat searchable record you audit rather than judge in, and agents writing over the API or MCP can capture signals but can never review one or turn it into backing. No evidence stays descriptive: it tells a reader this part of the spec is a decision, not a finding, and it is not a readiness failure.

Evidence carries a trust tier everywhere it leaves Pathmode

Every evidence item is now classified before it reaches an agent, an export, a reviewer, or a coverage count: reviewed backing, an unreviewed signal, or an AI-drafted assumption. Archived and dismissed items never leave the store. Agent prompts render the three tiers under their own headings and no longer describe unreviewed or assumed items as user feedback. Review links and spec coverage apply the same rule, so a claim anchored only to assumptions reads as a gap, not as covered. The MCP server (1.24.0) returns the tier on every item, hides dismissed evidence by default, and gains get_intent_evidence to fetch exactly what one intent cites.

Pull requests get an advisory intent review before merge

When a pull request that references an intent is opened or updated, Pathmode grades the diff against the intent the same way it grades a merge, and posts the result as a GitHub check named Pathmode intent review. Each run is bound to the exact head commit it read and the exact intent revision it graded against, so a verdict can always be reproduced. The check concludes success or neutral, never failure: it informs while the diff can still change and blocks nothing. A signed-in writer can accept, reject or waive each finding with a reason on the intent page; decisions follow the item to later commits while its judgment is unchanged, and the run that graded the merged head is carried into the merge record. A run the grader could not complete is recorded as unavailable, not as a pass.

Committed files carry references, not quotes

intent.md, CLAUDE.md, AGENTS.md and .cursorrules now reference evidence by type and id instead of copying quotes and source names into git. This is what the IntentSpec repo-safe profile requires: the repository gets the decision, Pathmode keeps the evidence behind it. Agents dereference an id through the MCP server when they need the content.

Removed

•The Kanban, Flow and Clusters layouts of the Evidence board. Pathmode is a trust layer for the claims in a spec, not a research canvas; the Inbox and the detail panel remain. This is a product decision, not a usage measurement
•Group-by, bulk selection and "Suggest intents" synthesis on the Evidence Browse view. Browse is now a flat, searchable record for locating and opening evidence; claim backing is inspected and added on the IntentSpec itself, and Evidence opens to the Inbox whenever unreviewed items are waiting
•Creating a general, non-claim evidence link from the signed-in UI. Making something trustworthy in the app now means choosing the exact claim it backs. Existing general links stay visible on the spec as "General / not claim-anchored", and API and MCP link_evidence are unchanged

Improvements

•Every door that creates evidence now states whether a person reviewed it: typed and kept items are reviewed, AI-drafted assumptions and file imports land in the Inbox, and evidence written through the API by an agent carries its own provenance
•The empty-state sample ticket and example cards persist as unverified assumptions rather than confirmed evidence
•Prose paste has one path: the Composer extracts, you review inline, and the kept items are saved. The import modal is for files only

August 31, 2026

Features

Bring the intent.md you already have

Onboarding no longer assumes every new user arrives empty-handed. Choose the repository path, sign in, select or create the workspace and Product that own the work, then run npx @pathmode/mcp-server@latest adopt pm_adopt_... from the repository. The command keeps the existing intent body, adds its Pathmode identity, and sends it to the Product you chose. The browser waits for that exact adoption session to finish, then closes the loop with the hosted capability a file cannot provide: a review link for someone who will never open the repository. Shipped in @pathmode/mcp-server 1.20.0.

Repository credentials belong to repositories

Connecting one repository could rewrite a global MCP configuration and point every repository on the machine at the newest workspace. Adoption now writes only a non-secret workspace binding into the repository. Its API key stays outside git in an owner-only file for that workspace, and the generated .mcp.json contains no credential. Two repositories can connect to different workspaces without “last setup wins,” and no committable configuration contains the secret.

Improvements

•Repository adoption validates intent.md before using the one-time code and stores the exchanged credential before pushing, so a failed network step can resume instead of burning the code or minting duplicate keys
•Adoption codes expire after 15 minutes, are stored only as hashes, can be claimed only once, and the unauthenticated exchange is rate-limited by caller before a code is parsed as well as by code for legitimate retries

August 30, 2026

Features

Use Pathmode with OpenSpec, not instead of it

The integration is public at /openspec. Two ways in. Run the free preflight on an OpenSpec change and get the same six deterministic gates and the same verdict, read-only, with nothing leaving your machine. Or add the pathmode-intent schema, which writes an intent.md into the change directory ahead of the proposal, so the decision is settled before the work is described. The page draws the line a public repository forces: repo-safe intent and references travel in the change, private evidence and authenticated attribution stay in Pathmode. This is an independent integration designed to work with OpenSpec, not a partnership, and the schema is labeled experimental. The old comparison page redirects here. Its copy said use both while its structure said choose one, and structure wins that argument every time.

IntentSpec has a standards repository

The format had a site, a normative spec, and a schema, but no open-source home, so “propose changes on GitHub” pointed at the validator Action. pathmodeio/intentspec now carries SPEC.md, schema.json, a conformance corpus, and governance. It also settles a conflict the OpenSpec work surfaced: the schema asks for an excerpt on every evidence item, which read literally invites pasting customer material into git. The spec now defines a repo-safe profile normatively. Summaries and references belong in a committed document; raw evidence and authenticated attribution belong elsewhere. That is a usage profile, not a schema change, and the schema cannot fork: it syncs in one direction and a parity test fails on drift.

Four parsers, one reading

There are four implementations of the IntentSpec normalization rules: the reference, the GitHub Action, the browser parser, and the MCP and CLI parser. Nothing pinned any of them to the spec, and accept-or-reject fixtures cannot catch two parsers agreeing a document is valid while disagreeing about what it says. A normalization corpus, markdown in and exact normalized object out, is now run by all four and published at intentspec.org/normalization-corpus.json so consumers fetch it instead of vendoring a copy that passes forever against whatever it was copied at. It earned itself on the first run: the reference accepted an ASCII arrow for edge cases while both shipped parsers accepted the Unicode arrow and a colon, so one document produced different edge cases depending on who read it. All four now accept all four documented forms, and the spec lists them.

The intent.md in your repo is the authority

check_intent_readiness with no arguments used to fall back to the workspace's "current intent" heuristic, which can pick a different intent than the file you are standing in. It now prefers this repository's intent.md and falls back to the workspace only when no repo-bound file exists. review-against-intent and handoff-intent follow the same rule: the file decides which intent is under discussion, and the workspace call enriches it with findings, handoff notes, and authorization rather than replacing it. Shipped in @pathmode/mcp-server 1.17.0 and plugin 0.1.12.

Handoff notes reach the next agent

handoff-intent tells an agent to record every decision and discovery with log_implementation_note, assuming the next reader has none of this conversation's context. Nothing ever read them back. The agent prompt hydrated open findings and had zero references to notes, so a shipped skill promised durable continuity into a write-only store. The prompt now renders a handoff section from those notes, capped at the 10 newest, and says how many it left behind instead of silently truncating. Notes render after findings deliberately: a proven contradiction outranks one session's account of what it was doing, and the copy frames a note as context rather than as an instruction, so a stale note cannot read as licence to diverge from the spec.

Claude Code tells you the repository has an intent

Open a session in a repository that has an intent.md and the plugin now states one line: the title, the status, and how far the spec has drifted from the code, in days since it was edited and commits since. State, not homework. A test asserts the line never says "you should", "please", or "run", because that is the rule most likely to erode under a well-meaning future edit. It is silent in repositories with no intent, since a hook that greets every repo with advice gets the plugin uninstalled. File reads and one git call: no network, no key. Shipped in plugin 0.1.12 and time-boxed as an experiment; if it has not moved repeated use by October 11 it comes out.

Improvements

•The Engineering Lead and First Intent use case exists, and its CTA routes to the keyless flow rather than the web signup. That cell's entire pitch is that no account is needed, and it was falling through to a fallback that asked for one
•The plugin install commands are single-sourced across the landing page, /preflight, the intent-compiler page and /developers, so they cannot drift against each other. Teaching only the marketplace command installs nothing, and this is how the public plugin repo sat four versions stale
•Page titles lead with the nouns people search for. The glossary index was titled "Glossary", which ranks for nothing, while every searchable term sat in the description where it earns no title relevance. The blog's structured data also described an earlier blog that no longer exists

August 29, 2026

Features

The OpenSpec bridge runs both ways

If you already keep specs as OpenSpec changes, adopting Pathmode meant re-typing judgment that exists in your repo. intent_import reads a change through the same projection the preflight grades with, so an imported intent's readiness verdict matches the change's preflight verdict by construction rather than by a separate claim. Field text travels deterministically and never through a model, because a confirmation made after import anchors to a digest of that text and a paraphrase would silently kill it. intent_export --format openspec runs the other way: proposal.md, a spec delta, and the verification contract in tasks.md, each placed where the reader actually looks, and it refuses to write into an existing change folder. What does not travel is named in the receipt rather than silently dropped: design.md prose and task lists stay in your workflow. Import never updates an existing intent, and that is a real trade rather than an oversight. Nothing proves the intent.md already in your repo corresponds to this change, so re-importing produces a new intent rather than a new version. Shipped in @pathmode/mcp-server 1.16.0.

Confirmations work against a workspace

confirm_intent_dimension only ever read intent.md, so a cloud user got "No intent file" from a tool whose storage had just been built. Local and cloud now differ only in where the spec is read and where the record is written. Which states are confirmable, what a record must name, and how it is anchored are computed once, so the two modes cannot drift into disagreeing about what a confirmation means. The cloud write is fenced on the version it read, so a concurrent edit is a conflict rather than a silent overwrite, and confirmations are carried by every projection that reads an intent, because a column present in one select and absent from another is this codebase's recorded defect family. Waivers are refused in cloud mode, with the reason: a waiver is a human decision and an API key is by construction the machine path. Until the editor can record one, cloud waivers are unavailable, which is the honest consequence of not letting an agent mint the strongest-looking record there is.

August 28, 2026

Fixed

•check_intent_readiness could not pass for any intent saved in a workspace. The tools that read an intent for grading were reading the list projection, which does not carry edge cases, so every cloud spec was graded with its failure modes missing and blocked on "No edge case with a defined expected behavior" however well it was written. get_current_intent, the outcome rubric export and the current-intent resource had the same hole, so an agent asking for the full spec never received the one part it would not invent for itself. Fixed in @pathmode/mcp-server 1.14.1

August 26, 2026

Features

Your agent gathers what the code looks like. You decide whether it counts.

An agent working in your repo can now hand back what it found where the change lands: the files involved, how they behave today, what a change would risk, how to verify it. Pathmode never clones or reads your source for this: the agent already in your repo does the reading, which is also why it can see work you have not committed. That context reaches the next agent as context immediately. Its risks and verification suggestions do NOT become criteria in the Outcomes rubric until you accept them, because otherwise the party being graded would be writing its own rubric. The accept is one click on the intent, and you can withdraw it.

Stamp the pull request and the merge does the rest

Name the intent in your branch or PR body and the merge reads the real diff, grades it against the spec, moves the intent to Shipped, and records what the verdict rested on. Agents are now told to write that reference, which is the part that was missing: the loop has existed for a while and almost nothing carried the name it needed. Agents are also told to stop short of marking work shipped themselves, and a merge will still grade an intent that was flipped early rather than staying silent about it.

A spec saved by an agent lands in your workspace

intent_save used to write a file and stop there, even with a workspace connected. It now creates or updates the intent in the workspace and writes intent.md as the projection of that record. Specs written keyless get real ids, so a keyless spec can be named in a pull request and the delivery loop works from the first run. If several products could own a new intent, the save asks which one rather than guessing, because the product decides which repository merge verification applies to.

Fixed

•A merged pull request did not update intents in workspaces that had set a per-product GitHub connection. The lookup assumed one connection per installation, so every delivery to those workspaces failed before it began
•A merge in one repository could mark an intent shipped whose product is bound to a different repository, and grade it against the wrong codebase

Improvements

•Two agents editing one spec can no longer overwrite each other silently: an edit states the version it was based on, and a conflict is refused rather than resolved by whoever wrote last
•The MCP surface is now 25 cloud tools, with record_implementation_context added

August 23, 2026

Features

Preflight has its own home

The free Claude Code plugin now lives at preflight.pathmode.io. The page runs the real readiness gate in your browser: two example specs, six deterministic checks, and the exact verdict an agent-bound intent would get, nothing mocked. Preflight is free and uses the models you already have access to in Claude Code.

Your agent proposes. You authorize.

An agent can now write a spec into Pathmode, but nothing in its own toolchain tells it to proceed until a human says so. A spec an agent authored starts pending, and the agent prompt opens with a DO-NOT-IMPLEMENT banner until you clear it. Authorization is a human-only verb: the endpoint accepts session cookies and never reads an API key, so an agent structurally cannot authorize its own proposal. Reject one and your note travels to the agent verbatim. Verdicts are reversible, and the latest human call stands.

Import your Linear or Jira backlog as evidence

Tracker integrations used to run one way: spec out, issue created. Now they read too. Point Pathmode at a Linear team or a Jira project and your open issues land in the triage inbox as evidence, deduplicated by issue URL, with bug-ish labels classified as friction and everything else as a request. No AI extraction, because issues are already structured. Every run is one undoable import: Undo deletes what nothing has linked to an intent and unlinks the rest, so a bad import is not a cleanup project.

Verification reads the pull request, not your summary

Verification used to grade a prose summary written by the party being graded: the evidence and the work had the same author. Name a pull request instead and Pathmode fetches the diff from GitHub, then grades each outcome, constraint, constitution rule, edge case, and verification check against what the code actually shows. The written summary is still accepted, and the prompt now says plainly that it is a claim rather than proof.

The assistant hands the spec off, not just writes it

Accept Finalize and the Socratic assistant reads your workspace's agent-connection state, then offers the step that actually applies: connect an agent, finish a setup nobody ever used, or hand the spec over now. The guidance comes from pure functions, so the model can discuss the next step but never invent one. This closes a measured gap: 65% of people who touch an intent reach readiness at least once, but only 31% of those ever take a visible handoff action. Work that already shipped gets no nudge, because every version of it reads wrong on something already built.

Current state: what the code does today

A spec can now say how the thing works today, not just what should change, and agents read and write the field over MCP as of server 1.10.0. It renders everywhere the intent travels: a Current State section in intent.md, a "do not regress this" block in .cursorrules, a line in the CLAUDE.md section, and a row in the Outcomes rubric. Fill it whenever the work changes something that already exists; leave it out for net-new capability. The tool surface is unchanged at 22 cloud and 7 local.

Removed

•Pushing an intent to GitHub Issues. The path was dead code, and a ticket is a copy that goes stale the moment the spec changes. GitHub still reads your repo for Implementation Context, hands the live spec to coding agents over MCP, and flips the intent to Shipped when a PR referencing it merges. Linear and Jira still create issues.

Improvements

•A "Connect a repository" step joined the setup checklist: the codebase analyzer was gated behind a GitHub binding that no onboarding surface ever mentioned
•Pasting a doc full of verbatim customer quotes and measured numbers no longer launders them into unverified assumptions: quotes land as quotes and metrics as metrics, tagged to the material they came from

August 22, 2026

Features

Your agent wrote a spec. Now it comes to you for review.

When a coding agent creates an intent through the API or MCP, Pathmode now knows: the spec carries agent authorship, lands at the top of the workspace judgment queue as "Your agent wrote a spec while you were away", and the workspace owners get an email, at most one per day, however busy the agent was. Opening the spec counts as your review and clears it from the queue. The one thing only you can do about a plan your agent committed to is check it, so that is the one thing Pathmode asks of you.

Outcome tracking: did the shipped thing work?

A shipped intent now shows its outcomes with a Record affordance: capture the baseline, the measured value, and whether the target was met. Product Home's Shipped Outcomes panel turns from a count into a scoreboard ("1 of 2 met · 1 measured"), and intents whose outcomes nobody has measured surface in the judgment queue. Measurements are keyed to the outcome itself, not its position, so reordering outcomes never re-points history.

Decisions you can write, edit, and record from anywhere

The decision log is no longer conversation-only. Add, edit, or remove decisions directly in the spec document, including what was ruled out and what would reopen the call. A new decisions API endpoint lets a decision made in a PR review, a Slack thread, or by an agent mid-build land on the same audit trail, with cited evidence verified against your workspace so provenance can't be fabricated. And when evidence a decision cites changes or disappears, the judgment queue tells you which decisions are worth revisiting.

Pathmode asks your role once, then shapes itself around it

The first interview now opens with a single question: what's your role? Product and founder answers steer the AI toward problems, outcomes, and evidence; engineering answers steer it toward constraints, failure modes, and verification. Product-side roles also get a setup path that ends at importing evidence and sharing for review, not at configuring an MCP server. Asked once, ever; changeable any time in your profile.

Install Pathmode into Claude Code with one command

There is a Pathmode plugin for Claude Code now. Run /plugin marketplace add pathmodeio/claude-plugin then /plugin install pathmode@pathmode and you have the MCP server and all seven skills together, with no config file to hand-edit. Skip the API key and it runs in local mode: specs live in intent.md in your project, nothing leaves your machine, and 7 local tools work. Add a key and the same install becomes the full 22-tool workspace. The key goes to your OS keychain, never into a config file.

Fixed

•Marking an intent shipped no longer demands a verification check you already added: the lifecycle gate now recognizes checks created in the current editor, not just the legacy format
•Unsubscribe links now verify their signed token instead of trusting the user id in the URL
•Recording an outcome measurement requires a writer role in the workspace; viewers can read but not write

Improvements

•Evidence arriving through connectors (support-ticket sync, Slack capture, the ingest API) is now labeled with integration origin instead of masquerading as manually entered
•The product setup checklist can actually finish now: team and agent-connection detection work, and the card retires itself when you're done
•Developer docs: the decisions endpoints are documented, and the implementation-findings endpoints, previously documented but rendered nowhere, are visible on /developers

August 21, 2026

Features

The keyless install we advertised now actually works

We published an install snippet under the words "No API key needed" that never entered local mode. Local mode was set by a flag the snippet omitted, so a keyless user got the cloud path with no client: every tool failed, including the four that read intent.md. The spec was write-only. Local mode is now inferred from the absence of a key rather than a flag, and a keyless agent sees the 7 tools that work instead of 22 of which 15 can only refuse.

Fixed

•Saving twice in one conversation no longer destroys the first spec: a save with the same id updates it and bumps the version, and a different id is refused unless you say overwrite explicitly
•intent.md round-trips. Every section used to truncate to its first line when read back, so three outcomes returned as one and Scope vanished entirely. Decisions had no reader at all and now have one
•The setup command no longer exits with an error when you have no API key, which made the documented first step of onboarding a wall for exactly the people it was written for

June 21, 2026

Features

Draft your first intent before you sign up

Describe what you're building in your own words and Pathmode drafts your first intent spec as a proposal, right on the landing page. It reads your description into product context, then proposes an objective and outcomes you can accept or sharpen. The first intent anchors to real signals only: any assumptions you add stay grounded as labeled beliefs, they never pass themselves off as evidence. Signing up commits exactly what you shaped.

Paste a doc to build product context

Paste a PRD, a positioning page, or rough notes and Pathmode extracts your product context: vision, north star, audience, guardrails, and the team's beliefs about its users. A strength meter shows how grounded that context is, so you can see what's thin before you build on it. Re-ingesting a second doc merges instead of clobbering: empty fields fill, conflicts come back as suggestions you choose, and guardrails append and dedupe. Beliefs land as labeled assumptions, never as facts.

The judgment loop: building writes back to the spec

Verification is a feedback loop now, not a test list. A spec can carry verification checks, grouped by kind with a pass or fail status, and they travel into every handoff: the agent prompt, the Claude Code and Cursor exports, and the local MCP export. When building a spec contradicts it, an agent records an implementation finding, the inverse of a decision: what the spec assumed versus what the build revealed. Open findings ride into the next agent's prompt so the loop converges instead of repeating a dead premise, and a finding that falsifies a check flips it to failing in the same write. Reconcile or dismiss each one in the editor. The method is written up in Verification Is a Feedback Loop.

sync_context: round-trip your intent into CLAUDE.md

The Pathmode MCP server can now write canonical context back into your CLAUDE.md or AGENTS.md, in place and idempotently. The Pathmode block is regenerated from the source of truth and merged between markers, so re-running updates the section instead of appending a duplicate, and an unchanged spec is a no-op with no noisy diff. Your repo's intent context stays generated from the source, never hand-maintained.

Fixed

•Archived evidence no longer reaches an agent prompt or export: signals you dropped stay dropped instead of riding along to the agent

Improvements

•Socratic sharpening on the warm landing screen: one pointed question to tighten a vague description before it becomes your first intent, because the pre-signup flow has no evidence to push back with yet
•Product Home shows a read-only product-context strength meter, so you can see how grounded a product's context is at a glance
•A substantial paste on the landing hand-off auto-extracts and skips the redundant paste box
•The new pre-signup AI endpoints (description sharpening, assumption drafting) are bot-challenged and rate-metered alongside the scan flow

June 18, 2026

Features

IntentSpec v1.2 — scope and verification are first-class

The open IntentSpec standard is now v1.2. Two optional fields join the format: scope — an inScope/outOfScope fence bounding what a change may touch — and verification, how each outcome is confirmed: the fastest automated check, a manual fallback, and the observable production signal. Both are additive and backward-compatible; the spec and JSON Schema are updated to match.

June 15, 2026

Features

Evidence is a property-driven collection now

The Evidence board behaves like a real database. Group the List by any property — type, severity, source, status — or flip to a board layout for an instant Kanban over whatever you grouped by (group by severity + board = a severity Kanban, for free). Open any signal and the detail panel is a live page: edit text, type, and severity in place, and link or unlink intents inline with a search-and-rank picker instead of a modal round-trip. The row is the page; nothing is locked behind an “Edit” mode.

Pull evidence from any MCP server

Connect a remote MCP server as an Evidence source and Pathmode reads its content into the board as AI-extracted, typed signals — the consumer side of the same MCP plumbing that powers our coding-agent handoff. SSRF-guarded, resources-only, manual sync for V1. Add one from Add Evidence → MCP source; synced items carry a “Synced” provenance label.

Home and Product Home are judgment queues

The workspace Home no longer opens on a static product catalog. It opens on “Needs your judgment” — specs at the readiness gate, critical friction with no intent, specs with an open AI question, untriaged evidence — each row ending in a verb (Review / Decide / Answer / Triage), with “Jump back in” and “New this week” below. Product Home gets the same treatment: a deduped list of the product's open gaps leads, the readiness score is demoted to a quiet line, and an empty product never shows a false “every spec is agent-ready.”

Edit your scanned workspace before you sign up

The scan “preview” is now a real, editable draft workspace. Scan a URL and you land in the actual product surface — seeded Product, Evidence, inline-editable header — and shape it in place. Sign-up happens in an inline drawer without leaving the page, and “Sign in to save” commits exactly what you saw. What you preview is what gets saved.

Teammates auto-join by email domain

Turn on domain access in workspace settings and teammates who sign up with your company email join the workspace automatically — as viewers, no invite required. Available on the Team plan, and only for a domain your workspace has claimed (a verified owner or admin on the same domain), so no one can vacuum up users from a domain they don't belong to. Verified emails only; personal providers are excluded.

Ask an AI about Pathmode

New section on the comparison, product-teams, competitor, homepage, and pricing pages that deep-links to Claude, ChatGPT, and Perplexity with a question about Pathmode pre-filled — one click opens the chat app ready to send. Competitor pages ask the comparison directly. No backend, no keys; just go ask the models yourself.

New essay: The Cost of Being Worth Using

AI helped 100,000 developers ship 30% more software. The number of people using it didn't move. Building got cheap; being worth using didn't — so product judgment is the scarce resource. Read the post →

Changed

•Removed the blocking post-signup "Which lens do you bring?" modal — it gated the very first workspace screen for every new user. Role still feeds the AI and is settable in Profile; we'll elicit it inside the conversation instead
•Legacy /journey-map URLs now redirect to /product-teams

Fixed

•Closed cross-tenant isolation holes in the Atlassian/Jira integration — an unbound Forge install could resolve another tenant's intent, and any admin could claim other tenants' installs. Both fixed with live host-authenticated binding and 15 regression tests
•The Anonymization Firewall now fails closed — if redaction can't run, data is held back rather than passed through
•Signup analytics no longer drop OAuth events to a malformed ID, and the signup form can no longer double-submit
•Fixed an infinite re-render loop in evidence suggestions, and a failed workspace load no longer dumps you into the create-workspace flow

Improvements

•Settings and the Intents board got a Notion-lens pass — a shared SettingRow primitive, three-tone color drain, and quieter chrome so your content leads
•Skip the scan and create your first product from the activation cards, and Pathmode now opens the intent editor for it automatically instead of dropping you on an empty product page
•Account deletion is no longer forensically silent — it emits an account_deleted event and an admin notification with churn context, and new accounts now derive a display name from your email instead of a generic "User"

June 12, 2026

Features

Evidence is a canvas now, not a form

Adding a signal no longer means a paste box and an “Analyze” round-trip. The Evidence board opens to a composer row: type a line and Pathmode types it for you — friction, quote, observation, metric, or request — or press / to pick the type yourself. Paste a whole support ticket and it extracts into multiple typed signals inline, right under the composer, where you keep or drop each one before they land. No modal, no detour.

Edit evidence in place

Hover any row to edit its text, type, and severity right where it sits — no panel, no navigation. The board is the interface; your signals are the content, not rows in a form.

Improvements

•Empty products now open with illustrative typed signals you can adopt with one click — you see the shape of a populated board before you have one, instead of reading an abstract description of it
•The add-evidence composer follows you across the List, Clusters, and Flow views; Inbox stays a focused, keyboard-driven triage lane and Sources stays document-first
•Typing a single line runs through the same model as a full paste, so a one-off observation lands as a properly typed signal without extra steps

June 8, 2026

Features

The Playbook gets an advanced tier

Three new guides go deep on operating intent at scale: The Product Constitution (rules that ride every spec at handoff), Verification Is a Feedback Loop (the four legs a test list misses), and Wire Pathmode Into Your Coding Agent (the MCP + skill-pack handoff, ticket to verified). The Playbook now opens with a “Start here” path for newcomers and a “Go deeper — Advanced” rail for practitioners already shipping specs.

Developer docs, single-sourced from the live spec

The /developers reference is now generated from the live REST API and MCP server definitions, with drift guards so the tool list, arguments, and OpenAPI schema can't fall out of sync with what actually ships.

Fixed

•Health Metrics — your "what must not degrade" guards — now travel in the Markdown agent prompt, not just the CLAUDE.md and .cursorrules exports, so regression guards reach every handoff
•Several broken "Get started" links in the Playbook guides now point to onboarding instead of returning a 404

Improvements

•The Playbook reads as a curriculum instead of an archive — guides follow a learning path with previous/next and related links, and difficulty now reads as a depth ladder (Advanced earns a single accent; Beginner is quiet) rather than a red/yellow/green traffic light
•The IntentSpec is taught in full across the Playbook, glossary, and comparison pages — all eight parts an agent actually receives (now including Scope and Health Metrics, with the placeholder "Goal" retired), so what you read matches what Pathmode hands the agent

June 6, 2026

Features

Constitution v1 — rules carry their judgment

The workspace Constitution is no longer a flat checklist. Each rule now carries the judgment behind it — a rationale, a scope, an enforcement level (advisory, required, or blocking), and worked examples — edited in a new master-detail manager with a per-rule “how agents see this” preview. Enforcement and rationale thread through every place an agent reads the constitution: AI Spec Review, exports, and the execution prompt, which now tags each rule [BLOCKING] or [advisory]. Agents respect the rule and know why it exists.

Readiness is a contract, not a suggestion

Whether a spec is ready to review or ship is now a single deterministic check the AI shows and can't argue its way around. The Spec panel's coverage indicator renders the exact gate state — title, objective, outcomes, constraints, edge cases, verification, plus advisory evidence — with the precise blocking reason on each row. Coverage dots can no longer read “filled” while the gate says blocked, and the AI stops re-declaring “ready to ship” on a spec that isn't. Backed by replay harnesses and a real-transcript eval so prompt changes are measured, not vibed.

MCP server v1.6 — skill pack + Claude Managed Agents

The Pathmode MCP server gained two things. A bundled skill pack — seven Claude Code skills (compile-intent, grill-intent, verify-intent, review-against-intent, and more) that auto-trigger from natural language — installable with npx @pathmode/mcp-server install-skills. And a new outcome-rubric export that renders an intent as a Claude Managed Agents “Outcomes” rubric — a writer description plus an independent grader rubric built from your outcomes, edge cases, constraints, and verification. Published to npm as @pathmode/mcp-server@1.6.0.

Fixed

•Intent conversations no longer dead-end when the AI model errors — a retry path appears instead of a stuck "Thinking…" state
•A fast conversation can no longer fork a phantom duplicate spec, and autosave no longer carries one intent's baseline into another
•AI streaming no longer drops updates that land on a chunk boundary
•Free-text scope entered in conversation now coerces into the structured scope and renders in the spec
•The re-engagement greeting no longer stacks when jumping between phases
•Demo requests submitted from the site are no longer silently dropped by row-level security

Improvements

•Spec panel restructured to read top-down like a document — title, a quiet property block (Status / Execution / Codebase), then the body — instead of a fixed toolbar bolted above your content. Metadata recedes so the spec is the artifact
•Conversation-first editor now runs on a single document store — one source of truth for the spec instead of two competing copies — eliminating a class of save races and stale-state bugs
•Constitution governance templates now ship with enforcement levels and rationale on each constraint, so seeded workspaces start with operational rules rather than bare imperatives
•Hardened the public site-scan endpoint against SSRF, with per-redirect-hop URL and connect-time DNS validation; added rate limiting across more mutation endpoints and replay-protection for inbound integration webhooks
•Patched dependency security advisories (Next.js, xlsx, react-router) and tightened database privileges on internal functions

May 27, 2026

Features

IntentSpec v1.1 — specs carry their evidence

The open IntentSpec handoff format is now v1.1. A new optional evidence field lets a spec carry the user signals behind it — the friction, quotes, and metrics that justify its outcomes, edge cases, and constraints — so intent travels as evidence-backed judgment, not a bare contract. The bump is additive and backward-compatible. The standard now also lives at its own home, intentspec.org, so the schema resolves at its canonical $id.

Category comparison pages

New category-level comparison pages — /vs/issue-trackers and /vs/spec-as-contract — sit above the individual vendor breakdowns, with each vendor page linking up to its archetype. Added Linear as a product-management comparison.

Fixed

•Scan bot-detection now lets through requests with no challenge token (usually an ad-blocker or a script-load race) instead of blocking real users with an unactionable "Bot detected" message — genuine bots are still rate-limited
•Intent editor — reopening an existing spec no longer re-fires turn analytics for messages loaded from history, and silent autosave failures are now tracked

Improvements

•Onboarding — a "skip the scan and start with an empty workspace" option (the workspace still seeds a sample product), returning users now land back in their existing workspace instead of a duplicate, and the same skip option appears as an escape hatch when a scan fails
•Positioning refresh across /philosophy, /use-cases, /patternry, /comparison, and /integrations/github — the product judgment layer, the discovery loop (discovery doesn't end at ship), and codebase-as-evidence (specs ground against your connected repo while you draft)

May 25, 2026

Features

Implementation Context

Every Intent Spec can now read your codebase. Click Analyze codebase on any spec and Pathmode shallow-clones the bound GitHub repo, identifies the files this change would touch, summarizes what exists today, flags risks, and suggests verification — all anchored to specific paths. The spec doesn't have to be guessed at anymore. Available today on every paid workspace; install the GitHub App and set a default repository per workspace or per product. Read the full post at /launch/implementation-context.

Agent exports carry code context

When you export a spec to Claude Code, Cursor, or via the MCP get_agent_prompt tool, the exported payload now includes the spec's Implementation Context — relevant files, current behavior, risks, verification suggestions. The receiving agent starts grounded in what already exists, instead of discovering it through tool use.

GitHub product-level repo overrides

A product can now point at a different repository than the workspace default. Useful when a workspace owns multiple codebases — e.g. an internal monorepo for the core product and a separate marketing-site repo. Configure per product under product settings → Code binding.

May 21, 2026

Features

Scan-first Onboarding

Paste a URL on the landing page and Pathmode reads your public positioning into a seeded workspace — a Product, Evidence quoted verbatim from your site, and a few questions to help you draft your first Intent. Anonymous scan, editable preview, sign-up gates the commit. Nothing is saved until you approve it. The landing hero is now the URL input — type and submit to scan live.

Multi-product Disambiguation

Scans of portfolio sites (Salesforce, Atlassian, AWS) ask which product you're working on before drafting context, then re-scan the chosen subproduct so signals and intents stay focused on what you actually build.

Description Fallback

JavaScript-heavy and login-walled sites get a paste-a-description path that runs the same extraction on your own words. The original URL stays attached as Evidence provenance.

Site-Scan Banner

Seeded workspaces show a one-time "Draft your first Intent" prompt on the Product page that hides once you've authored one.

Changed

•Every "Get started" / "Start for free" button on the public site now opens /onboarding/scan instead of the AuthModal — bookmarked /#signup URLs redirect too
•AuthModal becomes sign-in only — "Don't have an account?" links to the scan flow, so sign-up exists in exactly one place
•Sign-in without a workspace routes to /onboarding/scan instead of the legacy WorkspaceCreationModal

Removed

•First-run OnboardingHero — superseded by the scan-first flow; every new workspace now lands with a Product + Evidence already seeded

Improvements

•Setup checklist is scan-aware: "Seeded from your site" and "Draft first Intent" appear in the sidebar when a workspace was scan-seeded
•Two-tier product context: a scanned description satisfies the basic-context check, while Vision + North Star become an optional enrichment ("Strengthen product context") instead of a gating requirement

May 19, 2026

Features

Gemini 3.5 Flash

All AI surfaces on global workspaces now run on Gemini 3.5 Flash. 42% better on long-range multi-turn reasoning than the prior Flash generation — the dimension that matters most for the intent editor. The AI holds context across more turns and pushes back harder on vague intent. EU residency workspaces stay on Gemini 2.5 Flash; no Gemini 3.x Flash variants are available in europe-west1 yet.

May 11, 2026

Features

Pathmode for Jira — Atlassian Marketplace

Submitted "Pathmode for Jira" to the Atlassian Marketplace review queue. A Forge app that surfaces the linked Pathmode intent — objective, evidence, edge cases, status — inside every Jira issue. Authenticated with Atlassian-signed JWTs verified against the public JWKS; read:jira-work scope only.

Push to Jira → linked from inside Jira

The existing Push to Jira flow now creates an issue with the intent ID embedded in the description. The Forge panel on the resulting Jira issue resolves and renders the intent automatically — title, APPROVED/SHIPPED badge, evidence count, and a link back to Pathmode.

Bidirectional status sync

When a linked Jira issue moves to Done, the corresponding Pathmode intent flips to Shipped automatically, with an implementation note recording who shipped it. Native Jira webhook + connection-id capability token, no shared secret required.

Atlassian Forge App workspace binding

New section in Workspace Settings → Integrations for linking an Atlassian site to a Pathmode workspace. Detected installs surface as one-click claim cards; the bridge endpoint auto-registers installs on the first JWT-verified call so the binding flow works even when the Forge lifecycle webhook is missed.

Improvements

•Privacy policy gained a dedicated section covering Atlassian integration data flows — what we receive (cloud id, site URL, issue keys, account IDs), what we send (intent summary + description on push), how we authenticate, where it is stored, retention, and uninstall behavior
•New /support page with Pathmode for Jira–specific troubleshooting and security reporting contact
•Jira Test Connection now works after Save — server-side test against stored credentials instead of requiring the user to re-type the API token
•JiraIssueModal portals to document.body so it renders above the conversation panel in the Intent Editor

May 10, 2026

Features

AI Spec Review

A new review pass critiques your spec across six dimensions before you ship it to an agent: outcome quality, edge-case gaps, verification coverage, constitution conflicts, evidence grounding, and implementation drift. Two modes — Approval (gate before execution) and PR (post-implementation review).

Codex Integration Page

New Codex guide mirrors the Claude Code agent page. Both now share a single component and registry, so adding another coding agent is a data change, not a copy.

Use Cases Hub

New Use Cases index plus ten concrete walkthroughs — anchoring outcomes to evidence, auditing a spec for edge cases, founder ask to testable goal, support tickets to a prioritized spec, hand-off to Claude Code, and more.

Auto-Linked Glossary

Blog, playbook, and glossary content now auto-link the first occurrence of each glossary term. New entries propagate to old content automatically — no manual back-linking, no rot.

AI Turn Rating

Rate AI turns inline during an intent conversation. Per-turn signal flows into analytics so we can tune prompts on real data instead of vibes.

Workspace Ownership Transfer

Workspace owners can now transfer ownership to another member from the Danger Zone settings. Backed by a role-checked Postgres function so the transfer is atomic and safe.

Evidence Board 101 Playbook

New beginner playbook on running the Evidence Board as a diagnostic play — collect symptoms, spot patterns, decide where to operate — instead of a feedback dumping ground.

Blog Subscribe

Readers can now subscribe to the Pathmode blog. Email capture, confirmation, and rate-limited handling all in-app.

Changed

•Robots.txt moved from static `public/robots.txt` to dynamic `app/robots.ts` — adds disallows for /api/, /intent/, demo, and review routes, references the sitemap
•Dropped `offers` from SoftwareApplication structured data — Pathmode is SaaS, shopping-result fields do not apply

Removed

•Legacy Figma plugin package (was drifting from the current intent model)
•Legacy "Journey Mapping 101" playbook — replaced by Evidence Board 101
•Standalone `ClaudeCodePage` component — replaced by the shared `AgentIntegrationPage` used by both /claude-code and /codex

Improvements

•Spec Panel — Refactored, splitting execution hand-offs (Jira / Linear / Build Queue) and lifecycle controls (status, verification, review) into focused components. Smaller surface, fewer re-renders
•Intent Quality scoring centralized in one library so the Spec Panel, AI Spec Review, and readiness checks all use the same rubric
•Intent Interview JSON schema (with tests) replaces implicit field-name agreements between AI and client
•Glossary entries now cross-link to each other and to core terms — a small built-in knowledge graph
•New unified workspace integrations API across Jira, GitHub, Linear, and Slack with proper credential redaction
•Workspace settings — new Rename and Export Context endpoints, plus tracking for conversation-fired AI guidance rules
•Landing page hero, copy, and section structure tightened around "know what to build before you build it"

April 30, 2026

Features

First-Run Workspace Onboarding

New empty-workspace onboarding hero asks for one concrete product problem, creates the first Product and Intent, and sends the seed straight into the Intent Editor. Fresh users now see Pathmode form a spec immediately instead of landing in an empty workspace.

Onboarding-Aware Intent Conversation

The Intent Editor now supports onboarding mode with an open spec panel, seed handoff through session storage, first-response analytics, and a softer first AI turn that still drafts an objective right away.

Improvements

•Free plan now includes 3 editor seats (up from 1) — small teams can get started without hitting the paywall
•Product creation now returns full metadata, allowing onboarding and analytics flows to tie created products to follow-up intents without extra lookups
•Paid-plan CTAs open the in-app contact modal when billing is not enabled, keeping interested teams inside the Pathmode experience
•Updated primary landing CTAs to "Start for free" and tightened homepage messaging
•Simplified product demo animation state to reduce timer/state drift
•Onboarding analytics across the full activation funnel — hero views, submissions, skips, first AI response, and first spec update

April 6, 2026

Features

Intent Readiness Scoring

Pathmode now evaluates whether your spec is ready to hand off to an AI agent. Six blocking checks cover title, objective, outcomes, constraints, edge cases, and verification; supporting evidence is reported separately as an advisory signal.

Smarter Context Interviews

The product context builder runs a deeper interview flow, producing richer product context that feeds into every spec your team writes. Better context in, better specs out.

Agent Prompt Generation

The MCP server now generates full execution prompts for intents with readiness checks. AI agents get structured instructions with objectives, outcomes, constraints, and verification steps.

Plan Changes & Team Management

Workspaces can now upgrade, downgrade, and manage team members directly from billing settings. Full Lemon Squeezy integration for checkout, portal, and subscription sync.

Fixed

•Billing status hook, checkout flow, and portal redirect issues across multiple plan types

Improvements

•API Reliability — Rewrote intent API routes to share a single, tested handler layer with consistent validation
•MCP Server — Expanded tool surface: enhanced local file reading, better intent compilation, improved export formatting
•Context Health — Updated indicators so teams see at a glance which products have strong context and which need attention

March 29, 2026

Features

Functional Roles

Introduced role-aware Pathmode onboarding and profile settings for Product, Engineering, Design, Founder, and Mixed. Pathmode now tailors AI interview prompts and question flow based on the lens you bring to the work.

Improvements

•Role-aware onboarding now prompts first-time users to choose their lens from workspace home
•Functional role selection is saved to the user profile and can be updated later in Profile Settings
•Added database support for functional_role with a safe default and validation constraint

March 28, 2026

Features

Evidence Inbox

The biggest update since Pathmode went live. New dedicated layout mode for triaging evidence at speed. Single-item focused view with keyboard-driven actions: j/k to navigate, a to accept, d to dismiss, l to link to an existing intent. Pagination-aware — advances to the next batch automatically. Includes a Link to Intent modal that ranks existing intents by keyword match.

AI Intent Synthesis

New "Synthesize from Evidence" workflow: select evidence items and AI proposes intent specs grounded in real user problems. A new intent chooser modal lets you pick between blank/template creation and evidence-based synthesis. Also added Suggest Relations — AI proposes dependency relationships between intents.

Structured Outcomes

Outcomes upgraded from plain strings to structured objects with stable UUIDs and optional MoSCoW priority (must/should/could). Evidence anchor keys now reference outcome UUIDs instead of array indices, making anchors stable across reordering and insertion.

Intent Scope

New scope field on IntentSpec with explicit inScope and outOfScope lists that tell AI agents what they can and cannot touch. Supported in the editor, API, and MCP server.

Intent Engineering vs Context Engineering

New blog post exploring why intent is upstream of context when building with AI. Teams optimize AI briefing before figuring out what to ask — better context just helps AI fail more efficiently.

Changed

•Removed beta banner — header now shows "Pathmode has launched!" announcement
•Restructured workspace settings with new API Keys tab

Improvements

•MCP Server — Structured outcome support, live quality checking with explicit rubric, scope field support, product strategy in exports
•Document View — Keyboard navigation in outcome lists, structured outcome rendering with priority labels, provenance view integration
•Evidence Board — New Inbox and Sources layout modes, layout selection in sidebar sub-menu, triage status counts in badges
•PostHog — Server-side event tracking with session and distinct ID headers

March 21, 2026

Features

Conversation-First Intent Editor

Complete redesign of the intent editing experience. Spec crystallizes from dialogue rather than form fields. Natural language conversation is now the primary surface, with a collapsible "Spec panel" sidebar showing structured output. The AI displays spec updates with immediate auto-apply, visual indication of what changed, and a 10-second undo window.

ThinkingQuality Scoring

4-dimensional assessment (specificity, testability, coherence, tension) scored 0-3 each, replacing the previous SpecCompleteness metric for more nuanced feedback.

Evidence-Anchored Specs

AI auto-links outcomes and edge cases to product evidence items. Specs display inline badges showing evidence links that persist across updates.

Changed

•Legacy form-based editor available via ?mode=form query parameter; conversation-first is now default

Fixed

•Intent editor save flow to properly persist spec updates and undo history
•Navigation issues between intent editor and product home

Improvements

•Intent Editor Performance — Consolidated state machine and reduced re-renders
•UI Consistency — Spec panel uses workspace design system with gray tones and no decorative hover effects

March 14, 2026

Features

Constraints Document Discoverability

The constraints document feature is now surfaced across four key touchpoints. Upload directly from the Context Builder guardrails phase. See a tip when creating a new intent. The AI mentions the feature when no constraints exist. And the Product Home always shows a CTA to add one.

Improvements

•Context Builder guardrails phase now includes a file upload button for constraints documents (PDF, DOCX, TXT, MD, CSV)
•New Intent modal shows a tip about constraints documents when none is uploaded for the product

March 11, 2026

Features

Smarter, Faster AI Conversations

Major overhaul to the Intent Editor and Context Builder conversations. The AI now responds instantly with real-time streaming, stays on topic instead of repeating itself, and progresses naturally through the spec-building process. Selecting quick-reply chips sends your answer immediately — no extra click needed.

Fixed

•AI would loop on the same topic or re-ask questions you already answered
•Conversations could get stuck on "Thinking..." with no way to recover — retry options now appear on failure

March 9, 2026

Features

PostHog Analytics Integration

Full-stack analytics with client-side event tracking and server-side error capture via PostHog EU, routed through a reverse proxy.

In-App Feedback System

"Send feedback" in the sidebar now opens a modal that emails the team directly via Resend (replaces mailto: link).

Product Creation Onboarding Flow

After creating a product, a guided welcome step offers "Get Started" (Context Builder) or "I'll explore on my own".

Changed

•Evidence Board redesign — Tabbed layout (Evidence / Sources), sort dropdown, more compact cards, dedicated "Suggest intent" button
•Intent Editor spec panel widened from 480px to 560px for better readability
•Product Home — Strategy section split into compact two-column card (Vision | North Star); tighter spacing throughout
•Insights Digest — Renamed from "Signals Digest"; critical items now use amber highlights; "View all" links to Evidence
•Hero demo — Streamlined from 7 steps to 6 (Signals step removed)

Removed

•Entire Signals system — Views, hooks, services, API routes, cron job, MCP tools, Slack notifications, and all UI references
•Glyphex analytics tracker — Replaced by PostHog
•Outcome quality scoring — Removed per-outcome quality badges (Testable/Decent/Vague) from the Intent Editor

March 6, 2026

Features

Hand-Drawn Illustrations

Added custom hand-drawn editorial illustrations to the Philosophy and Product Teams pages. The ink-and-teal style matches the existing blog illustration series — depicting the traceability pipeline (Friction → Evidence → Intent Spec → AI Agent → Shipped) and the three-role collaboration model (Discover, Define, Deliver).

March 5, 2026

Features

Landing Page Refresh

Refreshed the landing page with a new hero headline (“Know what to build before you build it”), an updated interactive product demo that reflects the current UI across all 7 screens (Products, Home, Signals, Evidence, Synthesize, Intents, Export), and a tighter page structure — down from 11 sections to 9. Removed redundant diagram and Living Specs sections. Moved the Context Layer section higher and Metrics closer to the CTA.

Philosophy Page Rewrite

Rewrote the Our Approach page with a horizontal pipeline flow, three core convictions, and streamlined five-stage walkthrough. Replaced the confusing vertical diagram and removed the redundant product demo embed. Every section is now scannable in under 5 seconds.

Improvements

•Navigation link renamed from "Our Philosophy" to "Our Approach"
•Hero demo now shows workspace vs. product sidebar modes
•Each demo step includes a description bar explaining the screen
•Removed unused IntentEngineDiagram and WhyHowWhenPositioning imports from landing page

March 3, 2026

Features

Gemini 3 Flash & Global AI Endpoint

All AI features now run on Gemini 3 Flash, Google's latest model, via the global Vertex AI endpoint. This means better reasoning across context interviews, spec generation, and evidence analysis. The AI Processing Region setting lets workspaces choose between Global (best availability, latest models) and European Union (data residency compliance in europe-west1).

March 1, 2026

Features

Living Specs — The Spec Lifecycle

Specs are now living documents. Every spec in Pathmode is grounded in evidence, reviewed by humans, consumed by agents, and improved by outcomes. This release closes the loop between what you plan, what you ship, and what actually happened.

Make specs feel alive — grounded in evidence, reviewed by humans, consumed by agents, and improved by outcomes. That's the loop that makes Pathmode indispensable.

Evidence-Anchored Specs

Specs now link evidence at the section level. Each outcome, edge case, and constraint can reference the specific user evidence that justifies it. Anchors are visible inline as small badges showing the count of backing evidence, and expand to reveal the actual quotes, metrics, and observations that drove each decision.

Spec Review with Evidence Backing

The public spec review page (shared via token) now surfaces evidence anchors, problem severity, and health metrics. Reviewers see exactly which outcomes are backed by evidence and which are assumptions. Comment buttons are always visible on mobile for better touch targets. Unresolved comment count shows in the sticky header.

Reactive Signals

Signals are no longer manual. When new evidence is created, Pathmode automatically matches it against existing approved and validated intents using keyword and tag overlap. Matches appear as “Evidence Match” signals in the Signals view with one-click linking. The sidebar nav shows an active signal count badge. Five signal types are now persisted: evidence matches, freshness alerts, loose evidence, stale intents, and alignment drift.

Agent Verification Loop

Shipped specs can now be verified by AI. Click “Verify with AI” on any shipped or verified spec, provide an implementation summary, and Gemini 2.5 Flash grades every outcome, constraint, constitution rule, and edge case as pass, fail, or unclear. Results show inline with per-item reasoning, grouped by category. Failed verifications automatically create signals. Build Queue cards show verification status and score at a glance.

Improvements

•Evidence freshness indicator on specs — shows amber warning when linked evidence is older than 30 days
•Signal count badge in sidebar navigation
•Verification score badges on Build Queue kanban cards
•Verification failure signals with upsert dedup — re-running verification updates the signal instead of creating duplicates
•Updated AI verification model from Gemini 2.0 Flash to Gemini 2.5 Flash

February 22, 2026

Features

Intent Compiler for Claude Code

Shipped the Intent Compiler — a zero-config MCP tool that turns Claude Code into a Socratic product thinking partner. Describe a problem, paste a support ticket, or explain what's broken. Claude challenges vague language, asks one pointed question at a time, and builds a structured intent spec through conversation. When the spec is ready, it saves intent.md to your project and optionally exports as .cursorrules or CLAUDE.md. No API key or signup needed.

MCP Server v1.2 — Works Without API Key

The Pathmode MCP server no longer requires an API key to start. The Intent Compiler tools (compile-intent prompt, intent_save, intent_export) work entirely offline. Team features (dependency graphs, workspace strategy, governance) activate when you add an API key. Published to npm as @pathmode/mcp-server@1.2.2.

Official MCP Registry Listing

Pathmode is now listed on the Official MCP Registry as io.github.pathmodeio/mcp-server. Anyone searching for intent engineering, spec building, or product development tools can now discover and install Pathmode directly.

Intent Compiler Page

New /intent-compiler marketing page with interactive terminal demo, tabbed output preview (intent.md / .cursorrules / CLAUDE.md), 30-second setup guide, and REPL-to-Runtime comparison showing how the free compiler connects to the full Pathmode platform.

Improvements

•MCP server README rewritten to lead with Intent Compiler and zero-config setup
•API key changed from required to optional in manifest.json
•Fixed pre-existing TypeScript error in MCP server api-client.ts

February 18, 2026

Features

Cursor Directory Listing

Pathmode is now listed on the Cursor Directory. Install the Pathmode MCP server directly into Cursor with one click — giving your AI coding agent structured intent specs, dependency graph analysis, workspace strategy, and auto-generated .cursorrules from real product context.

February 17, 2026

Features

Integrations Hub

The workspace now supports four external integrations, turning Pathmode into a central hub for product signals. Connect your tools in Workspace Settings → Integrations and evidence flows into your Spaces automatically.

Google Analytics Integration

Connect your GA4 property via OAuth and sync analytics data directly into the Evidence Board. Pathmode fetches five report types — page performance, funnel analysis, event tracking, user acquisition, and engagement overview — then uses AI to interpret the raw metrics into actionable evidence items: friction signals from high bounce rates, metric data points, and behavioral observations. Daily auto-sync keeps your evidence fresh.

Zendesk Integration

Import support tickets as evidence items. Connect your Zendesk account, choose a target Space, and Pathmode syncs closed tickets through AI extraction — turning customer conversations into structured friction points, quotes, and feature requests.

GitHub Integration

Link your GitHub organization to connect repositories with your workspace. Pull requests can be linked to Intent Specs, closing the loop from product intent to shipped code.

Linear Integration

Connect Linear to link issues and projects with Intent Specs. Track how product decisions flow from evidence through specs into engineering execution.

February 14, 2026

Features

Claude Code Integration Page

New dedicated Claude Code page explaining how Pathmode connects to Claude Code via the MCP server. The page covers the full closed-loop system — from evidence collection through intent specs to phase-gated agent execution and verification. Includes interactive terminal mockups, the complete 12-tool MCP reference, and a step-by-step setup guide.

February 7, 2026

Features

Hero Animation as Video with Remotion

Built a shareable product demo video directly from our React hero animation — no screen recording needed. Using Remotion, we converted the existing phase-based hero component into a frame-perfect 1920×1080 video composition. All setTimeout chains became frame calculations, all useEffect animations became interpolate() calls — same JSX, same Tailwind, same SVGs. The result is a 37-second MP4 showing the full Pathmode workflow: Friction Inbox → Journey Map → AI Spec Generation → Export to Agent.

Improvements

•Added Remotion video rendering pipeline with preview and export scripts
•Downloaded and bundled Inter and Merriweather fonts for server-side video rendering

February 6, 2026

Features

IntentSpec Open Standard

Launched IntentSpec as an open standard for spec-driven development. The new IntentSpec page documents the schema, integration guides for AI agents (Cursor, Windsurf, Claude Code, GitHub Copilot), and a GitHub Action for CI/CD validation.

About Page

Added a dedicated About page with the Pathmode story, company values, and founder bio.

Philosophy & Product Demo

New Philosophy page with an animated product walkthrough. The hero demo visualizes the full workflow: friction signals flying in from support tickets, analytics, and research — AI synthesizing them into structured Intent Specs — and one-click export to your coding agent.

Playbook Guides

Expanded the Playbook with new guides including "Support Ticket to Shipped Feature" and "Why Specs Fail". Added embeddable components for flow diagrams, comparison tables, and chaos wall visualizations directly inside guide content.

Export to Agent

Enhanced the Export to Agent modal with contextual data loading. Specs now include Constitution Rules, Journey Map context, and Workspace Strategy — giving AI agents the full picture when generating code.

Improvements

•Landing Page: Redesigned hero section with interactive product demo and updated value proposition
•Solutions Pages: Added solution-specific landing pages for Journey Management, Product Intent Infrastructure, and Enterprise
•Footer: Added links to About, Philosophy, Playbook, and Comparison pages
•Terms of Service: Updated publicity rights and terms
•Intent Editor: Multiple stability and UX fixes across the spec editing workflow
•Blog: Published new articles on intent-driven development and AI-native teams
•Invitation Flow: Improved account handling and workspace invitation acceptance

February 1, 2026

Features

Intent Spec Workflow

We've completely revamped the "Living Agent Loop". You can now go from a Journey Map friction point directly to a generated Intent Spec. The AI researches context, drafts the spec, and lets you refine it with natural language.

January 29, 2026

Features

Inline Friction Highlighting

Replaced list-based friction display with Google Docs-style inline highlights directly within research documents. Click a highlight to see the finding, severity, and synthesize intents.

Document Highlighter Component

New DocumentHighlighter with viewport-aware popover positioning that never gets cut off by the browser window.

Improvements

•Document View: Added read/edit toggle via eye/pencil icons
•Friction Pipeline: Replaced "Specs Shipped" stat with "Evidence Docs" count
•Interactions: Changed popovers to click-based triggering for better stability
•Navigation: Fixed "View All Friction Points" button behavior
•Persistence: Upgraded storage engine to support rich friction metadata (findings, tags)

January 26, 2026

Improvements

•New Journey Experience: Redesigned modal to prioritize "Start from Friction" workflow
•Journeys List: Refined list view layout to reduce visual noise
•Welcome Email: Updated messaging to align with "Intent Layer" philosophy
•Build Queue: Upgraded to Kanban board interface for better tracking

January 22, 2026

Features

Intent Graph

Introduced interactive graph visualization for intent dependencies and strategic alignment. Visualize how your intents connect and ensure they align with your workspace strategy.

January 18, 2026

Features

From Journey Maps to Intent Layer

We started building Pathmode as a journey mapping tool. The vision was simple: help teams visualize customer experiences and connect user research to real workflows.

But as AI transformed how teams build software, we noticed something. Journey maps weren't just documentation—they were becoming the source of truth that AI agents needed to ship the right features. The map wasn't the output. It was the input.

Today, Pathmode is the Intent Layer for modern product teams. We don't just visualize journeys—we synthesize structured Intent Specs from real user friction, then push them to the tools that build. Cursor, Linear, Jira. The journey map is now a coordinate system for your entire product.

Intent is the new code. Specs are the new handoff. The map is the new constitution.

January 11, 2026

Improvements

•Admin Notifications: Implemented email alerts for new sign-ups
•UI/UX: Redesigned Blog Index page with responsive grid and author metadata
•Architecture: Decomposed MainApp for Next.js App Router migration
•Docs: Updated competitive landscape analysis
•Fixed: Resolved modal navigation issues on public pages

January 8, 2026

Features

Anonymization Firewall

We've added a powerful privacy layer for research data. You can now enable the Anonymization Firewall in your workspace settings to automatically detect and redact PII (Personally Identifiable Information) from your interviews and documents.

This feature uses a zero-retention AI pipeline to replace names, emails, and phone numbers with generic placeholders before data is ever saved to our database, ensuring full compliance with strict privacy requirements.

Improvements

•Added PII detection toggle in workspace settings
•Updated data ingestion pipeline with pre-processing hook

January 1, 2026

Features

Interactive Live Demos

Explore fully-generated journey maps without signing up. We added interactive scenarios like "Autonomous Ride-Sharing" and "B2B SaaS Onboarding" to the landing page, demonstrating the full capability of AI-generated insights and specifications.

Improvements

•Smart Caching: Implemented intelligent local storage caching for public viewers, ensuring instant load times for AI artifacts like Storyboards and Proto Specs
•Optimized Public View: Revised staleness detection logic to prioritize cached content for read-only users, preventing unnecessary regeneration loops
•Robust AI Pipeline: Enhanced the generation engine with better payload management to reliably handle complex, data-heavy journey maps

December 29, 2025

Features

Integrations View & Live Embeds

Showcase your tool ecosystem with the new Integrations view. Embed live Figma prototypes directly into journey steps to keep designs synchronized.

Improvements

•Added "Integrations" to main navigation
•Added "Design Prototype" panel to Step properties for embedding support

December 28, 2025

Features

Specs View: Triage & Kanban

Redesigned the Feature Specs interface to split workflows into two distinct views:

Triage View: Review and approve new opportunities.
Kanban Board: Track specs from "Draft" to "Shipped".

Added an Archive workflow to hide deprecated or irrelevant specs.

Compact Research Dashboard

Refined the Research Dashboard for density. Key performance indicators are now grouped into a single row, providing an immediate overview of library health.

Hybrid Rendering Architecture

Re-architected the application core. Marketing pages now use Server-Side Rendering (SSR) for SEO and initial load performance, while the workspace remains a client-side SPA for interactivity.

Improvements

•Updated Research Dashboard visual hierarchy
•Implemented `useAppNavigation` for consistent routing state
•Resolved authentication race conditions with optimistic session hydration
•Fixed session persistence issues on refresh
• eliminated "Map Not Found" navigation errors
•Resolved client-side hydration mismatches
•Fixed React hook ordering stability issues
•Centralized modal state management

December 26, 2025

Features

Brand Identity Update

Refined the logo for better legibility at small sizes. The new mark retains the spiral geometry with cleaner lines and balanced weight.

Before

After

Improvements

•Updated favicon and app icons across the platform
•Unified spacing standards in navigation bars

December 25, 2025

Features

Feature Specs

Turn your journey maps into shipping software with the new Specs view. Automatically aggregate insights and journey steps into live feature specifications, manage acceptance criteria, and maintain full traceability back to your user research.

Journey Editor Refinements

We've redesigned the "Add Stage" experience for better usability. The button has moved from the bottom of the canvas to a dedicated vertical column at the far right of the timeline, styled with vertical text to match the grid structure. Plus, adding a new stage now automatically creates an initial "New Step" so you don't have to click twice to get started.

Improvements

•Privacy Overhaul: Removed Google Tag Manager and installed privacy-first GA4 with strict cookie consent
•Updated default workspace logo to use the Pathmode brand icon
•Various performance tunings and layout fixes in the editor canvas

December 24, 2025

Features

New "Product Teams" Landing Page

A dedicated page for high-velocity product teams. We've broken down the value of Pathmode for Engineers (Specs), Product Managers (Docs), Service Designers (Orchestration), and Product Designers (Research). Check it out →

Improvements

•Updated front page tagline: "Stop managing journeys. Start building them."
•Added new "For Product Teams" navigation link in footer

December 22, 2025

Features

Dynamic Hero Video

The landing page now features an immersive autoplay video in the hero section, replacing the static image. This provides an instant, dynamic preview of the Pathmode interface in action.

Improvements

•Optimized landing page hero performance with video assets

December 21, 2025

Features

New "Pathmode vs The Rest" Comparison

Completely revamped the comparison page. Instead of generic tables, we now have deep-dive breakdowns comparing Pathmode specifically against TheyDo (Management vs. Execution), Smaply (Service Design vs. Product), and Miro (Brainstorming vs. Structure). Compare tools →

Performance Tuning

Significant optimizations for the Journey Editor. We implemented intelligent debouncing for saves (1s) and throttled cursor tracking (100ms), making the editing experience buttery smooth even with active collaboration.

Improvements

•Fixed "zombie session" issue ensuring immediate and permanent sign-out
•Cleaned up security section iconography on landing page
•Updated site-wide navigation to new comparison breakdown

December 19, 2025

Features

Analysis Workbench

Introducing a powerful new way to connect research to your journeys. Open the research sidebar to view documents side-by-side with your map, and drag highlights directly onto steps to create insights, opportunities, or evidence instantly.

Vibrant Cartoon Storyboards

We've updated the storyboard generator to use a vibrant, flat cartoon style! Your customer journeys are now visualized with colorful, engaging illustrations that make storytelling even more fun and effective.

Improvements

•Updated AI prompt to request "vibrant cartoon style" for storyboard panels
•Enhanced image generation parameters for consistent flat design aesthetics

December 16, 2025

Features

Competitor Comparison Page

Added a detailed comparison page to help users evaluate Pathmode against other journey mapping tools. This transparency helps teams make informed decisions about their journey management toolkit.

Improvements

•Restored missing comparison page routing and functionality
•Fixed an issue where the /compare link was resulting in a blank page

December 14, 2025

Features

Redesigned Front Page with AI-Style Illustrations

Completely redesigned the landing page with minimalist, AI-style illustrations to create a clean and modern visual experience. The "Problem We Solve" section now features full-size pictograms for each problem area, making the challenges more visually engaging and easier to understand at a glance.

Unified Design Workflow Visual Updates

Enhanced the "Unified Design Workflow" section with step-by-step illustrations. Each of the three steps (User Research, Automated Journey Map, and Prototype Specification) now features a prominent illustration that visually communicates the workflow process.

Enhanced Trust & Security Page

Redesigned the Trust & Security page with a new hero section featuring a security illustration. The minimalist design creates a professional and trustworthy first impression, with the illustration prominently displayed above the "Security at Pathmode" title.

Dynamic CTA Section with Rotating Words

Added an animated rotating word effect to the CTA section headline. The phrase "The future of design is..." now cycles through "unified", "intelligent", and "seamless" every second, creating an engaging and dynamic user experience.

Improvements

•Added pictograms to "The Problem We Solve" section: Research Silos, Design Chasm, and Costly Drift
•Added workflow illustrations to all three steps in the "Unified Design Workflow" section
•Redesigned Trust Center hero with security illustration and improved visual hierarchy
•Improved visual consistency across landing page sections with flat, minimalist design
•Enhanced image presentation with full-size pictograms that fill their container elements
•Updated color scheme to use theme colors (subtle gradients) for better brand consistency
•Added smooth word rotation animation to CTA section without layout shifts

December 13, 2025

Features

Enhanced Landing Page with Visual Journey Flow

Added a visual journey flow diagram to the landing page to help customers better understand what Pathmode is about. The image showcases the complete workflow from customer insights through journey mapping to prototype generation, making the value proposition immediately clear to visitors.

Improvements

•Improved visual communication of Pathmode's core value proposition on the front page
•Streamlined image display to use a single, clear visual representation of the journey mapping process

December 12, 2025

Features

Improved Workspace Settings Access

Workspace settings are now more accessible with a direct link below the workspace name in the sidebar header. Settings now use workspace-specific URLs (e.g., /workspace-name/settings) for better organization and navigation consistency.

Improvements

•Moved workspace settings link from bottom navigation to header below workspace name
•Settings now use workspace URL key format for consistent routing
•Simplified "Back to Workspace" button to just "Back" in settings view

December 11, 2025

Features

Enhanced Storyboard Generator with High-Quality AI Images

The storyboard generator now uses Nano Banana (Gemini 2.5 Flash Image) to produce high-quality, photorealistic images for your journey visualizations. Images are now generated as detailed PNG files instead of simple SVG placeholders, bringing your customer journey stories to life with professional-quality visuals.

Improvements

•Fixed image generation to properly extract images from API response structure
•Improved image quality from SVG placeholders to high-resolution PNG images
•Added authentication check - unauthenticated users see placeholder images with sign-up prompts

December 10, 2025

Improvements

•Improved Google sign-in experience - you'll now see "Pathmode" when signing in with Google for a more professional and secure authentication process

December 8, 2025

Features

Workspace Settings Navigation

Moved Workspace Settings to the main navigation panel for easier access. Settings now use workspace-specific URLs (e.g., /workspace-name/settings) for better organization and navigation consistency.

Improvements

•Fixed Activity feed navigation link
•Improved workspace invitation permissions - workspace owners can now create and manage invitations
•Streamlined Users & Team view by removing redundant Settings button
•Updated RLS policies to support workspace owner role for invitation management

December 6, 2025

Features

Trust & Security Center

Comprehensive security and privacy information page showcasing our security measures and compliance standards.

Team Management & Activity Feed

Complete overhaul of team management with email invitations, granular roles (Owner, Admin, Editor, Commenter, Viewer), and a new activity feed to track workspace actions.

Cookie Consent Management

GDPR-compliant cookie consent banner with granular controls for optional cookies and analytics.

Improvements

•Improved footer navigation across all pages
•Enhanced landing page with security information

November 27, 2025

Features

Beta Launch

Pathmode is now in public beta! We're excited to share our AI-powered journey mapping platform with designers and product teams.

API Rate Limiting

Implemented distributed rate limiting with Upstash Redis to prevent API abuse and ensure fair usage across all endpoints.

GDPR Compliance

Added comprehensive GDPR compliance features including cookie consent banner, privacy policy, terms of service, and self-service account deletion.

Profile Page

New profile page accessible from the sidebar where users can manage their account settings and delete their account.

Performance Monitoring

Integrated Vercel Speed Insights to monitor application performance and identify optimization opportunities.

Improvements

•Enhanced security headers and Content Security Policy
•Improved Trust & Security page with detailed compliance information
•Added links to legal pages throughout the application
•Launched changelog to keep users informed of updates

Want to stay updated? Visit our Trust & Security page for the latest on security and compliance.

Changelog

Updates and improvements to Pathmode. We ship regularly.

September 11, 2026

Features

Sign up with an email link, with no password to choose

Name your own workspace

A new workspace opens on one thing to do, and an agent finishes it

The teammate handoff has a page of its own, and it keeps

Removed

•The example product. A new workspace used to arrive holding Acme HR: a fictional product with three intents and ten evidence items. It answered "what is this?" while the question a new account actually holds is "what do I do now?", and four intents on the first screen give you no way to tell which one is yours. Demo workspaces still seed it deliberately, and workspaces created before this keep theirs

Improvements

•The welcome email waits until you confirm your address, and describes the workspace you actually land in instead of evidence that was never there
•Asking for an email link with an address that already signs in with Google now opens that account, instead of minting a second one with an empty workspace beside it
•Correcting a typo in your address sends the new link immediately. The one-minute wait between links is per address now, so the corrected address is no longer silenced by the request you were correcting
•The check-your-email screen has a way back, which is what a mistyped address needs: the link never arrives, and there was nothing on that page to click
•A workspace name the URL rules reject returns you to the naming form with the reason and with what you typed still in it, instead of an error screen with no way forward
•Confirming a signup in a second browser tab no longer ends on "Failed to create workspace". Both tabs land in the one workspace that was created
•The check-your-email screen no longer promises a scan that does not run on that path
•The signup page no longer previews what happens after signup while you are still deciding whether to sign up. What it costs stays on the page, because that is a question you hold before creating anything

September 9, 2026

Features

Creating an account now connects your repository

Hand the setup to the teammate who runs the agent

Try the readiness gate before creating anything

Improvements

•A question you deliberately left open now reads differently from one you never reviewed, both on screen and in the file your agent receives
•The pre-signup decision review no longer offers to accept every suggestion at once; each call is yours to take, edit, or leave open
•Working through a product decision now continues straight to creating the account and reviewing the proposal, without a separate workspace step in between
•Signing up from a decision that never named a product no longer fails at the last step
•The Pathmode wordmark on the preflight page returns to the home page instead of doing nothing
•Every brief now records which part of the product it was started from

September 8, 2026

Features

Review the intent instead of writing the whole spec

Agent additions stay visible until you review them

Authorize the proposal the implementation agent will use

Improvements

•Workspace and Product Home now lead with proposals that need a decision, drafts with suggestions to review, and work waiting on an agent
•Intent rows distinguish Review proposal, Review suggestions, Review revised proposal, and Waiting for agent from delivery status
•The conversation editor remains available for discussion and deeper editing, while the proposal is now the primary intent surface
•Agent-written outcomes and edge cases keep stable identities, so their suggestion and evidence references survive ordinary saves

September 3, 2026

Features

Know what backs every claim, and who judged it

Evidence carries a trust tier everywhere it leaves Pathmode

Pull requests get an advisory intent review before merge

Committed files carry references, not quotes

Removed

•The Kanban, Flow and Clusters layouts of the Evidence board. Pathmode is a trust layer for the claims in a spec, not a research canvas; the Inbox and the detail panel remain. This is a product decision, not a usage measurement
•Group-by, bulk selection and "Suggest intents" synthesis on the Evidence Browse view. Browse is now a flat, searchable record for locating and opening evidence; claim backing is inspected and added on the IntentSpec itself, and Evidence opens to the Inbox whenever unreviewed items are waiting
•Creating a general, non-claim evidence link from the signed-in UI. Making something trustworthy in the app now means choosing the exact claim it backs. Existing general links stay visible on the spec as "General / not claim-anchored", and API and MCP link_evidence are unchanged

Improvements

•Every door that creates evidence now states whether a person reviewed it: typed and kept items are reviewed, AI-drafted assumptions and file imports land in the Inbox, and evidence written through the API by an agent carries its own provenance
•The empty-state sample ticket and example cards persist as unverified assumptions rather than confirmed evidence
•Prose paste has one path: the Composer extracts, you review inline, and the kept items are saved. The import modal is for files only

August 31, 2026

Features

Bring the intent.md you already have

Repository credentials belong to repositories

Improvements

•Repository adoption validates intent.md before using the one-time code and stores the exchanged credential before pushing, so a failed network step can resume instead of burning the code or minting duplicate keys
•Adoption codes expire after 15 minutes, are stored only as hashes, can be claimed only once, and the unauthenticated exchange is rate-limited by caller before a code is parsed as well as by code for legitimate retries

August 30, 2026

Features

Use Pathmode with OpenSpec, not instead of it

IntentSpec has a standards repository

Four parsers, one reading

The intent.md in your repo is the authority

Handoff notes reach the next agent

Claude Code tells you the repository has an intent

Improvements

•The Engineering Lead and First Intent use case exists, and its CTA routes to the keyless flow rather than the web signup. That cell's entire pitch is that no account is needed, and it was falling through to a fallback that asked for one
•The plugin install commands are single-sourced across the landing page, /preflight, the intent-compiler page and /developers, so they cannot drift against each other. Teaching only the marketplace command installs nothing, and this is how the public plugin repo sat four versions stale
•Page titles lead with the nouns people search for. The glossary index was titled "Glossary", which ranks for nothing, while every searchable term sat in the description where it earns no title relevance. The blog's structured data also described an earlier blog that no longer exists

August 29, 2026

Features

The OpenSpec bridge runs both ways

Confirmations work against a workspace

August 28, 2026

Fixed

•check_intent_readiness could not pass for any intent saved in a workspace. The tools that read an intent for grading were reading the list projection, which does not carry edge cases, so every cloud spec was graded with its failure modes missing and blocked on "No edge case with a defined expected behavior" however well it was written. get_current_intent, the outcome rubric export and the current-intent resource had the same hole, so an agent asking for the full spec never received the one part it would not invent for itself. Fixed in @pathmode/mcp-server 1.14.1

August 26, 2026

Features

Your agent gathers what the code looks like. You decide whether it counts.

Stamp the pull request and the merge does the rest

A spec saved by an agent lands in your workspace

Fixed

•A merged pull request did not update intents in workspaces that had set a per-product GitHub connection. The lookup assumed one connection per installation, so every delivery to those workspaces failed before it began
•A merge in one repository could mark an intent shipped whose product is bound to a different repository, and grade it against the wrong codebase

Improvements

•Two agents editing one spec can no longer overwrite each other silently: an edit states the version it was based on, and a conflict is refused rather than resolved by whoever wrote last
•The MCP surface is now 25 cloud tools, with record_implementation_context added

August 23, 2026

Features

Preflight has its own home

Your agent proposes. You authorize.

Import your Linear or Jira backlog as evidence

Verification reads the pull request, not your summary

The assistant hands the spec off, not just writes it

Current state: what the code does today

Removed

•Pushing an intent to GitHub Issues. The path was dead code, and a ticket is a copy that goes stale the moment the spec changes. GitHub still reads your repo for Implementation Context, hands the live spec to coding agents over MCP, and flips the intent to Shipped when a PR referencing it merges. Linear and Jira still create issues.

Improvements

•A "Connect a repository" step joined the setup checklist: the codebase analyzer was gated behind a GitHub binding that no onboarding surface ever mentioned
•Pasting a doc full of verbatim customer quotes and measured numbers no longer launders them into unverified assumptions: quotes land as quotes and metrics as metrics, tagged to the material they came from

August 22, 2026

Features

Your agent wrote a spec. Now it comes to you for review.

Outcome tracking: did the shipped thing work?

Decisions you can write, edit, and record from anywhere

Pathmode asks your role once, then shapes itself around it

Install Pathmode into Claude Code with one command

Fixed

•Marking an intent shipped no longer demands a verification check you already added: the lifecycle gate now recognizes checks created in the current editor, not just the legacy format
•Unsubscribe links now verify their signed token instead of trusting the user id in the URL
•Recording an outcome measurement requires a writer role in the workspace; viewers can read but not write

Improvements

•Evidence arriving through connectors (support-ticket sync, Slack capture, the ingest API) is now labeled with integration origin instead of masquerading as manually entered
•The product setup checklist can actually finish now: team and agent-connection detection work, and the card retires itself when you're done
•Developer docs: the decisions endpoints are documented, and the implementation-findings endpoints, previously documented but rendered nowhere, are visible on /developers

August 21, 2026

Features

The keyless install we advertised now actually works

Fixed

•Saving twice in one conversation no longer destroys the first spec: a save with the same id updates it and bumps the version, and a different id is refused unless you say overwrite explicitly
•intent.md round-trips. Every section used to truncate to its first line when read back, so three outcomes returned as one and Scope vanished entirely. Decisions had no reader at all and now have one
•The setup command no longer exits with an error when you have no API key, which made the documented first step of onboarding a wall for exactly the people it was written for

June 21, 2026

Features

Draft your first intent before you sign up

Paste a doc to build product context

The judgment loop: building writes back to the spec

sync_context: round-trip your intent into CLAUDE.md

Fixed

•Archived evidence no longer reaches an agent prompt or export: signals you dropped stay dropped instead of riding along to the agent

Improvements

•Socratic sharpening on the warm landing screen: one pointed question to tighten a vague description before it becomes your first intent, because the pre-signup flow has no evidence to push back with yet
•Product Home shows a read-only product-context strength meter, so you can see how grounded a product's context is at a glance
•A substantial paste on the landing hand-off auto-extracts and skips the redundant paste box
•The new pre-signup AI endpoints (description sharpening, assumption drafting) are bot-challenged and rate-metered alongside the scan flow

June 18, 2026

Features

IntentSpec v1.2 — scope and verification are first-class

June 15, 2026

Features

Evidence is a property-driven collection now

Pull evidence from any MCP server

Home and Product Home are judgment queues

Edit your scanned workspace before you sign up

Teammates auto-join by email domain

Ask an AI about Pathmode

New essay: The Cost of Being Worth Using

Changed

•Removed the blocking post-signup "Which lens do you bring?" modal — it gated the very first workspace screen for every new user. Role still feeds the AI and is settable in Profile; we'll elicit it inside the conversation instead
•Legacy /journey-map URLs now redirect to /product-teams

Fixed

•Closed cross-tenant isolation holes in the Atlassian/Jira integration — an unbound Forge install could resolve another tenant's intent, and any admin could claim other tenants' installs. Both fixed with live host-authenticated binding and 15 regression tests
•The Anonymization Firewall now fails closed — if redaction can't run, data is held back rather than passed through
•Signup analytics no longer drop OAuth events to a malformed ID, and the signup form can no longer double-submit
•Fixed an infinite re-render loop in evidence suggestions, and a failed workspace load no longer dumps you into the create-workspace flow

Improvements

•Settings and the Intents board got a Notion-lens pass — a shared SettingRow primitive, three-tone color drain, and quieter chrome so your content leads
•Skip the scan and create your first product from the activation cards, and Pathmode now opens the intent editor for it automatically instead of dropping you on an empty product page
•Account deletion is no longer forensically silent — it emits an account_deleted event and an admin notification with churn context, and new accounts now derive a display name from your email instead of a generic "User"

June 12, 2026

Features

Evidence is a canvas now, not a form

Edit evidence in place

Hover any row to edit its text, type, and severity right where it sits — no panel, no navigation. The board is the interface; your signals are the content, not rows in a form.

Improvements

•Empty products now open with illustrative typed signals you can adopt with one click — you see the shape of a populated board before you have one, instead of reading an abstract description of it
•The add-evidence composer follows you across the List, Clusters, and Flow views; Inbox stays a focused, keyboard-driven triage lane and Sources stays document-first
•Typing a single line runs through the same model as a full paste, so a one-off observation lands as a properly typed signal without extra steps

June 8, 2026

Features

The Playbook gets an advanced tier

Developer docs, single-sourced from the live spec

Fixed

•Health Metrics — your "what must not degrade" guards — now travel in the Markdown agent prompt, not just the CLAUDE.md and .cursorrules exports, so regression guards reach every handoff
•Several broken "Get started" links in the Playbook guides now point to onboarding instead of returning a 404

Improvements

•The Playbook reads as a curriculum instead of an archive — guides follow a learning path with previous/next and related links, and difficulty now reads as a depth ladder (Advanced earns a single accent; Beginner is quiet) rather than a red/yellow/green traffic light
•The IntentSpec is taught in full across the Playbook, glossary, and comparison pages — all eight parts an agent actually receives (now including Scope and Health Metrics, with the placeholder "Goal" retired), so what you read matches what Pathmode hands the agent

June 6, 2026

Features

Constitution v1 — rules carry their judgment

Readiness is a contract, not a suggestion

MCP server v1.6 — skill pack + Claude Managed Agents

Fixed

•Intent conversations no longer dead-end when the AI model errors — a retry path appears instead of a stuck "Thinking…" state
•A fast conversation can no longer fork a phantom duplicate spec, and autosave no longer carries one intent's baseline into another
•AI streaming no longer drops updates that land on a chunk boundary
•Free-text scope entered in conversation now coerces into the structured scope and renders in the spec
•The re-engagement greeting no longer stacks when jumping between phases
•Demo requests submitted from the site are no longer silently dropped by row-level security

Improvements

•Spec panel restructured to read top-down like a document — title, a quiet property block (Status / Execution / Codebase), then the body — instead of a fixed toolbar bolted above your content. Metadata recedes so the spec is the artifact
•Conversation-first editor now runs on a single document store — one source of truth for the spec instead of two competing copies — eliminating a class of save races and stale-state bugs
•Constitution governance templates now ship with enforcement levels and rationale on each constraint, so seeded workspaces start with operational rules rather than bare imperatives
•Hardened the public site-scan endpoint against SSRF, with per-redirect-hop URL and connect-time DNS validation; added rate limiting across more mutation endpoints and replay-protection for inbound integration webhooks
•Patched dependency security advisories (Next.js, xlsx, react-router) and tightened database privileges on internal functions

May 27, 2026

Features

IntentSpec v1.1 — specs carry their evidence

Category comparison pages

Fixed

•Scan bot-detection now lets through requests with no challenge token (usually an ad-blocker or a script-load race) instead of blocking real users with an unactionable "Bot detected" message — genuine bots are still rate-limited
•Intent editor — reopening an existing spec no longer re-fires turn analytics for messages loaded from history, and silent autosave failures are now tracked

Improvements

•Onboarding — a "skip the scan and start with an empty workspace" option (the workspace still seeds a sample product), returning users now land back in their existing workspace instead of a duplicate, and the same skip option appears as an escape hatch when a scan fails
•Positioning refresh across /philosophy, /use-cases, /patternry, /comparison, and /integrations/github — the product judgment layer, the discovery loop (discovery doesn't end at ship), and codebase-as-evidence (specs ground against your connected repo while you draft)

May 25, 2026

Features

Implementation Context

Agent exports carry code context

GitHub product-level repo overrides

May 21, 2026

Features

Scan-first Onboarding

Multi-product Disambiguation

Description Fallback

JavaScript-heavy and login-walled sites get a paste-a-description path that runs the same extraction on your own words. The original URL stays attached as Evidence provenance.

Site-Scan Banner

Seeded workspaces show a one-time "Draft your first Intent" prompt on the Product page that hides once you've authored one.

Changed

•Every "Get started" / "Start for free" button on the public site now opens /onboarding/scan instead of the AuthModal — bookmarked /#signup URLs redirect too
•AuthModal becomes sign-in only — "Don't have an account?" links to the scan flow, so sign-up exists in exactly one place
•Sign-in without a workspace routes to /onboarding/scan instead of the legacy WorkspaceCreationModal

Removed

•First-run OnboardingHero — superseded by the scan-first flow; every new workspace now lands with a Product + Evidence already seeded

Improvements

•Setup checklist is scan-aware: "Seeded from your site" and "Draft first Intent" appear in the sidebar when a workspace was scan-seeded
•Two-tier product context: a scanned description satisfies the basic-context check, while Vision + North Star become an optional enrichment ("Strengthen product context") instead of a gating requirement

May 19, 2026

Features

Gemini 3.5 Flash

May 11, 2026

Features

Pathmode for Jira — Atlassian Marketplace

Push to Jira → linked from inside Jira

Bidirectional status sync

Atlassian Forge App workspace binding

Improvements

•Privacy policy gained a dedicated section covering Atlassian integration data flows — what we receive (cloud id, site URL, issue keys, account IDs), what we send (intent summary + description on push), how we authenticate, where it is stored, retention, and uninstall behavior
•New /support page with Pathmode for Jira–specific troubleshooting and security reporting contact
•Jira Test Connection now works after Save — server-side test against stored credentials instead of requiring the user to re-type the API token
•JiraIssueModal portals to document.body so it renders above the conversation panel in the Intent Editor

May 10, 2026

Features

AI Spec Review

Codex Integration Page

New Codex guide mirrors the Claude Code agent page. Both now share a single component and registry, so adding another coding agent is a data change, not a copy.

Use Cases Hub

Auto-Linked Glossary

Blog, playbook, and glossary content now auto-link the first occurrence of each glossary term. New entries propagate to old content automatically — no manual back-linking, no rot.

AI Turn Rating

Rate AI turns inline during an intent conversation. Per-turn signal flows into analytics so we can tune prompts on real data instead of vibes.

Workspace Ownership Transfer

Workspace owners can now transfer ownership to another member from the Danger Zone settings. Backed by a role-checked Postgres function so the transfer is atomic and safe.

Evidence Board 101 Playbook

New beginner playbook on running the Evidence Board as a diagnostic play — collect symptoms, spot patterns, decide where to operate — instead of a feedback dumping ground.

Blog Subscribe

Readers can now subscribe to the Pathmode blog. Email capture, confirmation, and rate-limited handling all in-app.

Changed

•Robots.txt moved from static `public/robots.txt` to dynamic `app/robots.ts` — adds disallows for /api/, /intent/, demo, and review routes, references the sitemap
•Dropped `offers` from SoftwareApplication structured data — Pathmode is SaaS, shopping-result fields do not apply

Removed

•Legacy Figma plugin package (was drifting from the current intent model)
•Legacy "Journey Mapping 101" playbook — replaced by Evidence Board 101
•Standalone `ClaudeCodePage` component — replaced by the shared `AgentIntegrationPage` used by both /claude-code and /codex

Improvements

•Spec Panel — Refactored, splitting execution hand-offs (Jira / Linear / Build Queue) and lifecycle controls (status, verification, review) into focused components. Smaller surface, fewer re-renders
•Intent Quality scoring centralized in one library so the Spec Panel, AI Spec Review, and readiness checks all use the same rubric
•Intent Interview JSON schema (with tests) replaces implicit field-name agreements between AI and client
•Glossary entries now cross-link to each other and to core terms — a small built-in knowledge graph
•New unified workspace integrations API across Jira, GitHub, Linear, and Slack with proper credential redaction
•Workspace settings — new Rename and Export Context endpoints, plus tracking for conversation-fired AI guidance rules
•Landing page hero, copy, and section structure tightened around "know what to build before you build it"

April 30, 2026

Features

First-Run Workspace Onboarding

Onboarding-Aware Intent Conversation

Improvements

•Free plan now includes 3 editor seats (up from 1) — small teams can get started without hitting the paywall
•Product creation now returns full metadata, allowing onboarding and analytics flows to tie created products to follow-up intents without extra lookups
•Paid-plan CTAs open the in-app contact modal when billing is not enabled, keeping interested teams inside the Pathmode experience
•Updated primary landing CTAs to "Start for free" and tightened homepage messaging
•Simplified product demo animation state to reduce timer/state drift
•Onboarding analytics across the full activation funnel — hero views, submissions, skips, first AI response, and first spec update

April 6, 2026

Features

Intent Readiness Scoring

Smarter Context Interviews

The product context builder runs a deeper interview flow, producing richer product context that feeds into every spec your team writes. Better context in, better specs out.

Agent Prompt Generation

The MCP server now generates full execution prompts for intents with readiness checks. AI agents get structured instructions with objectives, outcomes, constraints, and verification steps.

Plan Changes & Team Management

Workspaces can now upgrade, downgrade, and manage team members directly from billing settings. Full Lemon Squeezy integration for checkout, portal, and subscription sync.

Fixed

•Billing status hook, checkout flow, and portal redirect issues across multiple plan types

Improvements

•API Reliability — Rewrote intent API routes to share a single, tested handler layer with consistent validation
•MCP Server — Expanded tool surface: enhanced local file reading, better intent compilation, improved export formatting
•Context Health — Updated indicators so teams see at a glance which products have strong context and which need attention

March 29, 2026

Features

Functional Roles

Improvements

•Role-aware onboarding now prompts first-time users to choose their lens from workspace home
•Functional role selection is saved to the user profile and can be updated later in Profile Settings
•Added database support for functional_role with a safe default and validation constraint

March 28, 2026

Features

Evidence Inbox

AI Intent Synthesis

Structured Outcomes

Intent Scope

New scope field on IntentSpec with explicit inScope and outOfScope lists that tell AI agents what they can and cannot touch. Supported in the editor, API, and MCP server.

Intent Engineering vs Context Engineering

New blog post exploring why intent is upstream of context when building with AI. Teams optimize AI briefing before figuring out what to ask — better context just helps AI fail more efficiently.

Changed

•Removed beta banner — header now shows "Pathmode has launched!" announcement
•Restructured workspace settings with new API Keys tab

Improvements

•MCP Server — Structured outcome support, live quality checking with explicit rubric, scope field support, product strategy in exports
•Document View — Keyboard navigation in outcome lists, structured outcome rendering with priority labels, provenance view integration
•Evidence Board — New Inbox and Sources layout modes, layout selection in sidebar sub-menu, triage status counts in badges
•PostHog — Server-side event tracking with session and distinct ID headers

March 21, 2026

Features

Conversation-First Intent Editor

ThinkingQuality Scoring

4-dimensional assessment (specificity, testability, coherence, tension) scored 0-3 each, replacing the previous SpecCompleteness metric for more nuanced feedback.

Evidence-Anchored Specs

AI auto-links outcomes and edge cases to product evidence items. Specs display inline badges showing evidence links that persist across updates.

Changed

•Legacy form-based editor available via ?mode=form query parameter; conversation-first is now default

Fixed

•Intent editor save flow to properly persist spec updates and undo history
•Navigation issues between intent editor and product home

Improvements

•Intent Editor Performance — Consolidated state machine and reduced re-renders
•UI Consistency — Spec panel uses workspace design system with gray tones and no decorative hover effects

March 14, 2026

Features

Constraints Document Discoverability

Improvements

•Context Builder guardrails phase now includes a file upload button for constraints documents (PDF, DOCX, TXT, MD, CSV)
•New Intent modal shows a tip about constraints documents when none is uploaded for the product

March 11, 2026

Features

Smarter, Faster AI Conversations

Fixed

•AI would loop on the same topic or re-ask questions you already answered
•Conversations could get stuck on "Thinking..." with no way to recover — retry options now appear on failure

March 9, 2026

Features

PostHog Analytics Integration

Full-stack analytics with client-side event tracking and server-side error capture via PostHog EU, routed through a reverse proxy.

In-App Feedback System

"Send feedback" in the sidebar now opens a modal that emails the team directly via Resend (replaces mailto: link).

Product Creation Onboarding Flow

After creating a product, a guided welcome step offers "Get Started" (Context Builder) or "I'll explore on my own".

Changed

•Evidence Board redesign — Tabbed layout (Evidence / Sources), sort dropdown, more compact cards, dedicated "Suggest intent" button
•Intent Editor spec panel widened from 480px to 560px for better readability
•Product Home — Strategy section split into compact two-column card (Vision | North Star); tighter spacing throughout
•Insights Digest — Renamed from "Signals Digest"; critical items now use amber highlights; "View all" links to Evidence
•Hero demo — Streamlined from 7 steps to 6 (Signals step removed)

Removed

•Entire Signals system — Views, hooks, services, API routes, cron job, MCP tools, Slack notifications, and all UI references
•Glyphex analytics tracker — Replaced by PostHog
•Outcome quality scoring — Removed per-outcome quality badges (Testable/Decent/Vague) from the Intent Editor

March 6, 2026

Features

Hand-Drawn Illustrations

March 5, 2026

Features

Landing Page Refresh

Philosophy Page Rewrite

Improvements

•Navigation link renamed from "Our Philosophy" to "Our Approach"
•Hero demo now shows workspace vs. product sidebar modes
•Each demo step includes a description bar explaining the screen
•Removed unused IntentEngineDiagram and WhyHowWhenPositioning imports from landing page

March 3, 2026

Features

Gemini 3 Flash & Global AI Endpoint

March 1, 2026

Features

Living Specs — The Spec Lifecycle

Make specs feel alive — grounded in evidence, reviewed by humans, consumed by agents, and improved by outcomes. That's the loop that makes Pathmode indispensable.

Evidence-Anchored Specs

Spec Review with Evidence Backing

Reactive Signals

Agent Verification Loop

Improvements

•Evidence freshness indicator on specs — shows amber warning when linked evidence is older than 30 days
•Signal count badge in sidebar navigation
•Verification score badges on Build Queue kanban cards
•Verification failure signals with upsert dedup — re-running verification updates the signal instead of creating duplicates
•Updated AI verification model from Gemini 2.0 Flash to Gemini 2.5 Flash

February 22, 2026

Features

Intent Compiler for Claude Code

MCP Server v1.2 — Works Without API Key

Official MCP Registry Listing

Intent Compiler Page

Improvements

•MCP server README rewritten to lead with Intent Compiler and zero-config setup
•API key changed from required to optional in manifest.json
•Fixed pre-existing TypeScript error in MCP server api-client.ts

February 18, 2026

Features

Cursor Directory Listing

February 17, 2026

Features

Integrations Hub

Google Analytics Integration

Zendesk Integration

GitHub Integration

Link your GitHub organization to connect repositories with your workspace. Pull requests can be linked to Intent Specs, closing the loop from product intent to shipped code.

Linear Integration

Connect Linear to link issues and projects with Intent Specs. Track how product decisions flow from evidence through specs into engineering execution.

February 14, 2026

Features

Claude Code Integration Page

February 7, 2026

Features

Hero Animation as Video with Remotion

Improvements

•Added Remotion video rendering pipeline with preview and export scripts
•Downloaded and bundled Inter and Merriweather fonts for server-side video rendering

February 6, 2026

Features

IntentSpec Open Standard

About Page

Added a dedicated About page with the Pathmode story, company values, and founder bio.

Philosophy & Product Demo

Playbook Guides

Export to Agent

Improvements

•Landing Page: Redesigned hero section with interactive product demo and updated value proposition
•Solutions Pages: Added solution-specific landing pages for Journey Management, Product Intent Infrastructure, and Enterprise
•Footer: Added links to About, Philosophy, Playbook, and Comparison pages
•Terms of Service: Updated publicity rights and terms
•Intent Editor: Multiple stability and UX fixes across the spec editing workflow
•Blog: Published new articles on intent-driven development and AI-native teams
•Invitation Flow: Improved account handling and workspace invitation acceptance

February 1, 2026

Features

Intent Spec Workflow

January 29, 2026

Features

Inline Friction Highlighting

Replaced list-based friction display with Google Docs-style inline highlights directly within research documents. Click a highlight to see the finding, severity, and synthesize intents.

Document Highlighter Component

New DocumentHighlighter with viewport-aware popover positioning that never gets cut off by the browser window.

Improvements

•Document View: Added read/edit toggle via eye/pencil icons
•Friction Pipeline: Replaced "Specs Shipped" stat with "Evidence Docs" count
•Interactions: Changed popovers to click-based triggering for better stability
•Navigation: Fixed "View All Friction Points" button behavior
•Persistence: Upgraded storage engine to support rich friction metadata (findings, tags)

January 26, 2026

Improvements

•New Journey Experience: Redesigned modal to prioritize "Start from Friction" workflow
•Journeys List: Refined list view layout to reduce visual noise
•Welcome Email: Updated messaging to align with "Intent Layer" philosophy
•Build Queue: Upgraded to Kanban board interface for better tracking

January 22, 2026

Features

Intent Graph

Introduced interactive graph visualization for intent dependencies and strategic alignment. Visualize how your intents connect and ensure they align with your workspace strategy.

January 18, 2026

Features

From Journey Maps to Intent Layer

We started building Pathmode as a journey mapping tool. The vision was simple: help teams visualize customer experiences and connect user research to real workflows.

Intent is the new code. Specs are the new handoff. The map is the new constitution.

January 11, 2026

Improvements

•Admin Notifications: Implemented email alerts for new sign-ups
•UI/UX: Redesigned Blog Index page with responsive grid and author metadata
•Architecture: Decomposed MainApp for Next.js App Router migration
•Docs: Updated competitive landscape analysis
•Fixed: Resolved modal navigation issues on public pages

January 8, 2026

Features

Anonymization Firewall

Improvements

•Added PII detection toggle in workspace settings
•Updated data ingestion pipeline with pre-processing hook

January 1, 2026

Features

Interactive Live Demos

Improvements

•Smart Caching: Implemented intelligent local storage caching for public viewers, ensuring instant load times for AI artifacts like Storyboards and Proto Specs
•Optimized Public View: Revised staleness detection logic to prioritize cached content for read-only users, preventing unnecessary regeneration loops
•Robust AI Pipeline: Enhanced the generation engine with better payload management to reliably handle complex, data-heavy journey maps

December 29, 2025

Features

Integrations View & Live Embeds

Showcase your tool ecosystem with the new Integrations view. Embed live Figma prototypes directly into journey steps to keep designs synchronized.

Improvements

•Added "Integrations" to main navigation
•Added "Design Prototype" panel to Step properties for embedding support

December 28, 2025

Features

Specs View: Triage & Kanban

Redesigned the Feature Specs interface to split workflows into two distinct views:

Triage View: Review and approve new opportunities.
Kanban Board: Track specs from "Draft" to "Shipped".

Added an Archive workflow to hide deprecated or irrelevant specs.

Compact Research Dashboard

Refined the Research Dashboard for density. Key performance indicators are now grouped into a single row, providing an immediate overview of library health.

Hybrid Rendering Architecture

Re-architected the application core. Marketing pages now use Server-Side Rendering (SSR) for SEO and initial load performance, while the workspace remains a client-side SPA for interactivity.

Improvements

•Updated Research Dashboard visual hierarchy
•Implemented `useAppNavigation` for consistent routing state
•Resolved authentication race conditions with optimistic session hydration
•Fixed session persistence issues on refresh
• eliminated "Map Not Found" navigation errors
•Resolved client-side hydration mismatches
•Fixed React hook ordering stability issues
•Centralized modal state management

December 26, 2025

Features

Brand Identity Update

Refined the logo for better legibility at small sizes. The new mark retains the spiral geometry with cleaner lines and balanced weight.

Before

After

Improvements

•Updated favicon and app icons across the platform
•Unified spacing standards in navigation bars

December 25, 2025

Features

Feature Specs

Journey Editor Refinements

Improvements

•Privacy Overhaul: Removed Google Tag Manager and installed privacy-first GA4 with strict cookie consent
•Updated default workspace logo to use the Pathmode brand icon
•Various performance tunings and layout fixes in the editor canvas

December 24, 2025

Features

New "Product Teams" Landing Page

Improvements

•Updated front page tagline: "Stop managing journeys. Start building them."
•Added new "For Product Teams" navigation link in footer

December 22, 2025

Features

Dynamic Hero Video

The landing page now features an immersive autoplay video in the hero section, replacing the static image. This provides an instant, dynamic preview of the Pathmode interface in action.

Improvements

•Optimized landing page hero performance with video assets

December 21, 2025

Features

New "Pathmode vs The Rest" Comparison

Performance Tuning

Improvements

•Fixed "zombie session" issue ensuring immediate and permanent sign-out
•Cleaned up security section iconography on landing page
•Updated site-wide navigation to new comparison breakdown

December 19, 2025

Features

Analysis Workbench

Vibrant Cartoon Storyboards

Improvements

•Updated AI prompt to request "vibrant cartoon style" for storyboard panels
•Enhanced image generation parameters for consistent flat design aesthetics

December 16, 2025

Features

Competitor Comparison Page

Added a detailed comparison page to help users evaluate Pathmode against other journey mapping tools. This transparency helps teams make informed decisions about their journey management toolkit.

Improvements

•Restored missing comparison page routing and functionality
•Fixed an issue where the /compare link was resulting in a blank page

December 14, 2025

Features

Redesigned Front Page with AI-Style Illustrations

Unified Design Workflow Visual Updates

Enhanced Trust & Security Page

Dynamic CTA Section with Rotating Words

Improvements

•Added pictograms to "The Problem We Solve" section: Research Silos, Design Chasm, and Costly Drift
•Added workflow illustrations to all three steps in the "Unified Design Workflow" section
•Redesigned Trust Center hero with security illustration and improved visual hierarchy
•Improved visual consistency across landing page sections with flat, minimalist design
•Enhanced image presentation with full-size pictograms that fill their container elements
•Updated color scheme to use theme colors (subtle gradients) for better brand consistency
•Added smooth word rotation animation to CTA section without layout shifts

December 13, 2025

Features

Enhanced Landing Page with Visual Journey Flow

Improvements

•Improved visual communication of Pathmode's core value proposition on the front page
•Streamlined image display to use a single, clear visual representation of the journey mapping process

December 12, 2025

Features

Improved Workspace Settings Access

Improvements

•Moved workspace settings link from bottom navigation to header below workspace name
•Settings now use workspace URL key format for consistent routing
•Simplified "Back to Workspace" button to just "Back" in settings view

December 11, 2025

Features

Enhanced Storyboard Generator with High-Quality AI Images

Improvements

•Fixed image generation to properly extract images from API response structure
•Improved image quality from SVG placeholders to high-resolution PNG images
•Added authentication check - unauthenticated users see placeholder images with sign-up prompts

December 10, 2025

Improvements

•Improved Google sign-in experience - you'll now see "Pathmode" when signing in with Google for a more professional and secure authentication process

December 8, 2025

Features

Workspace Settings Navigation

Moved Workspace Settings to the main navigation panel for easier access. Settings now use workspace-specific URLs (e.g., /workspace-name/settings) for better organization and navigation consistency.

Improvements

•Fixed Activity feed navigation link
•Improved workspace invitation permissions - workspace owners can now create and manage invitations
•Streamlined Users & Team view by removing redundant Settings button
•Updated RLS policies to support workspace owner role for invitation management

December 6, 2025

Features

Trust & Security Center

Comprehensive security and privacy information page showcasing our security measures and compliance standards.

Team Management & Activity Feed

Complete overhaul of team management with email invitations, granular roles (Owner, Admin, Editor, Commenter, Viewer), and a new activity feed to track workspace actions.

Cookie Consent Management

GDPR-compliant cookie consent banner with granular controls for optional cookies and analytics.

Improvements

•Improved footer navigation across all pages
•Enhanced landing page with security information

November 27, 2025

Features

Beta Launch

Pathmode is now in public beta! We're excited to share our AI-powered journey mapping platform with designers and product teams.

API Rate Limiting

Implemented distributed rate limiting with Upstash Redis to prevent API abuse and ensure fair usage across all endpoints.

GDPR Compliance

Added comprehensive GDPR compliance features including cookie consent banner, privacy policy, terms of service, and self-service account deletion.

Profile Page

New profile page accessible from the sidebar where users can manage their account settings and delete their account.

Performance Monitoring

Integrated Vercel Speed Insights to monitor application performance and identify optimization opportunities.

Improvements

•Enhanced security headers and Content Security Policy
•Improved Trust & Security page with detailed compliance information
•Added links to legal pages throughout the application
•Launched changelog to keep users informed of updates

Want to stay updated? Visit our Trust & Security page for the latest on security and compliance.