For a long time, research and design lived in their own artifacts. A research deck for the readout. A Figma file for the build. Both were attempts to carry context across a handoff that ate a lot of meaning on the way through.
You probably know the feeling: you watched a user struggle with something specific, you named the pattern in a slide, you handed it off, and the thing that shipped was almost the thing — adjacent to your point, but not quite on it. Not because anyone was careless. Because the artifact you wrote in wasn't the artifact the build happened against.
That gap is what's changing.
What changes
In Pathmode, research isn't a presentation. It's a layer of the substrate. Friction logs, observation notes, user quotes, recorded sessions — these become first-class evidence items, sitting in the same surface where the spec lives. When a designer or researcher names a pattern, they don't compress it into a slide. They drop the evidence into the team's shared surface, where the spec is being written now, not next sprint.
When the PM writes an outcome, they anchor it to the evidence behind it. When an engineer reads the constraint, the rationale is one click away — the actual customer quote, the friction log entry, the observation that made it real. The why travels with the what.
This means the agent ships against your evidence, not a paraphrase of it. The edge case isn't invented from a prompt. It's the screenshot from the session recording where a user got stuck.
A concrete example
A researcher watches three users in a row hesitate before bulk-deleting old projects. Two of them undo immediately. One asks aloud: "is there a way to get this back?" The pattern is small but real.
The old shape: it shows up as a bullet on slide 14 of a deck. Maybe it becomes a Jira ticket. Maybe not. The bulk-delete feature ships without it. Three months later, support tickets confirm what you already saw.
The new shape: the observation enters Pathmode as evidence the same day. The next time someone writes a spec touching deletion, the evidence is right there — surfaced because it's anchored, not because someone remembered to search. The constraint all destructive operations must be reversible appears in the spec, anchored to the recording of the user who asked.
The thing that changed isn't research rigor. It's that the research reaches the build, in a form that survives the agent.
What you stop doing
Watching the AI ship a feature that misses the feel by a small but unmistakable margin. Re-explaining the same insight at three different review meetings. Worrying that the rationale behind a pattern is going to quietly disappear when it gets passed to a tool that wasn't there for the session.
What's left
User reality. Taste. The judgment about what's right that doesn't compress into a checklist and shouldn't. The work of seeing what's actually happening to people using the thing — and now, of making sure what you saw stays attached to what gets built.
Where this falls apart
Evidence-anchored specs aren't a substitute for direct contact with users. The most important thing a researcher does — sitting with someone, watching their face, asking the next question — is still, and probably always, the thing. Pathmode is what happens after you saw it. It doesn't replace seeing.
But for everything downstream of the session — the long, lossy journey from "I noticed this" to "the product reflects it" — Pathmode is where that journey stops being lossy.
