One research run, unrolled stage by stage: what your agent prepares, what your user experiences inside your product, and what comes back as evidence, timestamped to the moment it came from. The walkthrough follows trial users who start, explore, and leave.
In 46 seconds: design the study, meet a user inside the product, connect their answer to the source moment, compare related Interviews, and hand a grounded Finding to product triage.
The Study defines what to learn. Interviews capture what users say and do. Evidence links to those moments; a Finding summarizes the pattern. Your team reviews the Finding before sending it to a tracker.
You → your agent
It starts with the question your analytics cannot answer. Signups look fine, activation does not, and cancellations explain nothing. You hand the question to your agent the way you hand it any other task.
The brief, as you would type it
Trials keep stalling before anyone creates a report. Find out why — with evidence, not guesses.
MCP · CLI · Dashboard
Your agent drafts a study: the goal, how to meet users — silent observation, a task to try, or an open conversation — and the debrief questions it plans to ask. You review the plan before anything goes live, and you can see exactly what the participant is asked to agree to.
Study plan — ready for your review
Inside your product · Widget
There is no call to book and no panel to rent. When a trial user is in your product anyway, the interviewer meets them there, with consent, and watches the real workflow in one record: voice, navigation, and the screen on desktop browsers that allow screen capture; mobile interviews continue with voice and in-page events. When the user gets stuck, nothing pops up to rescue them. Stuckness is evidence.
Captured session — minute one of six
While context is fresh
Observation first, questions second. The interviewer asks why about the exact moment it just watched — while the user can still explain what they expected. What an exit survey asks three weeks too late, the debrief asks in the same session.
Planned debrief
Interviewer
You clicked New report three times, then left the page. What did you expect to happen?
Participant
I thought the report would show up in that list. Nothing changed, so I assumed the trial did not include it.
Source-linked
Everything the run learned comes back attached to its source — the participant's words, the observed behavior, or both — with the page path, the playback moment, and a confidence level. Participant words and interpretation stay in separate fields. If a card reads wrong, the recording is one click away.
Evidence card
Nothing changed, so I assumed the trial did not include it.
/reports · playback 00:19–00:52 · interview #14
Draft → reviewed → send
UserTold groups related Evidence into a draft Finding. You or your agent check the sources and summary, then mark it reviewed. Sending it to a tracker is a separate decision.
Draft Finding — under review
Report creation gives no feedback, reads as a trial limit
Pushed to Linear with sources attached
Linear or GitHub
Send a reviewed Finding to Linear for product triage or to GitHub for delivery. The issue includes the Finding and its Evidence links. In Linear, your team decides whether to accept it into delivery.
Closing the loop
When a linked Linear issue completes, the evidence beneath it resolves. Future interviews keep watching for the same pattern: if users still stall at that moment, it comes back as new evidence, not as a hunch. GitHub handoff does not include completion sync.
Recurrence watch
Evidence resolved when the Linear issue completed
New interviews checked for the same stall
“Users churn without a word. The exit survey is a ghost town.”
What changes
Interviews happen mid-use, while users still care enough to talk — not after they have already left.
“Nobody books the fifteen-minute call. Not even the power users.”
What changes
There is nothing to book. The interview meets users inside the product.
“Analytics shows exactly where they drop off. Never why.”
What changes
Observation captures the drop as it happens, and the debrief asks about that exact moment while it is fresh.
“Our roadmap is whoever shouted loudest in support this week.”
What changes
Evidence carries sources and confidence, so a quiet pattern across interviews can outweigh the loudest ticket.
“My agent can build anything. I still do not know what to tell it.”
What changes
The research output is a Finding with its Evidence attached. After review, the receiving team decides in product triage whether it becomes delivery work.
It interviews people who are already using your product, on the pages where you installed the script. You choose whom to invite; responses are not guaranteed.
During observation nothing interrupts, hints, or navigates for the user. Stuck moments are preserved as evidence, then explained in the debrief.
Review the Finding and its Evidence, then choose whether to send it to Linear for product triage or GitHub for delivery.
Review the quotes or observed behavior behind a Finding to check the interpretation.
The docs cover study design, the widget embed, methodology, and the agent surfaces.
Set it up in the dashboard, or let your agent do it over MCP and review the evidence when it lands. Either way, the next decision ships with sources.