Twelve interviews in. One ranked list of problems out.
Interview users to learn which problems are worth solving.
- For
- Product teams doing problem-space research before committing to a solution.
- Leads with
- Invite to call
- Preset goals
- 4 — editable, up to five
- Also uses
- The Sense Bot notetaker on Zoom, Meet, and Teams
Discovery happens in scheduled conversations, so the ways in start with the call itself.
Discovery is the one place where the twelfth interview is worth more than the first — but only if the first eleven are still legible when you get there. Capture starts with the call, and everything after it is built so the pile stays searchable instead of turning into eleven documents nobody reopens.
The capture routes this project puts in front of you.
All seven capture methods work in every Sense project. This template only decides the order — and for discovery interviews, that order starts here.
Paste a meeting link and the Sense Bot joins the Zoom, Meet, or Teams call, records it, and transcribes it.
Record a voice note in the browser — the fastest way to get a thought down right after a session.
Already have the text? Paste it in and it becomes a signal like any other.
Drop in audio, video, or a document you already have and we will transcribe it.
4 preset goals, written for this situation.
A goal is an extraction prompt: it tells the AI what to pull out of every transcript in this project. These ship with the template and are yours to rewrite — a project holds up to five.
The progress the person wants, in their own words; the circumstance that triggered it; how they judge it done — kept separate from any tool they happen to mention.
Where the current approach breaks down — friction, delay, rework, anxiety, workarounds — and what it costs. Specific recent episodes are preferred over general complaints.
What they use today, including spreadsheets, manual steps, other people, and non-consumption. Why they picked it, where it falls short, and what they abandoned.
What would push them to change and what holds them in place — search triggers, judging criteria, switching costs, and anxiety about a new solution failing. Only what was said, never what could be inferred.
One line becomes an action item, without losing the words.
Nothing here is a summary. Each hop keeps a link back to the one before it, so the item at the bottom still opens onto the sentence at the top.
- 01Capture
The meeting link goes in ahead of time and the Sense Bot joins the call, records it, and transcribes it. A discovery call, opening question in.
DRSKRECSenseSense Bot joined the call - 02Signal
It lands as a transcript — timestamped, searchable, with the recording attached.
0:02AnaTake me back to the last time you had to pull the quarterly numbers together.0:09RaviI rebuild it in a spreadsheet every quarter, because the dashboard never matches what finance sends me.0:21RaviIt costs me most of a Monday, and at this point I just don't open the dashboard. - 03Anchor
Read against this project's 4 goals, the passage that answers one gets lifted out verbatim and tagged. The anchor keeps its offsets into the transcript.
0:02AnaTake me back to the last time you had to pull the quarterly numbers together.0:09RaviI rebuild it in a spreadsheet every quarter, because the dashboard never matches what finance sends me.0:21RaviIt costs me most of a Monday, and at this point I just don't open the dashboard.Tagged toCurrent solutions - 04Insight
Anchors group into a finding. One insight often draws on more than one goal.
Quarterly reporting gets rebuilt by hand because dashboard and finance numbers disagree
3 anchorsCurrent solutionsStruggling moments - 05Action item
The finding becomes a backlog item on the workspace kanban, still linked to the anchor it came from.
Reconcile dashboard figures with the finance source of truthTodoTraces back to Ravi at 0:09
Every interview becomes a signal, and the patterns across them land in your backlog as problems worth solving.
Action items live on the workspace backlog, not inside a single project — so a fix that came out of a testing session sits next to one that came out of an interview, each carrying its own evidence.
A Jobs-to-be-Done instrument, not a note-taker.
- The goals are the interview framework: the job, the struggle, the current solution, and what would make someone switch. You are not asking a general-purpose AI to "find themes".
- The job someone is hired for stays separate from the tool they mention. A spreadsheet is a current solution, not a requirement.
- Switching triggers record only what was said. Nothing is inferred about what a person would do, because the whole point is to stop guessing.
The one place patterns across interviews are the point.
An insight is grounded in anchors from a single interview. A theme spans signals — it bundles related insights under a goal, ranked by how many anchors ultimately sit underneath. That is what makes the twelfth interview worth more than the first, and every theme still opens down to the sentence a specific person said.
All seven capture methods are available in every project. A template only decides what you see first.
Rewrite, remove, or add to the preset goals at any time. A project holds up to five.
A new workspace is seeded with one project per template. Nothing is locked behind a choice you make on day one.
Every anchor carries its citation offsets into the transcript, so each claim traces back to the words that were said.
Every workspace starts with this project already in it.
Create a workspace and all six projects are seeded for you — this one included, goals and capture order set up. Nothing to configure before your first capture.
Your first run in this project ends on “Paste an interview link”. The project tour spotlights the composer, ready for the link to your next scheduled interview.