Recording
Your recording
Paste your recording. Nothing to upload.
←recording
Make a interview guide
Turn recordings into an interview guide
Your last five interviews already told you which questions do not work.
Free to try, no card. Your recording opens in Ancher.
Transcript with timingsCommitment languageUnresolved threads
Kept in parts
Every one of these stays separately addressable instead of collapsing into one block of text.
GoalWarm-upCore questionsProbes
Interview guide
Questions ordered to get past the answer people rehearse.
The best source for a research guide is the recordings of the interviews you already ran. They show which questions produced a rehearsed answer, which produced a story, and which the participant answered by talking about something else entirely. Ancher reads across the collection to find where the interesting material actually arrived, and builds the next guide from the questions that got you there.
The honest version
The question that worked is often not the one on the guide
Interviews turn useful at unpredictable moments, and usually after an unscripted follow-up rather than a planned question. Because Ancher works across recordings with the timings intact, it can locate the passages that produced substance and identify what preceded them, which is how a follow-up that keeps working gets promoted into the guide.
One second of one recording, at 24:31, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
well, in theory we follow the process, but honestly we just
Shown after the follow-up — not readThe specific never reaches the draft
Interview guide
Shown after the follow-up
Spreadsheet with 4 manual overrides
from 24:31
Lands in the draft, with its timecode
- Questions that produced a short, rehearsed answer are flagged so they can be rewritten or dropped.
- Follow-ups that repeatedly opened participants up are promoted from improvisation into planned probes.
- Where a participant demonstrated something on screen, the guide notes to ask for a demonstration rather than a description.
What comes out
Interview guide, section by section
Questions ordered to get past the answer people rehearse.
Goal
What the next round needs to learn, given what previous rounds already settled.
Warm-up
Openers that got past the rehearsed version quickly in earlier sessions.
Core questions
The questions that produced substance, phrased as they were phrased when they worked.
Probes
Follow-ups that repeatedly unlocked more, with the moment each did.
Close
How to end so the last two minutes are not wasted, and what to ask for next.
Recordings-to-interview-guide prompt
The link on its own gets a summary. This is the instruction that produces the 5 sections above, in that order, with the rules that keep them honest. Paste it with your recordings — in Ancher, or in whatever assistant you already use.
Build an interview guide from these past interview recordings. State what the next round needs to learn given what these already settled. Identify which questions produced short rehearsed answers and rewrite them. Promote the unscripted follow-ups that repeatedly opened participants up into planned probes, citing the moment each worked. Note where asking for a screen share turned description into evidence, and end with a close that sets up the next contact.
The detail, if you want it
How each part of a recording becomes a section
| From the recording | Into | Why |
|---|---|---|
| Transcript with timings | Core questions | Locating where each answer actually got interesting requires timings, since the payoff rarely arrives in the same minute as the question. |
| Duration and timeline | Probes | A follow-up that turns a thirty-second answer into a four-minute one has proven itself, and length is how you find it. |
| Unresolved threads | Goal | What earlier sessions raised and never resolved is the honest objective for the next round of interviews. |
| Commitment language | Close | What participants said they would do next tells you what to ask about at the close, and who is worth returning to. |
| Screen shares, if it is video | Probes | The moments where somebody shared their screen are the moments a description turned into evidence, so the guide should ask for that. |
Everything Ancher keeps from a recording
Transcript with timings
Every segment carries start and end seconds, which is what turns a claim into a record.
Commitment language
I'll take that, by Friday, let's park it — these phrases are what separate a task list from a topic list.
Unresolved threads
What a conversation failed to close is usually the reason for the next one.
Screen shares, if it is video
A shared screen is sampled as frames, so the number that drove a decision stays attached to it.
Duration and timeline
Where the time actually went is a finding in itself for any recurring meeting.
The four steps
- Add the recording. Upload the audio or video file. Ancher transcribes it and keeps a start and end time on every segment, so any line in the output can be traced back to the moment it was said.
- Nothing gets flattened. Transcript with timings, commitment language, unresolved threads, screen shares, if it is video, duration and timeline stay separately addressable instead of collapsing into one block of text.
- Ask for a interview guide. Ancher fills goal, warm-up, core questions, probes, close using the mapping above, not a generic summary pass.
- Check it before you use it. Every specific keeps a link back to where it came from in the recording, so a claim can be verified without reopening the source.
Where this goes wrong
- A question that worked with five participants may have worked because of those five. Watch for questions that only land with one type of user.
- Do not let the guide grow. A guide built from everything that ever worked is too long to run and forces you to rush the probes, which is where the value is.
- Reusing recordings of participants for guide-building is still processing their data, and their consent needs to cover it.
Questions people ask
How does it know a question failed?
By what followed it. A question answered in one short, tidy sentence and immediately left behind produced a rehearsed answer, and the pattern is obvious once several interviews are compared.
How many past interviews are needed?
Three or four is enough to see which questions consistently produce short answers. Below that you are looking at a single participant's conversational style rather than at your guide.
Why note when someone shared their screen?
Because that is the moment a description became a demonstration, and demonstrations are consistently more accurate. If a question reliably leads there, the guide should ask for the screen explicitly.
Bring your own recordings
Everything you save lives in one workspace, so the interview guide is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a recording? The same interview guide also comes from PDF, web page.