Recording
Your recording
Paste your recording. Nothing to upload.
←recording
Make a research report
Turn recordings into a research report
One interview is a story. Six is a finding — but only if the sixth can contradict the first.
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.
The questionKey findingsEvidenceCounterpoints
Research report
A structured answer to a question, with the evidence and the counter-evidence attached.
The failure mode of interview research is deciding after two conversations and then hearing agreement in the next four. A report is only worth circulating if it can be traced back and disagreed with. Ancher works across a whole collection of recordings, reports how many participants supported each finding rather than how strongly one did, and keeps the passages that cut against it with the timestamps attached.
The honest version
A finding carries its count and its counter-evidence, or it is an opinion
Reports usually present findings as settled and quote the participant who put it best. That hides both how many people actually said it and who said the opposite. Because the recordings sit in one collection with timings intact, Ancher can state how many of them support a finding and link the passages that do not, which is what makes a report something a sceptical reader can use.
One second of one recording, at 27:33, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
we tried it for about and then went back to the spreadsheet
Shared during the session — not readThe specific never reaches the draft
Research report
Shared during the session
Trial abandoned at day 9 of 30
from 27:33
Lands in the draft, with its timecode
- Each finding says how many participants it rests on, so a single vivid interview cannot pass as a pattern.
- Passages that contradict a finding are kept and cited rather than quietly dropped.
- Every supporting quote carries the recording and the second, so any claim can be checked without asking the researcher.
What comes out
Research report, section by section
A structured answer to a question, with the evidence and the counter-evidence attached.
The question
What was being investigated, and what the sessions could and could not settle.
Key findings
Each finding with the number of participants behind it.
Evidence
Quotes with the recording and the timestamp attached.
Counterpoints
What was said against each finding, kept rather than smoothed away.
What to check next
Which findings are thin and what would firm them up.
Recordings-to-research-report 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.
Write a research report across these interview recordings. State the question and what these sessions can and cannot settle. For each finding, give the number of participants supporting it. Attach quotes with their recording and timestamp. Include a section of passages that contradict each finding rather than omitting them, and end with which findings are thin and what would strengthen them.
The detail, if you want it
How each part of a recording becomes a section
| From the recording | Into | Why |
|---|---|---|
| Transcript with timings | Evidence | Timings turn a quote into something a reader can verify themselves, which is the difference between evidence and assertion. |
| Unresolved threads | What to check next | Questions a session raised and did not answer are the honest agenda for the following round of interviews. |
| Commitment language | Key findings | What a participant said they would actually do next is stronger evidence than what they said they preferred. |
| Screen shares, if it is video | Evidence | A screen shared during a session shows the real workflow rather than the described one, and the two frequently differ. |
| Duration and timeline | Counterpoints | How long a participant argued against something is a signal that the finding is contested, not incidental. |
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 research report. Ancher fills the question, key findings, evidence, counterpoints, what to check next 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
- Counting mentions is not measurement. Six interviews can show a pattern worth investigating; they cannot tell you its size.
- Without speaker labels, a group session blurs whose view is whose. For attributable findings, one participant per recording is the safer design.
- Interview recordings carry consent, retention and often anonymisation obligations that vary by jurisdiction and by what you promised participants.
Questions people ask
How many recordings should be in the collection?
Enough that the count means something. Five or six is where a repeated observation stops being a coincidence, though it still tells you a pattern exists rather than how common it is.
Why keep counter-evidence?
Because a report without it cannot be argued with, and a report that cannot be argued with does not get trusted by anyone who was not in the room. The dissenting passages are also where the next round of questions comes from.
Can findings be traced to a specific participant?
To a specific recording, always. To a specific person within a recording, only if that recording has one participant, since there are no speaker labels — which is a good reason to record sessions individually.
Bring your own recordings
Everything you save lives in one workspace, so the research report is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a recording? The same research report also comes from YouTube video, PDF, X thread.