Recording
Your recording
Paste your recording. Nothing to upload.
←recording
Make a executive summary
Turn a recording into an executive summary
For the person who was not on the call and has four minutes.
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.
Bottom lineSituationKey numbersRisks
Executive summary
One page that leads with the conclusion and the decision being asked for.
An hour of conversation reduces to about half a page of things that actually matter: what was decided, what it costs, what is still open, what is being asked for. Ancher promotes the decision above the discussion that produced it, keeps a timestamp on every claim so the summary can be audited, and states plainly when a meeting reached no decision at all.
The honest version
Most meetings decide nothing, and the summary has to be willing to say so
The pressure on any summary is to produce something that looks like progress, and a conversation that circled for an hour can be written up to sound conclusive. That write-up then becomes the record, and the next meeting starts from a decision nobody made. A summary that says no decision was reached is more useful and much harder to write.
One second of one recording, at 52:30, read two ways.Illustrative. The figure is invented; the gap it falls into is not.
so where does that leave us — I think we're saying but let's confirm next week
On the shared screen — not readThe specific never reaches the draft
Executive summary
On the shared screen
Budget: 240k, unapproved
from 52:30
Lands in the draft, with its timecode
- The bottom line is a decision only if one was actually made; otherwise it says so.
- Every claim carries a timestamp, so the summary can be checked against the recording rather than trusted.
- The ask is separated from the discussion, because that is what the reader is deciding about.
What comes out
Executive summary, section by section
One page that leads with the conclusion and the decision being asked for.
Bottom line
The decision in one sentence, or a plain statement that none was reached.
Situation
Only the context a reader who was absent needs to make the bottom line intelligible.
Key numbers
Figures discussed, each with its timestamp and whether it was said or shown on screen.
Risks
What was raised as a concern and not resolved.
The ask
What is being requested of the reader, separated from everything above.
Recording-to-summary 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 recording — in Ancher, or in whatever assistant you already use.
Turn this recording into an executive summary. (1) State the decision in one sentence, or say plainly that none was reached. (2) Give only the context an absent reader needs. (3) List figures with their timestamps, marked SAID or ON SCREEN. (4) Record concerns raised and not resolved. (5) State the ask separately. Do not attribute positions to individuals — this source has no speaker labels — and do not invent a decision.
The detail, if you want it
How each part of a recording becomes a section
| From the recording | Into | Why |
|---|---|---|
| Commitment language | Bottom line | Decision language is distinguishable from discussion language, which is what lets a summary say honestly whether anything was settled. |
| Transcript with timings | Key numbers | Start and end seconds on every segment mean a figure in the summary can be played back rather than argued about. |
| Screen shares, if it is video | Key numbers | In a screen-shared call the number is on the screen while the speech points at it, so the frame is where the figure actually is. |
| Unresolved threads | Risks | What the conversation failed to close is the honest content of a risks section, rather than a list of worries. |
| Duration and timeline | Situation | How long a meeting ran against what it settled is context a reader deciding whether to attend the next one wants. |
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 executive summary. Ancher fills bottom line, situation, key numbers, risks, the ask 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
- Writing a decision into a summary that the meeting did not reach is the single most damaging thing this artifact can do, because the summary becomes the record.
- There are no speaker labels, so a summary cannot say who argued for what. Do not let a write-up imply attribution the source cannot support.
- Numbers said aloud in meetings are frequently approximate. Check anything consequential against the screen frame before it reaches a one-pager.
Questions people ask
What if nothing was decided?
Then the bottom line says so. That is a real and common outcome, and recording it accurately is more useful than a summary that reads as conclusive and quietly invents a settlement.
Can I attribute positions to people?
Not from this source. There are no speaker labels, so the summary reports what was said and not who said it. If attribution matters, you need a source that separates speakers.
Why timestamp a summary?
So it can be audited. A one-page summary of a ninety-minute call is a large compression, and the timestamps are what let someone disagreeing with it check the specific moment rather than the whole recording.
Bring your own recordings
Everything you save lives in one workspace, so the executive summary is built from your sources — not from a model's memory of the internet.
Open Ancher →Not a recording? The same executive summary also comes from YouTube video, PDF, X thread.