AI
An AI that turns meeting recordings into tracked actions
A recording of a meeting is transcribed, summarised, and split into action items with an owner and a date. The actions appear in a list that people tick off, and the next meeting starts with what is still open from the last one.
Automatically generated draft
Written by machine against our own engineering playbook. The company is invented; the decisions are the ones we would make on a real build. A reviewed blueprint goes further — nine sections, agreed line by line, and it is what the build is tested against.
Section 01 · What has to work
A meeting recording must reliably transform into actionable tasks that persist into the next meeting's agenda.
Section 03 · Screens
Every screen, and what it is for.
- ›Upload — team member uploads audio file, triggers processing, and waits; progress bar must be instant.
- ›Transcript — team member reads diarized text and summary; scrolling and text highlighting must be instant.
- ›Action List — team member ticks off completed tasks; checkbox state toggle must be instant.
- ›Meeting Prep — team member views carry-over items from previous session; list load must be instant.
Anything not on this list is not in version one. That is what keeps a fixed price fixed.
Section 04 · The data model
What it stores, and who can read a row.
meeting
id uuid, title text, recorded_at timestamptz, audio_url text, raw_transcript jsonb, summary text, status enum(uploaded, transcribing, summarized, failed), created_at timestamptz
Access · Authenticated team members can read rows where organization matches user organization.
action_item
id uuid, meeting_id uuid, owner_id uuid, description text, due_date date, status enum(open, completed, carried_over), created_at timestamptz
Access · Authenticated team members can read rows linked to meetings in their organization.
team_member
id uuid, email text, name text, organization_id uuid, created_at timestamptz
Access · Users can read rows where organization_id matches their own.
Those access rules belong in the database, not in the screens. Someone who edits the address bar still cannot read a row that is not theirs — and the test that proves it blocks delivery if it fails.
Section 05 · States
uploaded → transcribing → summarized → completed | failed(reason)
Most scope arguments three weeks into a build are really arguments about a state nobody named at the start.
Section 06 · Where this breaks
What bites products like this one.
Large audio files exceed transcription API timeout limits during peak upload hours.
Chunk audio files on the client before upload and process asynchronously via background worker queues.
AI incorrectly assigns ownership or misses action items due to conversational ambiguity.
Provide a manual re-assignment and item creation interface directly on the transcript review screen.
Section 08 · Deliberately left out
What version one does not do.
- ×Automatic calendar integration for meeting creation — manual upload is simpler and avoids OAuth complexity for v1.
- ×Voice biometrics for speaker identification — manual speaker label assignment on the transcript view covers initial needs.
This is the section that protects the date, and the only place in the document where somebody says no. It is also why clients trust the rest of it.
Still open
What we would ask before quoting.
- Which speech-to-text and LLM providers are mandated, or do we select based on latency and cost?
- How are team members authenticated and mapped to their organization?
Half of this already exists
Doc Intake
The paperwork half of this is a solved problem: documents read on arrival, validated against your rules, and a person asked only about what does not add up.
It is one of our pre-built products: the code is handed over to you, adapted to your own wording and rules, and the rest of the specification above is built on top of it rather than from scratch.
Your product, not this one
Get this written for what you are actually building.
Describe it in a sentence and the generator returns the same sections for your own product. Free, no email, nothing saved to a list.
Next step
Find out if your idea fits in 10 working days.
Tell us what you want to build. We reply the same day with a straight yes, no, or here is what we would cut.