What is meeting intelligence?
Meeting intelligence is the analysis layer above transcription: instead of recording what was said, it reports what the meeting meant — which decisions were made and against which trade-offs, who committed to what in their exact words, where the disagreement was, who changed position, and what the room avoided.
Notes answer “what was said”, intelligence answers “what happened”
A transcript is a record; a summary is a compression of that record. Both are backward-looking artefacts that a careful reader could have produced. Meeting intelligence makes claims: this decision was made without anyone naming an alternative; this commitment has now been promised in three consecutive meetings; this objection was answered with a change of subject. Those are findings, and the useful ones are uncomfortable — which is precisely why they need evidence attached.
What makes a finding trustworthy
Three things, and a tool that skips any of them is guessing. Attribution: real speaker names, taken from the meeting itself rather than inferred from voice, otherwise “who deferred to whom” is fiction. Citation: every claim anchored to a quote and a timestamp, so it can be checked in seconds. Memory: the ability to compare this meeting to previous ones, because patterns — repeat blockers, recycled promises — are invisible in a single session.
Why custody and candour are the same problem
A report that names who dominated the room and which question got dodged is genuinely useful and genuinely sensitive. Teams will only tolerate that honesty if the artefact stays inside their own perimeter. That is the design logic behind Donna: the analysis is blunt because the storage is private, and the storage is private because the analysis is blunt.
Related questions
Is meeting intelligence just a better summary?
No. A summary compresses; intelligence interprets and takes a position, then cites the evidence for it. The test is whether the output can surprise you — a summary of a meeting you attended rarely can.
Does it need video, or is audio enough?
Audio carries almost all of it: who spoke, what was said, who deferred, what was avoided. Video adds the shared screen, which matters for demos and design reviews. Donna records both and analyses the transcript.
What does Donna produce specifically?
A report of eight or nine sections depending on the lens — the plain story first, then decisions with trade-offs, verbatim receipts, tensions, what nobody said, position shifts, the room read, and owned, dated follow-ups.
Put Donna in your next meeting
Access is open — sign in with your Google account and she’s in your dashboard in minutes. Rolling out to a whole team, or want a hand with the server setup? We’re glad to help.