Meeting-driven work intelligence

    Most meetings are in violation of common sense.Stop working on work. Get work done.

    71% of senior managers say their meetings are unproductive (HBR). Yet the status, the commitments and the risks were all said out loud in them. Then the meeting ended and someone wrote it up from memory.

    meetapp.ai reads the pipeline reviews, QBRs and team weeklies you already hold. It scores every deal, account and project on what was actually said, then chases whatever's missing. A deal nobody has spoken to in six weeks can't show green.

    0
    CRM updates, status decks or forms asked of anyone
    100%
    of scores trace to a quote, a speaker and a date
    Never
    a score on a person. Deals, accounts and projects are scored; the people in the room are not
    Silence
    counts against the score: an account gone quiet can't read green
    The meeting problem

    Six rules every business enforces, until a meeting starts

    Not because the people in them are careless. Because a meeting is the only process most businesses run with no specification, no record of what it was supposed to establish and no check on whether it did. A sales call, a QBR and a team weekly all break the same six.

    It starts without a stated purpose.

    Every other process has a spec. A room's purpose is set before anyone joins and that purpose becomes the agenda.

    The agenda is abandoned by item three.

    Whatever the meeting never reached is logged as a gap against the dimension it was meant to feed, before anyone leaves.

    Actions leave the room without an owner or a date.

    Commitments are lifted out with the name and the date attached, from the words that were actually said.

    The next one re-establishes what the last one decided.

    Decisions and open loops carry forward. The session starts where the previous one stopped, not where memory failed.

    The person who actually decides was never in the room.

    Coverage shows which of the people this work needs have actually been in a room with you. A decision-maker you have never met is a red cell, not a footnote.

    Nobody checks whether any of it happened.

    What the room agreed is checked against what actually happened, not to grade anyone, but so nothing quietly falls through.

    A meeting with a purpose is a unit of work.

    None of these are hard problems. They survive because nothing holds a meeting to its own purpose. Give the room a purpose, hold the agenda to it, take the record out automatically. The hour stops being something you report on afterwards and starts being where the work gets done.

    Work on work, versus work done

    Same book of business, same people. The difference is how much of the week goes into keeping everyone informed about the work instead of doing it.

    WORK ON WORK
    • Someone loses a day a week assembling a status pack that is stale before it is read.
    • Half of every review is spent establishing what happened since the last one.
    • Chasing missing information is somebody's entire Thursday.
    • Every call ends with ten minutes of CRM. Monday's forecast still gets argued from memory.
    • The account's health score is whatever the CSM last typed in.
    • “Why is this account amber?” starts a two-day email chase.
    • The dashboard is a month behind, everyone knows it, so nobody opens it.
    • The agenda gets abandoned by item three and nobody notices what was not covered.
    WORK DONE
    • The status is already there. It came out of the meetings you were holding anyway.
    • That part is already written. The review starts where it should have started.
    • Whatever the meeting never reached gets asked for on its own and closed when the answer lands.
    • The deal scores itself from the call. Monday starts from what the buyer actually said.
    • The health score is what the client said at the last review, quoted.
    • Click the dimension. There's the sentence, the speaker, the date.
    • The board moves when a meeting moves it and says so when it has not heard anything.
    • What the meeting never reached is logged as a gap before anyone leaves the room.
    How it works

    From a calendar invite to a live score

    Not a note-taker with a dashboard attached. One chain, where every link is configured from the one after it: the board decides what the room needs, the room decides what the agenda covers and the agenda decides what counts as missing.

    1Configure the room

    Every team, deal, client or project gets a room, set up from what your board measures. Room type, lifecycle, participants, cadence and lens all come from one definition.

    2The agenda sets the coverage

    The room's purpose becomes the meeting's agenda: the specification for what this conversation has to establish. Circulated before; carried forward when it isn't reached.

    3Email and meetings are digested

    Transcripts, recorded calls, forwarded threads and attached documents, all read automatically. No forms, no data entry, no new habit for anyone to maintain.

    4Intel lands in the room

    Commitments with owners and dates. What was agreed, what was dodged, what was promised last time. Every item anchored to the words that produced it.

    5The room feeds the board

    Room intel maps onto your dimensions at your weights, scored deterministically and rolled into triage. AI writes the narrative; it never writes the number.

    6The gap scanner closes what's missing

    The transcript is scored against the agenda. Anything not covered, not answered or gone stale becomes a gap with an owner and a route home.

    Open gaps lead the next agenda

    Six links, one loop. Every one of them used to be somebody’s job.

    The idea

    Most agendas are a courtesy. This one is a data contract.

    In most businesses the agenda is circulated an hour before and abandoned by the second item. Here it's the specification. When a room is configured, the board tells it what it needs to know and those requirements become the agenda. The meeting is now carrying a defined payload.

    Afterwards the transcript is read back against it, item by item. That comparison is what turns “we ran out of time” from a forgettable moment into a tracked gap with a name against it. Nobody has to notice. Nobody has to raise their hand.

    Service performance since last review
    Covered
    figures given, quoted
    Service Delivery refreshed
    Adoption and usage
    Partially covered
    promised, not tabled
    Commitment logged · owner · due date
    Commercial and renewal position
    Never reached
    meeting ran out of time
    Gap raised · leads the next agenda

    Coverage isn't a judgement call. It's the agenda, checked against what was actually said.

    Digestion

    A transcript, a forwarded thread, a PDF attached to it

    Businesses don't produce clean data. They produce recordings, email chains, board packs and hallway confirmations. meetapp.ai treats all of it as one input class: unstructured material that contains, somewhere inside it, facts a room is supposed to hold.

    Meetings
    • Recorded calls and video meetings
    • Live or pasted transcripts
    • Reviews, QBRs, 1:1s, board sessions
    • Speaker-attributed: who said it is part of the record
    Email and documents
    • Threads sent or forwarded to the room
    • Attachments read in full: packs, accounts, certificates
    • Replies to gap requests, parsed and applied
    • Filed against the right entity, because the room is the entity

    Nothing is matched by guesswork. Email routed to a room lands on that entity; there's no sender-domain lottery deciding whose account it belongs to.

    Live, not a video

    Switch the room type. Watch the whole board reconfigure.

    Filter the book, sort it worst-first, open a row, click a dimension through to the quote behind it, generate this week's digest. Fictitious data, real engine.

    Internal
    Commercial
    The company
    The fund
    Client Engagements

    One room per account. QBRs, service reviews and escalations land in it; the board shows which clients are healthy, which are drifting and which have simply gone quiet.

    14 clients
    Lifecycle axis
    14 clients5 healthy4 watch2 critical3 not enough signal
    Client
    Score
    Nothing stays missing

    The part that goes and gets what's missing

    Every dashboard tells you what it knows. This one works on what it doesn't. The gap scanner runs continuously across the whole book; everything it finds has an owner and a route home.

    Never covered

    The agenda called for it; the meeting didn't reach it.

    Unanswered

    Asked for, acknowledged, not delivered.

    Gone stale

    Last signal is older than this dimension tolerates.

    Unowned

    A commitment with no name or no date against it.

    Into the next agenda

    As an item to Ask, Confirm or Bring, leading the meeting.

    Into the weekly digest

    As a request with a reply scaffold; the reply closes it.

    Straight to whoever owes it

    A chase with the original ask quoted back.

    Silence is a signal, not an absence.

    A request that goes unanswered for three weeks doesn't leave the score unchanged; it lowers confidence in it. Data quality erodes the longer you go without the next update and that erosion belongs on the screen, not in someone's head.

    Evidence on every score

    Click the number. Land on the sentence.

    Most tools summarise a meeting. We take evidence from it. The reason people stop trusting status dashboards is that nobody can say where a number came from, so here every dimension decomposes into the signals behind it and every signal carries the exact words, who said them and which session they were said in.

    The standard is absolute: no quote, no claim. Anything the model cannot anchor to something actually said is discarded rather than estimated. It measures the work, never the people doing it.

    Relationship4.2 ▼1.1
    Sponsor delegated down · 2nd consecutive review · 12 Jun
    “I'll send someone from my team, I can't make it.”
    Client sponsor, Quarterly review, 12 June

    Illustrative. Every score on the live demo drills down the same way.

    And a score we can't back, we don't show.

    A dimension with no recent signal reads as unknown, not as average. An entity that's gone quiet is flagged stale, not fine. Coverage sits on the card next to the score, because the most dangerous entity on any board is the one at a comfortable middle number because nobody has heard from it.

    No span, no record

    Extraction that can't quote itself is discarded, not guessed.

    Deterministic numbers

    The score is arithmetic on signals. AI writes only the prose.

    Coverage and freshness

    How much of this score is actually evidenced, on every entity.

    Full history

    Every movement keeps the meeting that caused it.

    One engine, configured

    The same machine, pointed at eleven different books

    Rooms, agendas, lenses, dimensions, roll-up, gap scanner: one engine. What changes per client is the configuration: what a work stream is, what the board groups them by and which dimensions the business actually judges health on.

    Teams & Projects
    2 room types

    Your own work, run internally. A project spans teams and a team spans projects: two room types, one set of meetings underneath.

    Team
    Recurring team meetings
    Row TeamAxis FunctionEvery 7d
    Project
    Delivery and programmes
    Row ProjectAxis PhaseEvery 14d
    Sales & Client
    2 room types

    One commercial relationship, end to end: the same room model from first discovery call through to renewal.

    Sales
    Deals and pipeline
    Row DealAxis StageEvery 14d
    Client Engagements
    Accounts and renewals
    Row ClientAxis LifecycleEvery 30d
    Founders
    1 room type

    The company's own operating book: every work stream inside it, scored on the meetings already being held. It is one half of a two-sided pair: the same board meeting feeds the fund's book too, with a boundary down the middle. The fund's six rooms are below.

    Founder
    The company's own operating book
    Row Work streamAxis DomainEvery 14d
    The fund
    6 room types

    A portfolio board is one room of six. A company is sourced, diligenced and transacted long before anybody monitors it; it leaves through an exit, with fund operations running alongside all of it.

    1
    Sourcing
    Pipeline before it becomes a deal
    Row
    Prospect
    Axis
    Pipeline Stage
    Every
    14d
    2
    Due Diligence
    What the diligence actually established
    Row
    Candidate
    Axis
    Diligence Phase
    Every
    7d
    3
    Deal Execution
    From term sheet to funded
    Row
    Transaction
    Axis
    Deal Stage
    Every
    7d
    4
    Investor
    Portfolio companies and boards
    Row
    Portfolio Company
    Axis
    Funding Stage
    Every
    30d
    5
    Exit
    Readiness, buyers and timing
    Row
    Holding
    Axis
    Exit Path
    Every
    30d
    ·
    Fund Operations
    The fund's own operating book
    Row
    Fund workstream
    Axis
    Function
    Every
    30d
    For investors

    New room type, same engine: a configuration, not a rebuild.

    What stays inside, stays inside

    Internal and shareable are architecturally separate

    Your team’s own working notes (open risks, blockers, where things really stand) live on the internal side and cannot cross into anything client-facing. A boundary in the system, not a policy in a document.

    Shared records are approved before they go

    Nothing reaches a client, customer or external party without the owner reviewing it first.

    Facts are human-owned

    AI proposes; the accountable person owns the record. Stage, value and review dates are never written by a model.

    Your model, your keys

    Model routing is centralised and portable, including running entirely on your own provider account.

    Every entity, every score, fully auditable: back to the meeting, the speaker and the sentence.

    The meetapp.ai loop

    Configure the room → the agenda sets the coverage → email and meetings are digested → intel lands in the room → the board scores itself → the gap scanner closes what's missing → and whatever's still open leads the next agenda.

    Every step in that loop is something a person used to do by hand: write the update, compile the board, notice the gap, send the chase. That is the work on work and it is the part that goes away.

    The reporting layer disappears.

    The work is what's left. Open the live demo and triage a board of deals, accounts and projects: evidence, coverage, open gaps and the Monday digest. Fictitious data, real engine.