Agora runs community meetings end to end


Agora runs the whole life of a community planning meeting: what the room agreed to before it convened, what happens while it is in session, and the reviewed record it leaves behind.

One event, from consent to permanent record

A human gate sits between what the system derives and what the community publishes, and there is no path around it.

0%
Choose a stage to hold the band there.
  1. 01

    Consent-gated capture

    Recording starts only within the consent posture set for the event, and a visible recording indicator stays up for as long as it runs. Nothing is captured silently.

  2. 02

    Streaming editable transcript

    The transcript appears as the table talks and the facilitator corrects it in place. A dropped connection buffers locally and reconciles on reconnect, so a dead spot in a church basement costs the record nothing.

  3. 03

    Swappable transcription vendors

    Which vendor transcribes a meeting is a deployment decision rather than an architectural one, which is what puts the vendor agreement check somewhere it can actually be enforced.

  4. 04

    Rolling signal extraction

    While the conversation runs, the analysis engine derives emerging priorities, named barriers, action proposals and a conversation trajectory. The engine proposes; the facilitator keeps, edits or discards.

  5. 05

    Human review gate

    Drafted outputs stay drafts until a named person reviews them and publishes under their own name. There is no auto-publish path anywhere in the system.

    Draft In review Published

  6. 06

    Commitments and reminders

    Accepted proposals become commitments with owners, due dates, reminders, overdue escalation, and completion-rate reporting by sector. An action item stops being a line in minutes nobody reopens.

  7. 07

    The longitudinal record

    Every published report writes into a community-scoped store: recurring barriers over time, priority evolution, completion trends by sector. The strata are what a briefing is later assembled from.

Before

Organizers design the event and write down what the meeting is for. An organizer has to approve that statement before it becomes the reference frame for everything that follows.

During

Each table records while its facilitator curates. The meeting facilitator watches every table at once and sees the patterns no single table can see.

After

Agora drafts the summary and traces every claim back to the conversation it came from. A named person reviews and publishes it, and accepted proposals become tracked commitments.

What the room can see while it is still in the room

What a table sees, what the meeting facilitator sees, and what the wall shows are kept separate in the architecture rather than in a settings panel.

The table cockpit

Each table runs its own view, and it never shows a bare score. It shows a reading and the lines of conversation that justify it, so a facilitator can disagree with the machine using the same evidence the machine used.

Everything the engine derives is kept, edited or discarded by the person running the table.

Illustration, not a screenshot.

The facilitator dashboard

When three tables independently name transportation, the facilitator finds out while the room can still act on it, instead of reading about it in a report three weeks later.

Alerts flag the three states a facilitator would otherwise have to walk the room to find: a table that has stalled, one that has gone silent, and one that has asked for help.

Illustration, not a screenshot.

The display wall

Only what has been explicitly published can reach the wall.

Raw transcript, un-curated signals and speaker attribution have no route to it at all. This is not a permission they are denied; there is no code path that would carry them there.

Illustration, not a screenshot.

Outcome-guided intelligence

A meeting is only on track relative to what it was called for, so Agora measures it against a statement of purpose a person approved before the room convened.

The reference frame

The organizer’s approved statement of outcomes is the reference frame. Nothing becomes an outcome because a model proposed it.

Continuous comparison

As the conversation runs, it is compared against those outcomes rather than against a generic idea of a good meeting.

The scorecard

The end-of-meeting analysis judges each outcome and cites the conversation behind that judgment. Facilitators never see a bare score.

The conversation grouped into themes, with the meeting’s approved outcomes as anchors. Drag to orbit.

Agora watches how the meeting is going while it is still going

Eight detectors watch for the ways a facilitated conversation is known to go wrong. The engine is built and has been evaluated against fixtures taken from real sessions.

These are observations about the process rather than judgments about people. Every one of them is something an experienced facilitator would notice, assuming they could sit at all six tables at once.

Guidance surfaces

The panels that would put this in front of a facilitator are still in development and have not shipped.

A nudge advises the person running the table. It never claims the AI understands the room.

The eight risk detectors

Phragma names the barriers

A barrier described differently at every meeting cannot be counted, compared or resolved.

33 Named barriers
7 Families
9 Routes through
3 Lenses
Hover or focus a route to light the barriers it resolves. Codes, names and routings from the canonical taxonomy v0.1.

The seven families

  • LLegal & Regulatory
  • FFinancial & Incentive
  • IInformational & Technological
  • TTrust & Relational
  • CCultural & Paradigmatic
  • SStructural & Operational
  • PPolitical & Accountability

The nine poroi

  • POR-1 CodifyWrite the agreement down.
  • POR-2 BrokerInsert a human connector.
  • POR-3 AlignRestructure incentives and metrics.
  • POR-4 InstrumentBuild the technical bridge.
  • POR-5 ConveneCreate shared governance.
  • POR-6 TranslateBuild shared language.
  • POR-7 ProbeRun safe-to-fail experiments.
  • POR-8 AdvocateRoute the barrier upward.
  • POR-9 RitualizeTrust through repeated small commitments kept.

Shadow barriers

A shadow barrier is present in the conversation, absent from the formal outputs. It was named in a side comment, or in the sentence somebody said before the note-taker started typing.

These are systematically under-captured, and they are frequently the constraint that actually binds.

The human-confirmation rule

No barrier is attributed to a named organization before a human analyst confirms it. Deciding whose constraint it is stays with a person, permanently.


Where Phragma actually is

Only the first of these four phases exists. The other three are on the roadmap, in the order we intend to build them.

  • Phase A Taxonomy as versioned configuration, plus the analyst workflow. Built and in use.
  • Phase B Automated batch detection over completed events. Not built.
  • Phase C Data signatures and longitudinal barrier tracking. Not built.
  • Phase D Live in-meeting barrier surfacing. Not built, and hard-gated.

We gate our own features. Live surfacing ships only after proven precision on real deployments and a recorded human decision to go ahead.

What the coalition still has in three years

A single meeting is not the unit of value. What matters is what accumulates.

The longitudinal store

Every published report adds to a permanent record: which barriers recur, which priorities moved, and which commitments closed.

The briefing generator

It answers one question: what has this coalition accomplished, and where is it stuck? A claim with nothing behind it does not get made.

Grant Platform export

Community evidence becomes grant evidence, but only from a briefing a named person has already published.

The community keeps what it learned without keeping the recording

Before a transcript is destroyed, everything durable in it is preserved: the decisions, barriers and commitments, each with the evidence behind it. If that preservation has not finished, the deletion does not happen.

A deletion promise gets kept, and the community still keeps what it learned.

chain unverified

Verify re-derives the chain in your browser; tamper alters one entry and re-derives it again.

How the privacy guarantees are actually enforced

Meeting audio at recovery-sector events is treated with the highest level of confidentiality from the first line of code.

  • Encryption

    Every record is encrypted under its own key, so the protection travels with the record rather than with the disk it happens to be sitting on.

  • Access

    A read that is not explicitly permitted does not happen, and the attempt is written down anyway.

  • The audit log

    The log can only be appended to, and each entry commits to the one before it, so a rewrite is visible to anyone holding it.

  • Vendors

    The system refuses at runtime to send protected data to any vendor without a signed agreement on file.

  • Consent

    Recording is gated on the consent the room gave, and a visible indicator stays up for as long as it runs.

  • Deletion

    Deleting a record destroys its key, which makes the data unrecoverable. Deletion is a physical fact, not a flag on a row.

  • Derived data

    Anything derived from sensitive text inherits its sensitivity and its deletion. There is no loophole through a copy.

What is built, what is not

A deliverable is marked done only when its automated checks pass, so this table reflects verified progress rather than intentions.

Delivery status
Milestone What it delivers Status
Core milestone ladder M0–M8 The platform spine: event design, consent-gated capture, live analysis, human review and publication, commitments, and the longitudinal store. Built
Collaborative Strategic Planning (Exhibit C) The planning workbook, complete and in use as a facilitation framework. Built
Knowledge preservation and retention enforcement Retention windows, permanent deletion, and the preservation run a deletion cannot proceed without. Built
Desired Outcomes framework The outcomes document an organizer approves before the event, which becomes the reference frame everything is compared against. Built
Meaning matching Comparing what is said against the meeting’s outcomes, with the vendor behind it swappable. Built
End-of-meeting analysis A judgment on each outcome, with the conversation behind it cited. Built
Conversation State Engine Eight detectors watching how the conversation is going, evaluated against fixtures from real sessions. Built
Phragma Phase A The barrier taxonomy as versioned configuration, with the analyst confirmation workflow. Built
Guidance surfaces Nudge cards in the facilitator view and guidance panels on the dashboard. In development
MOA mode The settlement-specific mode for Memorandum of Agreement reporting. In development
Longitudinal Planning Series chaining Linking a sequence of planning events into one continuous series. In development
Phragma Phase B Automated batch barrier detection over completed events. Roadmap
Phragma Phase C Barrier data signatures and longitudinal barrier tracking across events and years. Roadmap
Phragma Phase D Live in-meeting barrier surfacing. Hard-gated behind proven precision on real deployments and a recorded human go decision. Roadmap
Reasoning Graph track Explicit representation of how a conclusion was reached across a series. Roadmap
Poros, Convocant Grant Platform, Phoreo, Oikos The rest of the portfolio. The Grant Platform export contract is already built into Agora. Roadmap

What you can see in a demo today

The whole lifecycle, running. Set up an event, record a table, curate what the engine finds, and watch the all-tables dashboard flag a table that has stalled or gone quiet.

Then review the drafted summary, follow any claim back to the conversation it came from, publish it as a named reviewer, and turn the accepted proposals into tracked commitments.

How “done” is decided

A milestone is not complete because someone says it is. It is complete when its automated evidence checks pass in the build, and the status column above reads from that result.

Anything this page describes as in development or on the roadmap is exactly that. We are not selling it as shipped.