Write a PRD

PRD: AI Meeting Summaries — Decisions & Action Items

Sep 24, 2026 · @Martin Slaney

Summary

We will generate a summary after every recorded Huddle meeting that lists the decisions made and the action items, each with an owner who was verifiably in the meeting. The organizer reviews the summary and sends it in one click; nothing is emailed without that step in v1.

Problem. Today attendees write their own notes after the call. Notes are inconsistent, often missing, and action items lose their owners within a day. We already have what we need to fix this: a recording, a transcript with speaker labels, and the calendar attendee list.

Why this is not trivial. Two of those inputs are unreliable. Speaker labels are wrong about 8% of the time, mostly during crosstalk and when several people share a meeting-room device. About 15% of meetings include someone who joined without a calendar invite. A naive build would misassign owners often enough to lose trust in the first week.

Goals and metrics

The goal is summaries people send without rewriting, with zero actions assigned to non-attendees.

Goals

• Replace manual post-meeting notes for recorded meetings.
• Every action item has a correct owner or is explicitly marked unassigned.
• Get action items to owners within minutes of the meeting ending.

Non-goals (v1)

• Pushing tasks into Jira, Asana or Linear.
• Summaries for unrecorded meetings or live, in-call summaries.
• Improving diarization itself. We design around the 8% error rate, not fix it.

Success metrics

Owner precision is measured from organizer edits plus a weekly labelled sample of 200 meetings.

Users and core flow

The organizer owns the summary; attendees receive it.

• Organizer: reviews, fixes owners, sends. Usually the calendar invite's creator; can hand off to any attendee.
• Action owner: receives their items by email and in the app.
• Other attendees: receive the full summary once sent.

```mermaid flowchart LR A[Meeting ends] --> B[Transcript +<br/>join log ready] B --> C[Build verified<br/>roster] C --> D[Extract decisions<br/>and actions] D --> E[Roster filter +<br/>confidence check] E --> F[Organizer review] F --> G[Send to owners<br/>and attendees] ```

The roster filter runs as deterministic code after the model, never inside the prompt alone.² Target: summary ready for review within 5 minutes of meeting end for meetings up to 90 minutes.

Requirements

An owner can only be chosen from the verified roster: people who actually joined, not people who were invited.

Verified roster

1. R1. Build the roster from the join log, not the calendar invite.¹ Invited people who never joined are excluded. 2. R2. Each roster entry has an identity tier: - Verified: joined signed in to a Huddle account, or by a dial-in matched to a known number. - Guest: joined with a display name only (most of the 15% uninvited joiners). - Room: a meeting-room device; people behind it are unknown individuals. 3. R3. Match uninvited joiners to workspace accounts by signed-in account only. Never match on display name alone.

Summary content

1. R4. Decisions: a short statement of each decision, with a transcript timestamp link. No owner field.
2. R5. Action items: task, owner (or "Unassigned"), due date if said aloud, timestamp link, and confidence.
3. R6. Every item links to its evidence in the transcript so reviewers can check it in one click.

Assignment rules

1. R7. The model returns a proposed owner per item. Code then checks it against the roster. Any owner not on the roster is replaced with "Unassigned", and the named person is shown as a mention ("mentions: Dave, not in meeting").
2. R8. Owner comes from content first: a named request ("Priya, can you…") beats the speaker label of "I'll do it".
3. R9. Mark an owner low confidence when the evidence depends on a speaker label in an overlapping segment, a Room entry, or a Guest entry.
4. R10. Low-confidence items show as "Suggested: Priya" and need organizer confirmation before any email goes out.
5. R11. Room and Guest entries cannot receive email. The organizer can reassign to a verified person or leave it unassigned.
6. R12. Log every model proposal, filter result and organizer edit. This is our precision measurement.

Handling the known limits

Both limits hit ownership, not decisions, so we contain them at the owner step.

The error compounds per meeting. If each item's owner is wrong 8% of the time, a meeting with 5 action items has a 34% chance of at least one wrong owner (1 − 0.92⁵). That is why confirmation sits before email, not after.

Sales request: auto-email on meeting end

Decision: not in v1 as requested. We ship one-click organizer send now, and gated auto-send in phase 2 once measured precision earns it.

Why not now. An email to the wrong owner is the most visible failure this feature can have. With the error rate above, roughly a third of 5-item meetings would email someone a task that isn't theirs. With external guests, it may land outside the customer's company. Early trust is hard to win back.

What Sales gets instead.

• v1: the organizer gets a "Summary ready" notification within 5 minutes and sends with one click. Goal: sent within 30 minutes (see metrics).
• Phase 2: a workspace setting to auto-send at meeting end, but only items that are high confidence and owned by a Verified attendee. Everything else still waits for the organizer. It ships only when owner precision on high-confidence items is ≥ 97% for 4 consecutive weeks.
• Auto-send never emails Guest or Room entries, or anyone outside the customer's domain, unless an admin enables it.

Design notes

The review screen must make checking owners faster than writing notes.

• Decisions first, then action items grouped by owner, then Unassigned.
• Low-confidence owners look visibly different ("Suggested") and are editable inline from a roster picker, never free text.
• Each item plays its transcript clip on click.
• The Send button states who gets email: "Send to 4 owners and 7 attendees".
• Empty state: if no decisions or actions are found, say so plainly rather than inventing any.

Rollout

Open questions

• [ ] Is the join log's signed-in identity reliable enough to call "Verified"? Engineering to confirm.
• [ ] Who organizes when the invite creator didn't attend? Proposed: first Verified attendee from the invite.
• [ ] Do customers need to disable summaries per meeting for sensitive calls? Legal and Sales to confirm.
• [ ] Retention: how long do we keep drafts and the evidence log?

PRD: AI Meeting Summaries with Decisions and Action Items

Status: Draft for engineering and design leads Product: Huddle

1. Problem

Huddle records and transcribes meetings with speaker labels, but attendees still write their own notes afterward. Notes are late, inconsistent, or never written, so decisions get lost and action items have no clear owner. We will generate a summary after each meeting that lists decisions and proposes action items with owners.

2. Goals and non-goals

Goals - Produce a summary within 5 minutes of meeting end: decisions, action items (task, owner, due date if stated), and open questions. - Never assign an action item to someone who was not in the meeting (hard constraint, see §4). - Keep the host's review to under 60 seconds for a typical meeting.

Non-goals (v1) - Fully automatic emailing of action items to owners (see §3). - Cross-meeting task tracking or integrations with Jira, Asana, and similar tools. - Summaries for meetings without a transcript.

3. Decision on the Sales request

Sales asked for action items to be emailed automatically to owners the moment a meeting ends. We are not building that for v1. Instead, we will send the draft summary to the host at meeting end. The host can send it to owners with one click, and owners are emailed on send.

Reasons: - Speaker labels are wrong about 8% of the time. An automatic email would sometimes tell a real person they own a task they never agreed to. Because it goes out with no human check, the error becomes visible to a customer's colleagues. - Email is irreversible, so a wrong or non-attendee assignment cannot be quietly fixed afterward. - The underlying Sales need is that owners hear about their tasks quickly and nothing falls through the cracks. A host prompt at meeting end with one-click send meets that need at the cost of a few seconds.

Path to automation: Auto-send will be an opt-in, per-workspace setting, considered after launch once the gates in §9 are met. It would send only high-confidence, presence-verified items and leave everything else for host review. Engineering should build the send pipeline so that auto-send is later a policy change rather than a rebuild.

4. The hard constraint: who can own an action item

Rule: An action item's owner must be a participant who was actually in the meeting when the item was discussed. Anyone else is ineligible.

This rule cannot rely on the calendar invite, and it cannot rely on the model behaving well.

Attendance source. The eligible-owner roster is built from Huddle's session join/leave logs, not from the calendar invite. This handles both failure modes: - Invitees who never joined are not on the roster. - The roughly 15% of meetings with uninvited joiners include those people, matched to a user account when possible.

Presence at time of item. A person is eligible for an item only if they were in the session at the timestamp of the relevant utterance. Someone who left at minute 10 cannot own an item from minute 40.

Enforcement is structural, not prompt-based. 1. The extraction step receives the roster as a list of participant IDs and must return an owner ID from that list or `null`. 2. A deterministic validator runs after the model. It rejects any owner ID not on the roster or not present at the item's timestamp, and it converts that item to unassigned. 3. The UI and email layers accept only validated owner IDs. There is no free-text owner field on the model output path. 4. Names mentioned in the transcript who were not present ("have Dana look at it") produce an unassigned item. The text may keep the speaker's wording, but Dana gets no assignment and no email.

Shared rooms. A room device usually appears as one participant, so individuals in the room are not in the presence log. We cannot verify that a named person is in the room. Such items become unassigned by default, and the host can attest who was in the room during review (§6). That attestation counts as human-verified presence.

Uninvited joiners without an account (guests) can be eligible owners, shown by display name. They receive email only if the host supplies an address during review. We never guess addresses.

5. Handling speaker-label errors

The 8% label error rate is concentrated in crosstalk and shared rooms. Eligible-owner enforcement does not solve it, because a mislabel can still pick the wrong person who was present. Mitigations:

Confidence tiers (High/Medium/Low) are stored on each item, shown to the host in review, and used later to gate auto-send. Thresholds are set empirically during the evaluation in §9. The tiers themselves are a v1 requirement.

6. User experience

Host flow 1. The meeting ends and the host gets a notification: "Summary ready to review." 2. The review screen lists: - Decisions as short statements, each linked to the transcript moment. - Action items with the task, owner chip, due date if stated, and a confidence indicator. - Unassigned items grouped at the top of the actions list, so gaps are visible. 3. The host can edit text, reassign from a picker limited to eligible people, delete items, or add room attendees ("Who was in the room?"). Adding room attendees makes them eligible for items in the room segments. 4. Send emails each owner their own items plus the decisions. Unassigned items go to no one.

Design requirements - Every item has a "jump to source" link that plays the transcript segment. Reviewing should be verification, not re-listening. - The owner picker never offers non-attendees. If the host wants to assign to an absent person, show a separate option, "Send as a follow-up (not from the meeting)," which is a different item type with clearly different wording and no "you agreed to" language. Design to decide whether this ships in v1; the default is that it does not. - Low-confidence owners appear as suggestions ("Suggested: Sam") and never as assignments. - Email copy says "Action item from Meeting name, date", includes the source excerpt, and offers a "This isn't mine" link that notifies the host. This gives owners a correction path. - If the host does not review, send a reminder at 24 hours. Nothing is sent to owners without host action in v1.

7. Functional requirements

1. Roster service: builds the per-meeting roster with join/leave intervals from session logs and links to user accounts where possible.
2. Extraction: from the transcript and roster, produce decisions, action items, and unassigned items. Each action item has task text, owner ID or null, due date or null, source timestamps, and a confidence tier.
3. Validator: enforces §4 as code with unit tests, independent of the model, and logs every rejection.
4. Review UI: as described in §6, on web and desktop. Mobile is view-only for v1.
5. Delivery: per-owner emails on host send, with a record of who was emailed. Sends are idempotent, and edits after sending trigger an explicit "send update" action.
6. Audit log: stores for each item the model output, validator result, host edits, and send events.
7. Admin setting: workspace-level toggle for summaries, plus retention aligned with existing transcript retention.

8. Edge cases to specify and test

• Invitee never joined but is mentioned as owner.
• Uninvited joiner takes an action; the guest has no account.
• Person leaves and rejoins (multiple intervals).
• Two people share a first name; ownership must resolve by roster, and ambiguity means unassigned.
• Whole meeting in a shared room (all items default unassigned until the host attests).
• Multiple languages, or a transcript with large gaps.
• Nobody commits to anything: show "No action items detected" rather than inventing some.

9. Success metrics and launch gates

Launch gates (must all pass) - Zero non-attendee assignments across a labeled evaluation set of at least 500 meetings, deliberately oversampled for uninvited joiners, shared rooms, no-show invitees, and crosstalk. Any production occurrence afterward is a Sev-1 incident. - Among High-confidence items, wrong-attendee assignment rate of 3% or less (target, to be validated against the evaluation set; propose a stricter figure if data supports it). - Median summary delivery within 5 minutes of meeting end.

Post-launch metrics - Share of meetings where the host sends the summary within 1 hour. - Host edit rate per item, and owner "This isn't mine" rate. - Share of action items left unassigned. Some is healthy, but a high rate means the model is too timid.

Auto-send criteria (future): two consecutive months of High-tier precision above the agreed bar and no non-attendee incidents. Sales and Support are consulted before enabling.

10. Risks and open questions

• Sales disagreement. Sales may see the host step as friction. We should share §3 with them early and offer a pilot of auto-send with a few design-partner accounts after the gates are met.
• Hosts skipping review. If sending rates are low, the fix is better reminders and faster review, not removing the check.
• Presence data quality. Do our session logs reliably capture join/leave for all clients and dial-in users? Engineering to confirm in week 1.
• Guest privacy. Can we email or display guest names without consent, given customer policies? Legal to advise.
• Room attestation. Is host attestation adequate for the constraint, or should room participants confirm individually? Recommend host attestation for v1.
• Follow-up items for absent people. Ship in v1 or defer? Design and Product to decide.

11. Milestones

1. Weeks 1–2: roster service, presence data audit, evaluation set labeling begins.
2. Weeks 3–5: extraction, validator, confidence tiers, offline evaluation.
3. Weeks 4–7: review UI and email delivery, in parallel.
4. Weeks 8–9: internal dogfood, gate review.
5. Week 10: limited beta with design-partner customers, including Sales' accounts.