Bulkhead Forge — product / Actions
Meetings go in. Tracked action items come out.
Actions listens to the conversations your team already has — Google Meet today, Slack and email next — transcribes them, and turns every decision into an assigned, deduplicated action item. A tracker that fills itself.
Working MVP · Runs on Google Cloud · EU region
Illustrative pipeline output — the stages are real, the file and counts are placeholders, not a measured client run.
The problem
Meetings end. Follow-ups evaporate.
Decisions get made in calls, then live in one attendee's notes — if anywhere. Trackers only know what someone bothered to type in, so they drift from reality within a sprint. Actions closes the gap at the source: the conversation itself.
| Artefact | Today | With Actions |
|---|---|---|
| Notes | One attendee's doc, unread after Friday | Structured analysis filed next to the recording |
| Follow-ups | Re-typed into a tracker by hand — or not at all | Extracted, assigned and deduplicated automatically |
| Decisions | Folklore within two weeks | Logged with the meeting, the owner and the date |
How it works
From spoken word to tracked item
-
Phase 01
Capture
New Google Meet recordings are detected automatically. Any video or audio in Drive can be submitted by hand. Typed items work too — automation shouldn't forbid keyboards.
-
Phase 02
Transcribe
Audio is extracted with ffmpeg, staged to Cloud Storage and transcribed with Speech-to-Text V2 (chirp). The Markdown transcript is filed next to the source recording.
-
Phase 03
Analyse
A model reads the transcript under an enforced JSON schema: summary, key topics, decisions, action items, open questions, risks, follow-ups. Constrained output — not free-form parsing.
-
Phase 04
Track
Items land in the console with owners, labels, comments and subtasks. A confidence-gated second pass catches duplicates — a re-raised topic gets a "discussed again" comment, not a clone.
What you get
Tracker ergonomics, minus the typing
-
Auto-extracted action items
Owner, status, due date — pulled from speech, then editable like any task you'd have typed.
-
Duplicate guard
Dedup verdicts carry high / medium / low confidence; you set the weakest verdict that's allowed to act.
-
Decision log
Every decision is kept with its source meeting — the "why" survives the quarter.
-
People, not strings
Speakers resolve to real people; assignees are accounts with history, not names in a cell.
-
Context that survives
Labels, comments, subtasks and relations between items — everything a tracker owes you.
-
Full activity trail
Who changed what, when — every item carries its history, human edits and agent edits alike.
Sources
A source is an adapter
The pipeline doesn't care where the words came from. Each channel is a thin adapter in front of the same transcribe → analyse → track path — so adding one doesn't touch the core.
Live today
- Google Meet — recordings detected automatically
- Google Drive — drop any video or audio file
- Manual — create and edit items by hand, anytime
On the roadmap
- Slack — threads and huddles into the same pipeline
- Zoom — recordings from outside the Google world
- Email — decisions made in writing count too
Your team talks somewhere else? Tell us — adapters are the cheap part.
Google Cloud
Built on Google Cloud from day one
Running today
- Cloud Run services & jobs — europe-west1
- Speech-to-Text V2 (chirp) transcription
- Cloud SQL (PostgreSQL) + Cloud Workflows
- Google OAuth · Drive & Meet APIs
- Secret Manager · Artifact Registry · keyless WIF deploys
- Cloud Monitoring — every model call metered (ai.model.*)
Where Gemini fits next
- Long-context transcript analysis — an hour of meeting in one pass
- Schema-enforced action-item extraction on Vertex AI
- Dedup verdicts as fast, cheap classification calls
- Provider swap is config, not code — calls are already metered per feature, so cost per meeting is visible from the first day
Roadmap
Where this goes
Now
- Meet auto-ingest & Drive uploads
- Analysis, dedup, decision log
- Console tracking: people, labels, comments
Next
- Slack & email adapters
- Gemini on Vertex AI for analysis & dedup
- Slack notifications on new items
Later
- Two-way sync with Jira & Linear
- Cross-meeting insights per person & topic
- Public API for custom sources
Early access
A tracker that fills itself. Try it before everyone else.
Working MVP, onboarding a first cohort of teams on Google Workspace. No forms — one email is the whole first step.
contact@bulkheadlogic.com