The AI Project Manager that turns transcripts into vault tickets — humans review, never start blank.
Not a writing assistant.
—
Production.
Send this deck to a Head of Product with 5 minutes. They'll know whether to take the call.
A product lead finishes a 90-min customer call Friday at 4pm. Blocks 90 minutes Monday. Drafts tickets. By Tuesday: three tickets duplicate work in flight; one missed the actual decision the call settled.
A consultant runs four discovery calls in a week. By call three, paraphrasing from memory. Proposal Monday reads like generic AI consulting prose. Because that's what running on memory produces.
An engineering lead gets a 2,099-line transcript. Pricing decisions, technical commitments, scope-shifts, a quiet contradiction. The cost of missing one isn't theoretical — it's a misaligned spec by week six.
Most companies, asked where their PM-Vault lives, will point at ClickUp. Their actual PM-Vault is the inside of three senior people's heads. It leaks every weekend.
The bottleneck isn't thinking.
It's transcription.
AI is genuinely good at transcription. The hand-authored ticket flow is the bottleneck nobody's measuring because everyone's paying it.
Same call. Same team. New flow.
transcripts/. Lead types /pm-from-transcript.proposal.yaml. Seven tickets, epics placed, points estimated, RACI inferred. Plus an "ambiguities" block and a "duplicates detected" block.proposal.yaml. Confirms one disputed owner. Accepts a merge. Rejects one ticket as scope-creep. Edits a title. Approves.git commit. Pre-commit hook validates. Seven tickets land in the vault.19 minutes from call-end to ticket-merge.
"Friday afternoon ends with the work captured.
Monday morning starts with delivery,
not transcription."
Anyone can ask Claude to "summarize this call into tickets."
That's a writing assistant.
What we ship is production.
The schema. The review gate. The citation chain. The duplicate detection. The project-context awareness. Output goes into a system of record under version control — not a Slack thread that evaporates by Tuesday.
Six alternatives you've already been pitched.
| Option | Why we passed |
|---|---|
| ClickUp / Linear / Jira AI | Output shaped by the SaaS data model, not your schema. No transcript-line citations. |
| Notion AI / Coda AI | Optimised for reading, not systems-of-record. No schema validation. No commit gate. |
| Custom Zapier + ChatGPT | Hallucinations end up in your system of record. This is how most teams discover the failure mode the hard way. |
| Otter / Fellow / Granola / Read.ai | Strong on transcription; weak on synthesis into your actual ticket schema. Useful upstream; not the painkiller. |
| "Wait for the incumbent" | Their economic incentive is to keep your data inside their SaaS. Their interest is not your interest. |
| "Build it from scratch" | The "I don't know what to evaluate" trap. We treated it as input, not output. |
We didn't pick one. We synthesized. Took the strongest mental model — vault-as-tickets with a pre-commit hook — built a three-stage pipeline on top.
Three agents and a safety net.
Reads line-by-line. Pains · decisions · action items · BANT. Every item linked to the transcript line range.
Reads existing ticket index + schema. Emits proposal.yaml. Surfaces ambiguity rather than guessing.
Writes valid markdown into tickets/. Frontmatter + body autopopulated. Writes but does not commit.
Mechanical, not an agent. Same gate every human passes through. Invalid frontmatter blocks the commit. AI gets no special treatment.
A single agent that "reads a transcript and writes tickets" is the writing-assistant pattern.
Works on demos. Fails in production.
Three agents in series gives:
The hard problems we already paid for.
Each one is roughly two weeks of work to discover, scope, and fix when you encounter it cold. We already paid that tab.
Self-applied. Validated against ground truth.
"We refused to hire a $5K/mo PM."
"We built this instead."
Runs three projects in parallel. Onboards to any new task, industry, or stakeholder instantly. The CR practice has shipped 150+ enterprise AI projects on this pattern.
Most credible kind of evidence: we did this to ourselves before pitching it.
Above the 80% / ≤20% bar set at design time. Reproducible from a real transcript with line citations and a hand-derived ground-truth set.
/pm-from-transcript + 8 minutes.Markdown files under your git history. Self-hosted. Your schema, your conventions.
Every ticket links back to the transcript line range. Replayable, auditable, queryable.
Disable the pipeline. Team falls back to hand-authoring. Zero downtime.
Tickets are .md files. Yours regardless of whether the pipeline runs tomorrow.
What's shipped, what's scheduled.
/ingest-transcript callAnti-overclaim. The credibility bank.
If any of those is what you need, we'll tell you on the first call and send you somewhere honest.
Bring one transcript and the tickets your team hand-derived from it.
We'll show you the pipeline against the same source.
Your meeting cadence, your transcript pipeline, your ticket schema. We tell you honestly if it's a fit. First slots usually within 48 hrs.
The vault-as-tickets pattern this pipeline rides on. The pipeline is the leverage; the vault is the foundation.