MeetRecord

Build me a focused revenue meeting intelligence workflow for the personal core of MeetRecord. Requirements:

- Use exactly this stack: Python 3.12 + FastAPI + whisper.cpp + SQLite. Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
- Paid product context: Call recording, coaching, scorecards, and CRM-linked revenue intelligence. Build only this DIY scope: Build a private revenue meeting intelligence pipeline that accepts an audio file, transcribes it, creates structured notes, and exports Markdown.
- For revenue meeting intelligence, import a consented recording and preserve its original hash and duration.
- Transcribe into timestamped segments and produce notes whose decisions and actions link back to segment IDs.
- Review the transcript and export Markdown with action owners and source timestamps.
- Use a local web page with input, progress, review, and export views. Required input or access: FFmpeg; local Whisper model or optional API key in .env. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: When transcription fails, keep the recording; every quoted note must reference a segment that exists in the saved transcript.
- Out of scope: calendar and CRM integrations; cross-call team analytics. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

# AGENTS.md — Build guide for MeetRecord

## Project scope
Build a private revenue meeting intelligence pipeline that accepts an audio file, transcribes it, creates structured notes, and exports Markdown.

Catalogue verdict: no. Do not mistake the interface for the product. MeetRecord's durable value is capture, integrations, reliability, which a solo one-shot build cannot reproduce responsibly. The prompt therefore builds only the closest honest personal consolation tool.
Use the implementation prompt below to define the deliverable. Complete each phase's acceptance checks before extending the scope.

## Working agreement
- Inspect the repository and its existing instructions before choosing paths, dependencies or commands. Keep one coherent stack and explain changes to the proposed architecture.
- Plan a vertical slice that accepts a real input and produces the useful output described below. Persist only the state the prompt calls for; respect memory-only and upstream-managed workflows. Use fixtures only when they are clearly labelled.
- After scaffolding, document the actual install, development, check and build commands in README and keep them synchronized with the package or project manifest. Do not report commands as successful unless they ran.
- Work in small steps. At handoff, list implemented flows, checks actually performed, remaining blockers, and any credentials or provider setup the owner must supply.
- Do not publish, spend money, contact customers, delete source data or run irreversible migrations without the project owner's authorization.

## Prerequisites
- Python 3.12
- FFmpeg
- local Whisper model or optional API key in .env
- Explicit README warning that this is a consolation build, not a production replacement

## Stack and architecture
- Use exactly this stack: Python 3.12 + FastAPI + whisper.cpp + SQLite.
- Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
- Interface for this revenue meeting intelligence workflow: a local web page with input, progress, review, and export views.

## Security and data integrity
- When transcription fails, keep the recording; every quoted note must reference a segment that exists in the saved transcript.
- Keep API keys and OAuth secrets in .env; redact them from logs, generated files, and error responses.
- State the practical limit: calendar and CRM integrations.

## Agent implementation rules
- Project rule, data: Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
- Project rule, behavior: For revenue meeting intelligence, import a consented recording and preserve its original hash and duration.
- Project rule, recovery: When transcription fails, keep the recording; every quoted note must reference a segment that exists in the saved transcript.

## Optional agent skills and references
No installable skill is listed for this guide; use the project rules and the stack documentation.

Read the linked SKILL.md and its dependencies before adding a skill. Select only the skills matching this project's runtime and task; their documentation does not supply API access, credentials or approval to perform external actions. Pin the reviewed revision where the tool supports it. Follow the chosen agent's documented project-level installation mechanism.

## Distribution ideas
These are optional planning notes. Obtain the owner's approval before publishing or contacting anyone.
- Demonstrate this revenue meeting intelligence operation with sample or user-owned data: For revenue meeting intelligence, import a consented recording and preserve its original hash and duration.
- Show a concrete result or export: Review the transcript and export Markdown with action owners and source timestamps.
- State the practical limit: calendar and CRM integrations.

## Engineering roadmap
1. Phase 1, architecture and data: Use exactly this stack: Python 3.12 + FastAPI + whisper.cpp + SQLite. Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
2. Phase 2, implement: For revenue meeting intelligence, import a consented recording and preserve its original hash and duration.
3. Phase 3, implement: Transcribe into timestamped segments and produce notes whose decisions and actions link back to segment IDs.
4. Phase 4, review and output: Review the transcript and export Markdown with action owners and source timestamps.
5. Phase 5, recovery and acceptance: Verify this invariant with a saved fixture: When transcription fails, keep the recording; every quoted note must reference a segment that exists in the saved transcript. State the practical limit: calendar and CRM integrations.

## Paid-product capabilities outside this build
- calendar and CRM integrations
- cross-call team analytics
- meeting-bot auto-join
- live multi-speaker accuracy

## Implementation prompt
Build me a focused revenue meeting intelligence workflow for the personal core of MeetRecord. Requirements:

- Use exactly this stack: Python 3.12 + FastAPI + whisper.cpp + SQLite. Model source documents, editable pages or notes, internal links, revisions, and exports; retain source IDs and timestamps.
- Paid product context: Call recording, coaching, scorecards, and CRM-linked revenue intelligence. Build only this DIY scope: Build a private revenue meeting intelligence pipeline that accepts an audio file, transcribes it, creates structured notes, and exports Markdown.
- For revenue meeting intelligence, import a consented recording and preserve its original hash and duration.
- Transcribe into timestamped segments and produce notes whose decisions and actions link back to segment IDs.
- Review the transcript and export Markdown with action owners and source timestamps.
- Use a local web page with input, progress, review, and export views. Required input or access: FFmpeg; local Whisper model or optional API key in .env. Keep credentials in .env.
- Acceptance: with one labelled sample, show the input, saved intermediate state, and exported result; verify this invariant: When transcription fails, keep the recording; every quoted note must reference a segment that exists in the saved transcript.
- Out of scope: calendar and CRM integrations; cross-call team analytics. Keep this a personal, inspectable workflow.
- Include a README with setup, a sample input, required keys or permissions, data location, and the supported scope.

## Completion evidence
Demonstrate the prompt's acceptance scenarios against the scoped workflow. Include setup from a clean checkout and failure recovery. Check persistence across restart and export/restore only for the state the prompt says to store; for memory-only tools, confirm that temporary content is discarded as specified. Record actual results and remaining limitations. A detailed plan alone does not establish a working replacement.