How samadritaacharya/meeting-intelligence-agent works
Meeting Intelligence Agent is a Streamlit application that turns pasted transcripts, uploaded audio, or sample content into a structured meeting decision package, then presents it and offers downloadable reports and operational artifacts. Analysis can use Anthropic or a deterministic fallback; local Whisper transcription is optional. The excerpts show the main analysis call and PDF export call, while the README documents the broader export formats and product outputs. Some app wiring for audio and non-PDF exports is not excerpted, so those links are marked unverified.
Main entry points: app.py Streamlit workspace · analyzer.py Meeting analyzer · exporter.py PDF report
Components 16
Meeting workspace
- Streamlit workspace
app.py - Transcript and audio input
app.py - Decision package views
app.py
Analysis pipeline
- Meeting analyzer
utils/analyzer.py - Deterministic fallback
utils/analyzer.py - Anthropic analysis
utils/analyzer.py - Whisper transcription
utils/analyzer.py - Response normalization
utils/analyzer.py
Operational artifacts
- PDF report
utils/exporter.py - DOCX report
utils/exporter.py - Jira action CSV
utils/exporter.py - Risk register CSV
utils/exporter.py - Markdown notes
utils/exporter.py
Other components
- Meeting user
- Anthropic API
- Local Whisper
Connections 16
- Meeting user → Streamlit workspace: uses
README.md - Streamlit workspace → Transcript and audio input: collects
app.py - Streamlit workspace → Meeting analyzer: analyzes transcript
app.py - Transcript and audio input → Streamlit workspace: provides meeting content
README.md - Streamlit workspace → Decision package views: presents results
app.py - Meeting analyzer → Deterministic fallback: falls back to
utils/analyzer.py - Meeting analyzer → Anthropic analysis: requests analysis
utils/analyzer.py - Anthropic analysis → Anthropic API: calls
utils/analyzer.py - Meeting analyzer → Response normalization: normalizes response
utils/analyzer.py - Streamlit workspace → Whisper transcription: transcribes audio
app.py - Whisper transcription → Local Whisper: uses
utils/analyzer.py - Streamlit workspace → PDF report: exports PDF
app.py - Streamlit workspace → DOCX report: offers DOCX download
README.md - Streamlit workspace → Jira action CSV: offers action CSV
README.md - Streamlit workspace → Risk register CSV: offers risk CSV
README.md - Streamlit workspace → Markdown notes: offers Markdown
README.md