How youssefamdouni/rde works
Smart Backlog Assistant is a web UI and FastAPI service for turning meeting notes into reviewed backlog changes. Users authenticate, submit notes or questions, and receive streamed results: safety checks and intent routing send meeting notes through topic extraction, story matching, and proposal drafting, while general questions use web search. Users approve, reject, or edit proposals; approved changes update Pinecone and the backlog can be downloaded. The README documents these capabilities; some internal calls and frontend endpoint wiring were not excerpted, so those relationships are omitted or attributed to the README.
Main entry points: main.py FastAPI routes · agent.py Backlog pipeline adapter · llm_config.py LLM configuration · router_agent.py Intent router
Components 21
Web interface
- Chat and review UI
frontend/script.js
API and sessions
- FastAPI routes
backend/main.py - JWT authentication
backend/auth.py
Backlog workflow
- Backlog pipeline adapter
backend/agent.py - Topic extraction
backend/agent.py - Story matching
backend/agent.py - Proposal drafting
backend/agent.py - Proposal review
backend/main.py - Approved-story sync
backend/agent.py - Backlog download
backend/main.py - Backlog ingestion
sample_data/ingest_backlog.py
Assistant capabilities
- Input safety guard
backend/guard.py - Intent router
backend/router_agent.py - Web-search agent
backend/web_search_agent.py - History compression
backend/memory_manager.py - Tavily search
Persistence and configuration
- LLM configuration
backend/llm_config.py - Application database
backend/database.py - Pinecone index
- Structured logging
backend/logger.py
Other components
- User
Connections 26
- User → Chat and review UI: submits input
README.md - Chat and review UI → FastAPI routes: uses API
README.md - FastAPI routes → JWT authentication: requires identity
backend/main.py - JWT authentication → Application database: reads and writes
backend/auth.py - FastAPI routes → Application database: stores sessions
backend/main.py - FastAPI routes → Input safety guard: checks input
README.md - FastAPI routes → Intent router: classifies input
README.md - Intent router → Backlog pipeline adapter: routes meeting notes
README.md - Intent router → Web-search agent: routes questions
README.md - FastAPI routes → Backlog pipeline adapter: streams pipeline
backend/main.py - Backlog pipeline adapter → Topic extraction: runs step one
README.md - Backlog pipeline adapter → Story matching: runs step two
README.md - Backlog pipeline adapter → Proposal drafting: runs step three
README.md - FastAPI routes → Proposal review: accepts decisions
README.md - Proposal review → Approved-story sync: syncs approvals
README.md - Approved-story sync → Pinecone index: upserts stories
README.md - FastAPI routes → Backlog download: serves download
README.md - Web-search agent → Tavily search: searches web
backend/web_search_agent.py - Web-search agent → History compression: compresses history
backend/web_search_agent.py - Backlog ingestion → Pinecone index: seeds vectors
sample_data/ingest_backlog.py - Input safety guard → LLM configuration: configures classifier
backend/guard.py - Intent router → LLM configuration: configures classifier
backend/router_agent.py - Backlog pipeline adapter → LLM configuration: configures models
backend/agent.py - Web-search agent → LLM configuration: configures synthesis
backend/web_search_agent.py - History compression → LLM configuration: configures summarizer
backend/memory_manager.py - Backlog pipeline adapter → Structured logging: logs activity
backend/agent.py