PentagonAI - Market Analysis Agent
A market-analysis backend that turns news and time series into a searchable event graph. Qdrant-based matching, LLM canonicalization, impact links, and an agent council support timelines and forecasts.
A market-analysis backend that turns news and time series into a searchable event graph. Qdrant-based matching, LLM canonicalization, impact links, and an agent council support timelines and forecasts.
What made this system difficult?
Required an operable pipeline for ingestion→extraction→canonicalization→council execution, with queue separation and endpoints for ops/debugging so long-running LLM workflows remain manageable.
How did the design respond?
Built a FastAPI server with domain routers (events/timeline/council/forecast/triggers/search/threads/ops/auth/users) and a Celery worker with stage-separated tasks. Implemented event identity merging, impact link generation, trigger-driven meeting creation, and forecast resolution/scoring endpoints, plus a model-routing debug endpoint for visibility.
How responsibility moves through the system.
Event Pipeline
- — Multi-source collection
- — Entity extraction
- — Temporal parsing
Analysis Engine
- — Embedding-based dedup
- — Impact link generation
- — Timeline visualization
Overview
- Solo-built market intelligence system: ingestion → event extraction → canonicalization/linking → council-style analysis.
Purpose & User Experience
Purpose
- Convert scattered news/time-series into a navigable event graph (search + timeline) and generate forecast artifacts via a council-style workflow.
User Flow (high level)
- Ingest/backfill → extract events → canonicalize/merge → browse timeline/search → run council → resolve/score outputs and review reports.
Key Components
- Celery worker pipelines separated by stage for operational control
- Qdrant similarity search + LLM judgment for event identity/canonicalization
- Event impact linking and multi-agent “council” orchestration
- Ops/debug endpoints (health, routing visibility) for day-2 operations