Shown·ChatGPT agent, Cursor, Custom agent
Multi-agent stock analysis pipeline
ChatGPT agent, Cursor and Custom agent: The author built a LangGraph system where valuation, sentiment and fundamental agents plus a coordinator rate four stocks and backtest the resulting portfolio.
A working pipeline that outputs picks, performance metrics and a chart, with a 63-day backtest against an equal-weight benchmark and a test suite.
Overview
How it was set up
Cursor and Claude for code and prompts, ChatGPT Agent mode for news and SEC filing data, LangGraph for orchestration, financialdatasets.ai for prices, VADER for sentiment.
Worth knowing
Prototype with no transaction costs, one backtest window (Aug to Nov 2024), survivorship bias, and thresholds chosen by trial rather than tuned.
A prompt to start from
The source does not show the prompt.
Sources 1
History
- Added to Agentic Feats
- 2026-10-13
- Pick
- No
- Markdown copy
- /c/multi-agent-stock-analysis-pipeline-cursor.md
More in finance and admin
22 featsResultAbout two minutes after the setup worked, a dozen FSA reimbursement claims had been submitted automatically.
ResultThe author handled complicated legal and medical insurance forms while feeding their newborn daughter, with Claude doing the filling.
ResultCodex caught real errors, including a wrong Schedule L field mapping, and the author found their own 2025 mistakes.