Governed LLM agents for hedge funds, risk and portfolio management. A free, open course that takes you from LangChain v1 fundamentals to designing a governed multi-agent hedge fund, with real code and verified institutional sources.
Major funds no longer ask whether to use language models, but how to govern them. Kensho (S&P Global), Bloomberg, JPMorgan, BlackRock and Man Group run agentic systems in production today. This course teaches exactly that: how those systems are built, evaluated and governed when real money is at stake.
No order goes out without a human signature. No number is invented by the model: a deterministic tool computes it and the LLM explains it. Every module applies this boundary — understand, reason, act — backed by the institutional evidence behind it.
From the institutional landscape to the capstone: a governed multi-agent hedge fund, end to end.
Real buy-side adoption, verified institutional cases, and the golden rule: the LLM reasons, the math decides, the human vetoes.
OPEN →The Runnable mental model, LCEL, structured output with Pydantic, and low-level tool calling.
OPEN →create_agent, middleware, StateGraph, persistence, real human-in-the-loop, and multi-agent patterns.
OPEN →2026 source map, programmatic SEC EDGAR, news and sentiment, and point-in-time pipelines without traps.
OPEN →Structure-aware chunking, hybrid search with reranking, the text/numbers split, and RAGAS evaluation.
OPEN →Role-based system prompts, few-shot, judicious chain-of-thought, and anti-numeric-hallucination grounding.
OPEN →Exact VaR and Expected Shortfall, stress testing, and the LLM as an explanation layer, never a calculator.
OPEN →Efficient frontier, Black-Litterman with LLM views, and optimizer sensitivity.
OPEN →From text to signal, backtests without look-ahead, realistic costs, and the deflated Sharpe ratio.
OPEN →AI Act, NIST AI RMF, model risk management, and auditable evidence for agentic systems.
OPEN →Observability with LangSmith, continuous evaluation, costs, latency, and governed deployment.
OPEN →Full integration: research, risk, portfolio, and execution with human sign-off in a single system.
OPEN →Every formula in the course, checked against the primary literature, in a single reference.
OPEN →Full environment setup: dependencies, APIs, paper trading, and lab conventions.
OPEN →Course terminology: from LCEL to point-in-time, precisely defined.
OPEN →All the course evidence: papers, official docs, engineering blogs, and primary sources, verified as of July 2026.
OPEN →LCEL pipelines, agents with middleware, audited tool calling, bull/bear debates with LangGraph, risk dashboards: copyable, commented LangChain 1.x code aimed at production.
421 verified sources: documented deployments at Kensho, Bloomberg, JPMorgan, BlackRock, Man Group, Bridgewater, AQR, Balyasny and Point72 — and also the independent replications that debunk the hype.
Exact formulas checked against the primary literature, point-in-time data, realistic costs and the deflated Sharpe ratio. Where there is no evidence, the course says there is none.