The flagship program
Mastering AI Agents in Finance
Three levels, one path, from your first API call to production systems a risk committee can audit. Every level is built the same way I learned this myself: raw code first, so you understand what the frameworks are doing before you let them do it for you.
The path
Three levels. Each one stands alone. Together, a crescendo.
Start where you are. Level 1 gets you building agents from scratch. Level 2 makes you an architect of multi-agent systems. Level 3 makes your systems production-grade: guarded, traced, and evaluated.
AI Agents in Finance: The Complete Foundations
From your first LLM API call to your first multi-agent finance system. For Python-capable finance and tech professionals starting from zero on LLMs: you hand-build your own agent harness, the loop that turns a language model into something that acts, before touching any SDK, so when the framework arrives, nothing in it is magic.
- Hand-build tool calling, the agent loop and ReAct, then rebuild on the OpenAI Agents SDK
- Memory that persists across runs + agentic RAG with LlamaIndex
- Multi-agent handoffs, routing, and agents-as-tools
- Deep dives: Morning Briefing Desk (Espresso) · Financial News Bot (Hot Take) · Earnings Season Watchtower (Harvest)
Multi-Agent Systems in Finance: The Architect Course
You've built an agent. Now learn to design systems of them that you can defend in an architecture review: stateful graphs that branch, persist, and resume; reasoning patterns with an honest cost model; memory and context engineering; multi-agent orchestration with human approval gates; and agentic RAG built two ways, hand-rolled in LangGraph and framework-native with LlamaIndex. Built around three committee-grade finance deep dives.
- Think in graphs, not loops: typed state, branching, checkpointing, mid-run resume
- ReAct, reflection, and self-consistency built as graphs, plus evaluator-optimizer, handoffs, and agents-as-tools
- Memory that survives sessions, workflow patterns, and tracing what your agents actually did
- Deep dives: Autonomous Rates Analyst (Reflex) · FX Strategy Desk (Bullfight) · ETF Portfolio Construction Team (Sous-Chef)
Production AI Agent Systems in Finance
The gap between a demo and a system your institution will actually run is guardrails, observability, and evaluation, not more prompting. This level covers the complete agent landscape, then goes where no other level goes: harness and loop engineering, guardrails, security and auditability, tracing at scale, and evaluation in depth, including RAG evaluation. The systems you build here are meant to survive an audit.
- Harness and loop engineering: budgets, circuit breakers, checkpoint and resume
- Guardrails, injection defense, audit trails, and observability with cost dashboards
- Evaluation in depth: LLM-as-a-judge, tool-call and trajectory evals, RAG evaluation
- Deep dives: Autonomous Rates Analyst (Iron Reflex) · Regulated Robo-Advisor Platform (By the Book) · Global Macro Monitoring Desk (Watchdog)
Self-assessment
Which level am I?
Thirty seconds of honesty saves you a wrong purchase. Each level stands alone; join where the description matches you.
You've never built an agent
You write Python, you follow the AI news, but you've never wired a model to a tool and watched it act. Start at Level 1: Foundations. You'll build the agent loop by hand before any framework touches your keyboard.
You've built one; now you want architectures you can defend
You've shipped a single agent or a chatbot with tools, but multi-agent design, memory, and agentic RAG are still improvisation. Go to Level 2: The Architect Course. You'll learn the patterns and when each one earns its complexity.
You need production-grade systems
Your prototype works; your compliance team is unconvinced. Go to Level 3: Production Systems. The harness, guardrails, security, tracing, and evaluation: the parts that turn a demo into something a risk committee can audit.
How I teach
The pedagogy, stated plainly
These four choices shape every chapter across all three levels. If you disagree with them, this program isn't for you; better to know now.
Raw first, then SDK
You build tool calling, the agent loop, and RAG in plain Python before any framework. When abstractions break in production, and they do, you'll know exactly what's underneath.
Finance-native labs
No pizza-order tutorials. Every lab is a desk you could sit at: briefing desks, credit committees, FX strategy, robo-advisory. The domain friction is the point.
Build-up, not toy-hop
Systems grow chapter over chapter instead of resetting to a new toy every lesson. You finish each level with something coherent, not a folder of disconnected demos.
Notebooks + script mirrors
Every lab ships as a Colab-ready notebook and a mirrored Python script: explore in the notebook, then see the same code structured the way production code actually looks.
Questions
Frequently asked
What are the prerequisites?
Working Python: you can write functions, use dictionaries, install packages, and read a stack trace without panic. That's it for Level 1; no prior agent or ML experience is assumed. Levels 2 and 3 assume you've built at least one agent (from Level 1 or elsewhere). No finance background is required, though the labs will feel more familiar if you have one.
Do I have to take the levels in order?
No. Each level is standalone, with its own on-ramp. The program is a crescendo if you take all three, but if you've already built agents on your own, join directly at Level 2 or 3; the self-assessment above is an honest guide to where you belong.
What is the refund policy?
Level 1 (self-paced) carries a 30-day money-back guarantee. The cohort courses (Levels 2 and 3) offer a full refund through the end of week 1: enough time to attend the first live call, work the first labs, and decide with real information. No forms to justify, no friction.
When do the next cohorts start?
Level 1 is self-paced; start whenever you enroll. Levels 2 and 3 run in cohorts a few times a year, and dates are announced to the waitlist first. Join the waitlist to get the next dates and the first-15 enrollment bonuses.
Will this teach me to trade or pick stocks?
No. Let me be explicit: this program teaches you to engineer AI agent systems for financial workflows: research, analysis, document intelligence, advisory tooling, monitoring. It does not teach trading strategies, stock picking, or any way to make money in markets, and nothing in it is investment advice. If that's what you're looking for, this is not your course.
Ready?
Pick your level. Start building.
From your first hand-built agent loop to a deployed, guardrailed system; the path is laid out. The only question is where you enter it.
Not sure? Take the 30-second self-assessment or ask me directly.