Build a Research Agent: Decisions, Workflows and Tools

Thu Nov 12·4:00 PM UTC

Design a Research Agent with Decision Models

Design an agent that chooses what to investigate, selects a tool, and uses the result to decide what to do next. We will connect an open decision model, document retrieval, and Python in an earnings-research example. Inspect the action choices, evidence record, and a failure case, then turn the observation into a testable research question. No trading background is required; basic Python will help you adapt the example.

You'll learn from

Stefan Jansen

Builds production ML and agent systems, then teaches the operating method.

Wed Nov 18·4:00 PM UTC

Build an ML for Trading Research Workflow with AI Agents

AI agents can help write research code, but a completed task is not evidence that a trading idea works. Follow a worked ETF research example: define a task, inspect the agent trace and code changes, then check the result against the research question. See where an agent helps and where validation, portfolio choices, and trading costs still require judgment.

You'll learn from

Stefan Jansen

Builds production ML and agent systems, then teaches the operating method.

Wed Nov 25·4:00 PM UTC

Open-Source Tools for ML Trading Research

Building an ML trading experiment involves market data, features, validation, and a realistic trading simulation. Take a practical tour of the open-source ML4T libraries behind the book, see how their inputs and outputs connect, and find the documented examples you can run. We'll follow one research example and discuss where data access, costs, and validation still require your judgment.

You'll learn from

Stefan Jansen

Builds production ML and agent systems, then teaches the operating method.