Free Lesson
Build an ML for Trading Research Workflow with AI Agents
30 min
Nov 18, 2026 11:00 AM
By continuing, you agree to Maven's Terms and Privacy Policy.
What you'll learn
Give a research agent a task it can check
Define an ETF research task with inputs, tools, and acceptance checks before the agent changes code.
Inspect the evidence behind an agent result
Read a worked agent trace, inspect its code changes, and distinguish reported success from verified output.
Connect the agent task to a trading experiment
Connect data, features, validation, and trading costs while retaining responsibility for research decisions.
Why this topic matters
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.
