Free Lesson

From Prompts to Loops: Engineering Reliable Agents

Hosted by Stefan Jansen

Wed, Jul 15, 2026

4:00 PM UTC (30 minutes)

Virtual (Zoom)

Free to join

Invite your network

Go deeper with a course

Engineering a Multi-Agent Forecasting System
Stefan Jansen
View syllabus

What you'll learn

Map any agent to four rungs you can engineer

Prompt, context, harness, loop: see what each one controls, and why you climb them in order.

See what actually makes an agent reliable

Watch a real agent stop smartly, use your own data, trace every step, and reconcile a team of sub-agents.

Take the map to your own agent

Leave able to place any agent you'd build — research, ops, policy — on the same four rungs.

Why this topic matters

Anyone can get an impressive demo from an LLM. Turning one into an agent you can actually rely on comes down to four engineering decisions: its prompt, its context, its harness, and the loop it runs in. In 30 minutes I'll climb all four on a real forecasting agent that researches live questions and scores its own calls — then show you the same map builds any agent, far beyond markets.

You'll learn from

Stefan Jansen

Author, ML for Trading · Founder, Applied AI · Investing since 2013

Stefan is the author of ML for Trading — the book and open-source companion code (20K GitHub stars) that has become a practitioner reference for applying ML to financial markets. The 2026 third edition expands to nine cross-asset case studies, with a foreword by Antonio Gulli, Senior Director, Google.


He maintains the Zipline fork the quant community relies on, and built the six-library stack — data to live — behind the third edition's case studies. Investment partner since 2013, he has built trading platforms and live strategies across asset classes. In 2016, he founded Applied AI, which brings production ML to investment teams and other data-rich verticals. He has taught ML to 110,000+ professionals through DataCamp and General Assembly, incl. at Bloomberg and BlackRock.

See all products from Stefan

Sign up to join this lesson

By continuing, you agree to Maven's Terms and Privacy Policy.