Wed, Nov 4, 2026
5:00 PM UTC (30 minutes)
Virtual (Zoom)
Free to join
Go deeper with a course
Engineering a Multi-Agent Forecasting System
Stefan Jansen
Author, ML for Trading (Ch. 24: agents) · Founder, Applied AI
Wed, Nov 4, 2026
5:00 PM UTC (30 minutes)
Virtual (Zoom)
Free to join
Go deeper with a course
Engineering a Multi-Agent Forecasting System
Stefan Jansen
Author, ML for Trading (Ch. 24: agents) · Founder, Applied AI
What you'll learn
See the failure modes a single agent doesn't have
Watch two independent runs land on different numbers, and see why that spread carries information a single run hides.
Bound what each agent is allowed to do
Learn how narrowing each agent's job makes the whole system easier to trust and cheaper to debug.
Check results before the system acts on them
See the verification the harness runs between steps, so one bad answer doesn't propagate through the system.
Why this topic matters
A multi-agent system has more ways to fail than a single call: agents drift off task, errors compound across steps, and independent runs disagree. The fix is engineering, not better prompts. This lesson covers where they break and the harness patterns that keep them reliable, from bounding each agent's job to checking results before they act, using the system built in the workshop.
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 (19,000+ GitHub stars) that have 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.