Subscribe
Sign in
Home
Book
Chapters
Libraries
Primer
Agent Lab
Archive
About
Latest
Top
Discussions
How to Design and Evaluate Skills for Research Agents - and the ML4T Skills Release
We are releasing 61 open-source ML4T skills for quantitative research. Two new benchmarks show where written procedures help and why strong verification…
Sep 1
•
Stefan Jansen
4
1
August 2026
How to Evaluate a Financial Research Agent as a System
From task interpretation and evidence retrieval to calculation, judgment, synthesis, and repeated-run reliability.
Aug 27
•
Stefan Jansen
2
1
Six Libraries for Quantitative Research in the Age of Agents
Data, features, models, diagnostics, backtesting, and live trading are now stable on PyPI. Why we built them, and why coding agents make a tested tool…
Aug 13
•
Stefan Jansen
13
2
July 2026
How Bridgewater Engineers a Research Agent
Five design decisions from PAT that do not need a 50-year archive, and the point-in-time test the talk leaves open.
Jul 29
•
Stefan Jansen
7
1
The Third Edition Publishes Tomorrow
What is new since 2020: the research process front and center, nine cross-asset case studies, six open libraries, 459 notebooks, 112 primers, and 61…
Jul 23
•
Stefan Jansen
7
2
2
The Coding-Agent Toolkit: A Workflow Loop You Can Install
Seven host-neutral steps to improve agent productivity, now public, that run the same on Claude Code and OpenAI Codex.
Jul 7
•
Stefan Jansen
7
1
A Coding-Agent Reading List: Behind the Loops
Loop engineering is only the surface. A reading path through the older control problems underneath — and the line between what a coding agent may change…
Jul 2
•
Stefan Jansen
9
4
From Research to Production with Nine Case Studies
A hands-on ML4T course built on nine case studies: one research workflow from feasibility through deployment — equities, options, futures, FX, and…
Jul 1
•
Stefan Jansen
3
1
2
June 2026
New Release: From Data to Model-Ready Evidence
The ML4T code release for Chapters 6-10 covers the research framework, labels, feature engineering, model-based features, and text features.
Jun 29
•
Stefan Jansen
1
How to build a Multi-Agent Forecasting System
They can turn current unstructured evidence into scorable probabilities, but the output has to compete with a model, market, or human baseline.
Jun 25
•
Stefan Jansen
3
2
2
New Release: The ML4T Data Layer Is Now Public
This release makes the Chapters 1-5 code public and focuses on the data foundation: data loaders, market microstructure, as well as alternative and…
Jun 22
•
Stefan Jansen
5
1
The ML4T Third-Edition Code Rollout Starts Today
Between now and launch, the public repo will fill in stages: workflow, case studies, libraries, and the checks that turn model forecasts into trading…
Jun 19
•
Stefan Jansen
3
3
2
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts
