Unquarked: “I'd like to see a concerted MI effort to exploit the capabilities of AI. Others have posted about training an AI agent with well-validated concepts, relevant articles, and data sets, and then prompting it to produce various screens.”

A set of examples from P123: Say hello to Alphanaut, our new AI agent - Latest Release -
community.portfolio123.com - Say hello to alphanaut our new AI agent
>> This is less than a year old, at this point as marco says “it is a good explainer / weak creator”. It will explain what a screen does including what each factor or factor ratio does.

P123-Claude-Skill: GitHub - github.com - Claude Skill Agent Skill for Portfolio123 (P123): 464 functions, 4456 factors, verified line-by-line against official docs. Factor investing, screening, ranking systems, backtesting, and p123api Python wrapper. Works with Claude Code, Cursor, and Codex. · GitHub

Historical fundamental data is becoming harder to get at a reasonable price. AAII Stock investor Pro until a couple of years ago used to have their historical data on their website for subscribers but their latest vendor made them take down all the data from previous vendors.