mattorb Stay curiousTighten Feedback LoopsIterate, Measure, LearnFan of Science, Design, and Systems Thinking

Ohhhhh...

Ohhhhh…

For fun, I’ve been building a little distributed agent scheduling system to explore different AI-related dev practices and workflows … with an eye towards stacking up primitives and finding compounding effects …

I just added Option ‘A’ here, which works sooooo much better than anticipated, I am dazed. There’s no substitute for a pro [human] designer, but with some taste (reject most ideas and adopt/try a select few), this raises the floor so much it feels crazy.

Terminal interface for creating a new agent job chain, with Visual Brainstorm HM×N selected and its fan-out and synthesis workflow described.

Here’s a little peek inside the engine for that first run and the models used, that I am still digesting…

Would have cost me ~$12 in tokens (if not for subscriptions).