Data-RSI: turning useful agent runs into training examples for the next model

PrajwalTomar_ · x · 2026-09-16

Step one of TokenRhythm's approach: the system watches what actually happens during a job — which model did the work, which tools it used, where it failed, how it recovered, and whether the final answer worked.

Useful runs then become training examples for the next model, a concept they call Data-RSI. The full stack has three parts: OpenSquilla runs the job, TokenRhythm API connects it to different models, and NeoHorse-1 is trained from the lessons of those agent runs.

Related event: TokenRhythm launches NeoHorse-1, turning agent run experience into model training(9 posts)→

Original post →

More from coding & agent

coding & agent channel →