unknown

Self-improving agents isn’t a single algorithm - it’s a systems engineering problem involving:
- eval data curation + maintenance
- experiment design to battle overfitting
- an update algorithm
- human review during the process & especially before prod

we share practical learnings + a local research scaffold to autonomously hill-climb harness centered around evals

our goal is to give everyone the tooling and infra to measure and iteratively their improve agents. Evals are training data for agents which fuels this loop

let's build the future of well-designed, self-improving systems 🚀

<p>Self-improving agents isn’t a single algorithm - it’s a systems engineering problem involving:
- eval data curation + maintenance
- experiment design to battle overfitting
- an update algorithm
- human review during the process &amp; especially before prod

we share practical learnings + a local research scaffold to autonomously hill-climb harness centered around evals

our goal is to give everyone the tooling and infra to measure and iteratively their improve agents. Evals are training data for agents which fuels this loop

let's build the future of well-designed, self-improving systems 🚀</p>

Harrison Chase

Self-improving AI agents are framed as a systems engineering challenge rather than a single algorithm, involving eval data curation and maintenance as key components.