Early Access to Weco's Autonomous ML Engineer

Aiden, Weco's autonomous ML engineer, works alongside your team: proposing and testing its own ideas, opening its own PRs, and shipping measurable improvements. It's the agent behind the results above, and it runs privately, inside your own environment.

Work email

What would you want it working on?

How does your team measure model performance today?

A

Automated evals that return a score (F1, AUC, latency, LLM-as-judge, win rate, etc.)

B

Have a metric, but evaluation is mostly manual

C

Looking at outputs and judging quality directly

D

Still figuring out our eval setup