Research
Research & blog
ReadMeta-Reward: Reward Modeling as Harness Optimization
Optimizing LLM-judge evaluator harnesses to build better agent reward models.
- Read
Meta-Agent: Continual Learning for Agents
An open-source library that automatically improves agent harnesses from production traces.
- Read
From Knowledge-Work Agents to Self-Improving Systems
How deploying Canvas led us to build the continual-improvement layer for production AI agents.