Blog
Technical notes on agent architectures, context enginerring, and evals.
Self-Improving Agents: From One-Shot Prompts to Closed Reasoning Loops
How coding agents go from one-shot code generators to systems that check and fix their own work, using test-time compute and real compiler and test output.
Building Tools for AI Agents
A field guide to tool names, tool scope, schemas, and error messages your agent can act on.
Context Rot in Long-Context LLMs
Why longer prompts make models worse at finding the right code, and how coding agents avoid look-alike distractors.