AI agent evaluation, observability, and education
AI needs supervision.
I build tools, frameworks, and courses that help developers see what their agents are doing, measure whether they are working, and improve them before users find the failure modes.
Read
Technical writing
Guides and essays on AI agents, observability, RAG, evaluation, and ML quality.
Watch TalksRecorded sessions on trustworthy data agents, hallucinations, RAG, and observability.
Learn CoursesHands-on AI courses across DeepLearning.AI, Coursera, LinkedIn Learning, and Stanford.
Build ProjectsOpen-source tools and experiments, from AI evaluation infrastructure to civic calculators.