Tag: #agent-evals
Writing on GPUs, LLMs, MLOps, Kubernetes — and mindset · 1 posts
OpenAI AgentKit and the New Agent Evaluation Workflow: A Practical Guide to Datasets, Trace Grading, and Prompt Optimization
A practical guide for engineering, product, and platform teams on how OpenAI AgentKit changes agent evaluation, with a rollout framework for datasets, trace grading, and automated prompt optimization.
2026-04-12 · 8 min read #ai-platform#agentkit#agent-evals#trace-grading#prompt-optimization