Product Evals: Travel Planner, Long Context, and The Weight Of Taste
May 22, 2026 · 4 min · 664 words · jiaxing ni
Context Engineering: Retrieval, Memory, and The Shape Of Evidence
May 22, 2026 · 3 min · 637 words · jiaxing ni
Agentic RL: Reward, Behavior, and The Long Shadow Of Feedback
May 22, 2026 · 4 min · 749 words · jiaxing ni
Evals As Instruments: Measuring What The Demo Hides
May 22, 2026 · 4 min · 729 words · jiaxing ni
Agent Design: Loops, Tools, and the Shape of Memory
May 22, 2026 · 4 min · 747 words · jiaxing ni