LLMs, agents and the tooling that puts them to work.
A practical guide to evaluating embedding models for code search, comparing open-source and proprietary options, and avoiding common pitfalls.
Prompt caching basics: how cache keys are constructed, why subsequent requests often miss, and practical patterns to improve hit rates.
Examine the mechanics of prompt caching for LLMs: how cache keys are constructed, why prefix matching fails, and how to design prompts for repeatable hits.
Implement JSON Schema to enforce structured, machine-readable responses from LLMs. Compare provider implementations, handle edge cases, and avoid common pitfalls.
