Discover AI Workflows
Explore prompts, agent designs, model notes, and developer tools
Explore prompts, agent designs, model notes, and developer tools
Evaluate agents with measurable outcomes.
How to build an evaluation set that actually catches regressions.
Practical tricks to make LLM judging more stable.
Chunk sizing + overlap guidelines for retrieval.
Common mistakes when using embeddings for search.
Why rerankers often improve relevance more than “better chunking”.
A practical comparison for developer workflows.
A simple heuristic for sampling parameters.
Practical token caps and truncation strategies.
A practical overview of injection risks.