A published set of standards from the LangWatch team for building agents well, covering prompt structure, evaluation habits and failure handling.
Source: Official GitHub repository. Last checked 2026-09-18. Spot an error? Tell us.
Nearby and similar
A written set of principles for building reliable LLM software, including factors on owning your prompts, owning context construction and treating tools as structured output.
A provider-neutral guide and agent skill describing prompt and harness design practices that work across Codex, Claude Code and similar coding agents.
A long-running engineer's notebook on AI developments, including sections on prompt engineering tooling and techniques, kept as an open reference.
A set of prompt templates and agent configurations for user-centred product development, walking from research and requirements through to specifications.
Anthropic's official notebook collection showing working patterns for Claude, including prompt structures for classification, extraction, tool use, retrieval and long-context work.
Anthropic's educational course repository covering API fundamentals, prompt engineering, evaluations and tool use. The repository is archived, with newer material published on Anthropic Academy.