Anthropic's prompt engineering docs: when to prompt-engineer and where to start
CodeByPoonam · x · 2026-09-10
Anthropic's Claude Platform docs lay out a complete prompt engineering guide: before starting, define success criteria, set up ways to test empirically, and draft an initial prompt. Not every failing eval is best solved by prompting—sometimes switching models improves latency and cost more easily.
All techniques (clarity, examples, XML structuring, role prompting, thinking, prompt chaining) live in the Prompting best practices reference, with an example-filled interactive GitHub tutorial and a lighter Google Sheets version.
More from coding & agent
- Alibaba open-sources Open Code Review: hybrid deterministic + LLM agent code reviewer — bibryam · 2026-09-10
- Terminal-native agent interaction: ANSI-staged commands at your shell prompt — remilouf · 2026-09-10
- Open-source Tab Zero turns browser tab history into searchable memory for agents — victorialslocum · 2026-09-10
- Benchmarking AI assistants: measure time to a checked result, not time to an answer — OriginalHospital · 2026-09-10
- Agent plans need explicit dependencies, not just numbered lists, argues new design pattern — OriginalHospital · 2026-09-10
- V4.1's agent-team decisions look reasonable on single-file projects, but subagents remain half-baked — teortaxesTex · 2026-09-10