Building with extended thinking - Claude Docs

Example: Passing thinking blocks with tool results Tool use without interleaved thinking Tool use with interleaved thinking System prompt caching (preserved when thinking changes) Messages caching (invalidated when thinking changes) Example: Working with redacted thinking blocks

Loading... Loading... Loading... Loading... Loading... Loading... Loading... Loading... Loading... Loading... Loading... Loading...

related reading

• Notionnanransohoff.com
• GitHub - brexhq/prompt-engineering: Tips and tricks for working with Large Language Models like OpenAI's GPT-4. · GitHubgithub.com
• GitHub - affaan-m/ECC: The agent harness performance optimization system. Skills, instincts, memory, security, and research-first development for Claude Code, Codex, Opencode, Cursor and beyond. · GitHubgithub.com
• Parsed | Custom, interpretable AI systems that continuously learnparsed.com
• GitHub - ByteByteGoHq/system-design-101: Explain complex systems using visuals and simple terms. Help you prepare for system design interviews. · GitHubgithub.com
• Use Cases | Claudeclaude.com
• GitHub - socketteer/loom: Multiversal tree writing interface for human-AI collaboration · GitHubgithub.com
• Prompt guidance | OpenAI APIdevelopers.openai.com
• GitHub - x1xhlol/system-prompts-and-models-of-ai-tools: FULL Augment Code, Claude Code, Cluely, CodeBuddy, Comet, Cursor, Devin AI, Junie, Kiro, Leap.new, Lovable, Manus, NotionAI, Orchids.app, Perplexity, Poke, Qoder, Replit, Same.dev, Tragithub.com
• OpenAI | Research & Deploymentopenai.com
• Mindbookmindbook.dev
• ChatGPTchatgpt.com