Prompt chaining breaks a complex task into a sequence of smaller prompts, where each output feeds the next.

Example: Writing a Blog Post

1. Prompt 1: "Generate 10 blog post titles about X"
2. Prompt 2: "Create an outline for title #3"
3. Prompt 3: "Write section 1 of this outline"
4. Prompt 4: "Write section 2..." (and so on)
5. Final prompt: "Edit the full draft for flow and consistency"

Why It Works

Smaller, focused prompts outperform one giant prompt on complex tasks every time.

Reference:

Prompt chaining guide

https://docs.anthropic.com/en/docs/build-with-claude/prompt-engineering/chain-prompts