Prompt Chaining
Connecting a series of prompts where the output of each step becomes the input for the next — breaking a complex task into a pipeline rather than trying to do everything in one prompt. For example: Step 1: extract key claims from an article → Step 2: fact-check each claim → Step 3: write a balanced summary. Chaining gives you more control than asking Claude to do it all at once, and makes it easier to spot where something went wrong.
In practice
You need Claude to analyze a document, then write a summary, then translate that summary into Spanish. Instead of trying to do all three in one prompt (which gets messy), you chain them: output of step 1 becomes input to step 2, output of step 2 becomes input to step 3. Each step is cleaner and more reliable than cramming everything into one shot.
Related concepts