Techniques that change the result
- 01Chaining prompts7 min
Breaking a complex task into a chain of short prompts, where the output of one becomes the input of the next, makes each link verifiable on its own instead of judging a single opaque block.
- 02Giving Claude hands7 min
Tool use lets Claude request the execution of a function you have defined, but the model never executes anything itself: it is your application, or for some tools provided by Anthropic its own servers, that actually carries out the operation, and the clarity of the tool's description determines how accurate the arguments it sends are.
- 03Composing a system prompt from several sources8 min
Merging the best rules from several system prompts works like an ordinary piece of writing, provided each imported rule is rewritten for its own context rather than copied as is, and the rules already in force settle any conflict.
- 04Citing sources and not beating about the bush6 min
A useful citation fits in an inline bracket right after the sentence it proves, one source per bracket, with no separate section at the end of the message, and a direct answer states the fact instead of announcing it and then closing with a polite question.
- 05Structured outputs and guardrails6 min
Forcing an exact schema on an output and checking that output before using it are two halves of the same reflex, one forces the form upstream, the other controls it downstream, and both matter more when the action that follows cannot be undone.
- 06Checking a prompt the way you check a result6 min
An eval is a fixed set of tests that scores a prompt, and meta-prompting uses Claude to improve an existing prompt, but in both cases the result stays a draft to test, never a final answer.
- 07Asking several times, and contradicting yourself6 min
Asking for several independent answers and keeping the majority filters out the noise of a single answer, and asking Claude to play devil's advocate against its own answer finds errors a single pass misses, provided you always run a final synthesis to sort the valid objections from the noise.