Prompt Patterns & Techniques
Move past one-off prompts and learn the named patterns pros reach for — worked examples, chain-of-thought reasoning, strict output shapes, and delimiter guardrails.
Delimiters and guardrails
Keep instructions and data apart When you paste a user’s text into a prompt, the model sees one continuous stream — it cannot automatically tell your instructions from their data. Delimiters draw that line for you. What a delimiter looks like A delimiter is any clear marker that fences off the pasted content. Common choices […]
Making the model check its own work
A second pass catches what the first one missed Models are markedly better at spotting a flaw than at avoiding it while generating. That asymmetry is useful: ask for the answer, then ask for a critique of the answer, then ask for a revision. Each pass is a fresh, narrow job. The three-pass shape Pass […]