Better prompting: practical recipes Write a clear request, compare the result and keep the version that works for your task. Reviewed 15 November 2026 · Utilising AI Pty Ltd https://www.utilisingai.com/learn/better-prompting These original examples work as starting points across chat tools. Agent actions, file access and structured-output settings depend on the product. A prompt cannot grant access to a file or enforce a security policy. Independent educational guide. Original examples; documentation-based guidance. Product availability varies. No provider integration or AI request is run by this download. Quick start =========== 1. Write the outcome in one sentence and identify the reader or user. 2. Add the source, one useful example and any real constraints. 3. Run a small example, compare the result with your checklist, then revise the weakest part. Practical tips ============== Use only the context that changes the answer Include the goal, relevant material, desired output and boundaries when they matter. A specific request is easier to assess than a long instruction to be brilliant. Leave out unrelated history that could distract from the current task. https://learn.chatgpt.com/docs/prompting Demonstrate the difficult part Use a short input/output example to show the format or judgment you need. Add a case with missing information if that happens in real work. Keep examples consistent; conflicting examples make it harder to know what a correct result should look like. https://aistudio.google.com/docs/prompting-strategies Define quality before asking for variations Choose criteria such as factual accuracy, required sections and a word limit. Compare outputs against those criteria. If the task fails repeatedly, check the missing data or the task design instead of endlessly adding stronger adjectives to the prompt. https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview Improve one thing at a time Ask for a targeted edit while preserving the parts already accepted. Our recommendation: keep a small set of representative inputs and record which prompt version worked better. That turns personal preference into a repeatable comparison. https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview Developer notes =============== Turn “works” into acceptance cases For a coding task, provide representative inputs, expected outputs and failure cases. A generated test should express the required behavior rather than merely repeat the implementation. Then run it in the actual project. https://docs.github.com/en/copilot/concepts/prompting-and-context/prompt-engineering Distinguish a response format from a guarantee “Return JSON” in a chat is an output request. For an API workflow needing a predictable structure, use a supported schema facility and validate the result. You still need to reject incorrect dates, quantities or business rules. https://aistudio.google.com/docs/structured-output Keep reusable rules short Put stable project commands and conventions in the instruction mechanism your tool supports. Give the individual task its own brief. If a rule protects production or secret data, use actual permission or review controls as well as wording. https://code.claude.com/docs/en/memory Original examples to adapt ========================== A compact reusable brief Outcome: [what I need]. Audience: [who will use it]. Source of truth: [attach or paste material]. Required output: [format, length, fields]. Constraints: [budget, time, facts to preserve]. Missing information: identify it; label assumptions. Check: [how we will judge the result]. Original Utilising AI template. Fill only the fields useful for your task. https://learn.chatgpt.com/docs/prompting Improve an existing draft Revise the draft below for [audience]. Improve [one issue]. Preserve the accepted facts, structure and call to action. Return the revised draft and a short list of substantive changes. Flag unsupported claims. Draft: [paste draft] Use permitted, non-sensitive source material. https://support.microsoft.com/en-us/word/copilot/write-effective-prompts Create a testable coding brief Feature: [behavior]. Existing pattern to follow: [file]. Examples: [input → expected output]. Edge cases: [empty, invalid and boundary input]. Constraints: [interfaces to preserve]. Deliverable: a minimal change, relevant tests, and observed check results. Original example; the coding agent needs actual project access to run checks. https://docs.github.com/en/copilot/concepts/prompting-and-context/prompt-engineering Check the result ================ - Is there one main outcome? - Does the prompt identify facts and unknowns separately? - Can you tell whether the result meets the stated criteria? Common mistakes =============== - Collecting magic phrases instead of testing the output. - Changing five instructions at once and not knowing which helped. - Asking an agent to deploy when you only intended to review a draft. Sources ======= OpenAI · Prompting · Official documentation https://learn.chatgpt.com/docs/prompting Google · Gemini prompt design · Official developer documentation https://aistudio.google.com/docs/prompting-strategies Anthropic · Prompt engineering overview · Official documentation https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview GitHub · Copilot prompt engineering · Official developer documentation https://docs.github.com/en/copilot/concepts/prompting-and-context/prompt-engineering Google · Structured outputs · Official developer documentation https://aistudio.google.com/docs/structured-output Anthropic · Claude Code best practices · Official documentation https://code.claude.com/docs/en/best-practices Microsoft · Effective prompts in Word · Official help https://support.microsoft.com/en-us/word/copilot/write-effective-prompts Anthropic · Project memory and instructions · Official documentation https://code.claude.com/docs/en/memory