Prompt template: A prompt template is a reusable, pre-written prompt with placeholders for the parts that change, such as [CLIENT NAME] or [PASTE THE EMAIL], so you can get consistent results from an AI model without rewriting instructions every time.
Most people write prompts from scratch each time and get results that swing from great to useless. A template fixes the parts that should never change (the role, the task, the format, the rules) and leaves blanks for the parts that do. Fill in the blanks, paste, and you get the same quality on Tuesday that you got on Monday.
A good template names the role the AI should play, states the task, provides the context it needs, specifies the output format, and lists constraints. Placeholders in ALL CAPS inside square brackets are easy to spot and hard to forget. Many people keep templates in a notes app or a shared document. ChatGPT's custom GPTs, Claude's Projects, and Gemini's Gems let you bake a template into a reusable assistant so the blanks are all a colleague has to fill.
Templates drift. The version that worked in January may produce worse results after a model update, and the placeholders may stop matching how your team actually works. Assign an owner, date each template, and retire the ones nobody uses.
Example at work
A recruiting team keeps one template for screening-call summaries: 'You are a recruiting coordinator. Summarize the following call notes for [ROLE] in five bullets covering experience, salary expectations, availability, red flags, and next step. Notes: [PASTE CALL NOTES]. If the notes do not mention salary, say so instead of guessing.' Every recruiter's summary now lands in the tracker in the same shape.
Why it matters
Templates are how one person's prompting skill becomes a team capability. They save the ten minutes of rewriting, remove the guesswork for less experienced colleagues, and make results consistent enough to build a process around.
Related terms
- PromptA prompt is the text (and sometimes files or images) you give an AI model to tell it what you want. A good prompt states the role the AI should play, the task, the relevant context, the output format, and any constraints.
- Prompt engineeringPrompt engineering is the practice of writing and refining instructions to get reliable, high-quality output from an AI model. It covers giving context, showing examples, specifying format, and iterating on what did not work.
- System promptA system prompt is a set of instructions given to an AI model before a conversation starts that defines its role, tone, rules, and boundaries. Vendors write one for their products; you can add your own in custom instructions, projects, and custom assistants.
- Custom GPTA custom GPT is a tailored version of ChatGPT that you configure with your own instructions, uploaded reference files, and optional connections to outside services, then reuse or share without rewriting the setup each time.
- Few-shot promptingFew-shot prompting is including a handful of examples of the input and output you want inside your prompt so the AI model can copy the pattern. It is the fastest way to get consistent formatting, tone, and judgment calls.