Regimenta
Language: en
prompt-builderruns locally in your browser
Start from a template

Who should the AI act as? Optional, but it sets vocabulary and depth.

Tone
No preference
Neutral and factual
Friendly and warm
Formal and professional
Direct and concise
Persuasive
Output format
No preference
Short paragraphs
Bullet points
Numbered steps
Table
Email with subject line
JSON
Length
No preference
Short (under 100 words)
Medium (about 150–300 words)
Detailed (as long as needed)
Extra instructions

Your prompt

You are a careful analyst who writes clear briefings.

## Task
Summarise the document below for a busy decision-maker. Highlight decisions, deadlines, risks and open questions.

## Tone
Neutral and factual.

## Output format
Bullet points, one idea per bullet.

## Length
About 150–300 words.

## Rules
- Only use information from the document
- Mark anything unclear as an open question
- Quote figures exactly as written
- If you are not sure about something, say so clearly instead of guessing.

If important information is missing, ask me up to three short clarifying questions before you start.

599 characters, about 150 tokens

Runs entirely in your browser. No data is sent to a server.

How it works

  1. Choose a template such as summarising a document or drafting an email, or start blank.
  2. Describe the task in one or two sentences, starting with a verb. Add a role if expertise or perspective matters.
  3. Paste the context or source material the AI should work with, and describe the audience.
  4. Pick tone, output format and length, and list any rules the answer must follow.
  5. Copy the finished prompt into your AI assistant. If the answer misses the mark, adjust the field that caused it and try again.

FAQ

Which AI assistants does the generated prompt work with?

Any chat-based assistant or LLM API that accepts text instructions. The structure of role, task, context, format and rules is not tied to one vendor.

Is what I type stored or sent anywhere?

No. The prompt is assembled in your browser and never leaves your device unless you copy it somewhere yourself. Still avoid pasting confidential data into AI tools your company has not approved.

Why does the prompt put the context between triple quotes?

Delimiters make it clear where your source material starts and ends, so the model is less likely to confuse it with instructions.

Should I always add a role?

No. A role helps when expertise, vocabulary or perspective matters. For simple tasks a clear task description and output format matter much more.

Related articles

  1. Few-Shot Prompting: When and How to Use ExamplesPrompting7 min
  2. How to Write a System Prompt (With Examples)Prompting7 min
  3. Prompt Engineering for Business: A Practical GuidePrompting8 min
  4. Prompt Templates for Everyday Business TasksPrompting7 min

More tools

  1. LLM API Cost Calculator

    Enter your token volumes and your provider's prices to see what a chatbot, assistant or automation will cost before you build it.

  2. AI Automation ROI Calculator

    Find out whether automating a recurring task with AI pays off, with review time and running costs included rather than ignored.

  3. EU AI Act Risk Checker

    Get a first orientation on where an AI use case sits under the EU AI Act: prohibited, high-risk, transparency duties or minimal risk.