Agent Instruction Prompt Formatter
Formats fuzzy agent instructions into a structured prompt with objective, available tools, constraints, success criteria, and failure handling.
Gives a vague or too-broad research request a defined scope, source criteria, comparison framework, and output format.
Vague research prompts produce vague research results. 'Tell me about X' gets you a summary. 'Compare X and Y on these criteria for this audience and output a table' gets you something you can use. This formatter adds the scope, criteria, and output structure your research prompt is missing — without changing what you're actually trying to find out.
Write what you want to find out
Include the topic, what you're trying to decide, and any constraints you already know about.
Open in Prompt Formatter
The formatter adds research question, scope, and output format sections based on your input.
Add source criteria if relevant
If your research requires specific source types (primary sources, no marketing pages, specific date range), add those to the source criteria section.
Run the structured research prompt
A structured research prompt produces results that map to your actual decision criteria instead of a generic overview of the topic.
It restructures without redirecting. The rules forbid narrowing the scope beyond the original request or adding criteria that weren't present or implied — it only supplies the Scope, Source Criteria, and Output Format sections your ask was missing. It reshapes the pasted request into structure; you still run the formatted research prompt in your own assistant afterward.
It gets omitted. The rules say to drop the Comparison Framework when the original isn't a comparison, and to skip Source Criteria if none were specified — the formatter won't manufacture criteria to fill an empty section. So a straight research ask comes back with Research Question, Scope, Audience, and Output Format rather than a padded seven-section shell.
Formats fuzzy agent instructions into a structured prompt with objective, available tools, constraints, success criteria, and failure handling.
Converts a stream-of-consciousness prompt into a structured one with Task, Context, Constraints, Requirements, and Output Format sections.
Turns scattered technical instructions into a coding prompt with a clear task, code context, constraints, and expected output.
Convert scattered bug notes, Slack messages, or user complaints into structured engineering tasks with reproduction steps, severity, and root cause hypothesis.
A reusable AI agent task template with variables for objective, context, available tools, constraints, success criteria, failure handling, and output format.
A set of before-and-after examples showing exactly what prompt cleanup removes — and what it deliberately leaves alone.
Turn a messy, stream-of-consciousness prompt into a clean, structured one.