Agent Instruction Prompt Formatter
Formats fuzzy agent instructions into a structured prompt with objective, available tools, constraints, success criteria, and failure handling.
Formats scattered bug observations — logs, guesses, reproduction steps, expected vs actual — into a structured debugging prompt.
Bug notes are written in the moment: partial observations, half-confirmed guesses, log snippets, and environment details all jumbled together. This formatter doesn't investigate the bug — it organises your notes into a structured debugging prompt so an AI assistant can reason from evidence instead of filling in gaps with plausible guesses.
Collect what you have
Paste your bug notes as-is: logs, observations, guesses, and reproduction steps in whatever order you have them.
Open in Prompt Formatter
The formatter classifies each note by type — task, constraint, or output expectation — and groups them into a structured debugging prompt.
Check the constraints section
Suspected causes and guesses tend to land in the Constraints section. Review them — if something is confirmed, make that explicit in your notes before reformatting.
Use with your debugging assistant
Paste the structured prompt with any relevant code. Structured bug reports produce more specific root cause analysis.
Anything that reads as a suspected cause lands in the Hypotheses section, tagged as unconfirmed, and the formatter is told not to confirm or deny it. So if your notes say 'probably a race condition,' that line moves under Hypotheses labeled unconfirmed rather than being promoted into Symptom or Actual Behavior as an established fact.
It won't. A rule instructs the formatter to preserve technical details exactly and not paraphrase log lines or error messages, so stack traces and log output land verbatim under the Error Messages or Logs section. That keeps the specific token or line number that often pinpoints the root cause intact instead of being smoothed into prose.
Empty sections get dropped. A rule tells the formatter to omit any section with no content in the notes, so if you never wrote down the OS or version, the Environment heading won't appear as a blank placeholder. It also won't invent reproduction steps that weren't in your notes, so gaps stay visible rather than fabricated.
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.