Prepare training files, JSONL datasets, prompt templates, and AI data exports before they reach an API.
Use these tools when AI data, prompt templates, or structured outputs need a quick sanity check before an API call or upload.
These pages target distinct jobs, so each result leads to a different working checker, converter, preview, or calculator.
Direct links for this workflow.
Paste a JSONL training file, find broken lines and message-role mistakes, then export the valid records.
Turn spreadsheet rows into one JSON object per line with a local CSV parser and copy-ready export.
Check a JSON Schema for common structured-output constraints before wiring it into an LLM request.
Estimate prompt tokens and request cost from pasted text plus editable per-million token rates.
Model repeated prompt-cache scenarios and compare cached versus uncached request cost.
Turn labeled prompt notes into escaped XML sections that are easier to paste into Claude workflows.
Find missing, unused, and repeated template variables across prompt text and a sample JSON payload.
Remove emails, bearer tokens, API keys, JWTs, and cookies from prompts or logs before sharing them.
Scan NDJSON records for field drift, missing keys, invalid lines, and mixed value types.