Inbound emails, free-form text, and messy PDFs rarely arrive in the shape your systems need. ETL / Parser Agent reads them and produces exactly the JSON or Pydantic schema your pipeline expects — validated before it ever reaches a table.
The agent reads the raw input — an email body, a scanned PDF, a copy-pasted block of text — and extracts every field your schema requires, flagging what it could not confidently fill in rather than guessing.
Every extraction is checked against the schema's types, required fields, and constraints before it's accepted. A record that doesn't validate is routed for human review instead of silently corrupting downstream data.
The messiest part of any pipeline — turning real-world input into clean data — handled consistently.
Emails, PDFs, scanned documents, and free-form text — all parsed against the same target schema.
Every record is validated before it reaches your database — malformed data never slips through.
Ambiguous or missing fields are surfaced for review instead of being filled with a best guess.
Deploys as a Workflow Editor node — wire it after any inbound trigger: email, webhook, or upload.