HTTP / REST API

Answer a question about any public document: fetch it over HTTP, hand the text plus the question to an LLM with a grounding prompt, and post the answer to a callback URL.

Receive a PDF (base64) by webhook, parse it, extract structured fields with a JSON schema, reshape them and POST the record to your API.

Download a CSV export every night, parse it, normalise the columns with the Process engine and upsert into a table.

Receive a list of items by webhook and call an API once per item, five in parallel, continuing past individual failures.

Extract structured data from text; when the model is unsure it pauses and asks a person to pick from candidates, then the record is posted.

A claim notification arrives by webhook; AI extracts the loss details, the payload is validated, an adjuster triages it and the claim is opened in Iris.

Ping an endpoint every 5 minutes; if it does not return 200, email the on-call address with the status code.

Poll the sales mailbox, classify each email as lead / existing customer / vendor, create Iris records for new leads and forward the rest to the right team.

Acts on Workflow Health findings Auto Fix cannot answer: plans, branches, fixes, validates, commits and opens a pull request for a code defect through the host runner; files the rest for a person; reports back to the health check. Tag the installed workflow system:health and point Settings → Workflow Health at it.

Call a flaky endpoint with backoff retries; on final failure wait, try a fallback endpoint, and if that also fails email an operator.

Every weekday morning pull a JSON summary from your API, have an LLM turn it into three bullet points and email the team.

Receive any JSON, normalise a few fields, reshape it and forward to another endpoint — the smallest useful glue workflow.