Use casesRegulated work

Insurance claims intake

Typed extraction into structs beats prompt-and-parse, and JSONL tracing gives you a per-claim audit trail with token and cost attribution.

The problem

Claims arrive as free text, photos, and PDFs. Someone has to turn that into structured fields - policy number, loss date, peril, reserve estimate - before downstream systems can act. The usual approach is an LLM call followed by regex or a second model pass to coerce JSON, which fails quietly when a field is missing or the wrong type.

Regulators and internal audit want more than a log line that says "model returned OK". They want a replayable record: which model, which prompt, which tokens, what it cost, and what struct came out - tied to a claim id.

Why Ecko

Typed extraction
Declare the output as a struct. The runtime validates the model's answer against it before your code runs, so a missing reserve field is a catchable error, not a null pointer three systems later.
JSONL tracing
Set ECKO_TRACE and every ai call appends one JSON object per line: provider, model, tokens, latency, retries, and cost. Pipe the file into your SIEM or attach it to the claim record.
Per-claim attribution
Built-in tokens() and cost() read the last call's usage, so a batch run can write spend next to each extracted claim without a separate metering service.

In practice

extract.ecko
type Claim = {
  policy_id: str,
  loss_date: str,
  peril: str,
  reserve_usd: decimal,
}

fn intake(raw: str) -> Claim {
  ai "Extract a first-notice-of-loss from this text" from raw
}

# ECKO_TRACE=claims.jsonl ecko intake.ecko
# one JSON line per ai call, claim id in your own log

Further reading

Related cases

All 32 use cases →

Try it on your workload.

Install Ecko Open the playground