Use cases
The file you were just sent. The schema you actually need.
A vertical tells you who we build for. These tell you what the run looks like — the messy headers it starts from, the template it lands on, which layers resolve it without a model call, and what needs a human before you commit.
- Raw records stay put in schema-only mode
- Most columns resolve with no model call
- Medium and high risk come back flagged
- PHI routes in-region under a BAA
- Hints in DE / FR / IT / EN / ES
Healthcare
Healthcare imports
EHR patient migration
A German-labelled demographics export lands on patient_demographics_v1, gets birth dates and identifiers validated per row, and emits a FHIR R4 Patient bundle — with the rows themselves never leaving your side in schema-only mode.
→ patient_demographics_v1 · risk: medium
See the run →Lab result onboarding
Every laboratory ships a different CSV. Map it once to lab_results_v1, have the LOINC codes checked before anything commits, and emit FHIR Observation — then reuse the mapping on every file that lab sends after.
→ lab_results_v1 · risk: medium
See the run →Claims ingestion
Billing files arrive per clearinghouse, per payer, per month. Map them to claims_line_items_v1, have every CPT and ICD-10 code checked before the batch is written, and emit FHIR Claim.item.
→ claims_line_items_v1 · risk: medium
See the run →Finance & payments
Finance & payments imports
Bank account import
A supplier or counterparty account list is a payment incident waiting to happen. Map it to bank_accounts_v1, have every IBAN checked mod-97 and every BIC checked by format, and get the review flag on every run.
→ bank_accounts_v1 · risk: high
See the run →Payment file import
Processors export settlements in their own shape. Map them to payments_v1 — brand, last four digits, amount, currency, status, processor reference — with the template built so a full card number has nowhere to land.
→ payments_v1 · risk: high
See the run →KYC profile import
Onboarding a KYC vendor, or migrating off one, means importing identity profiles with risk ratings attached. Map them to kyc_profiles_v1 — a high-risk template that comes back flagged for review every single time.
→ kyc_profiles_v1 · risk: high
See the run →HR & people
HR & people imports
Payroll file import
Payroll files carry salary and bank details in one row — the highest-sensitivity data most companies move. Map them to payroll_v1, have every IBAN checked by its own checksum, and get the review flag back on every run.
→ payroll_v1 · risk: high
See the run →HRIS employee onboarding
An HRIS migration is one file with identity, contact, national ID and bank details per person. Map it to employees_v1, validate the identifiers, and get a review flag on every run because the template is high-risk by design.
→ employees_v1 · risk: high
See the run →Not listed
The engine maps to any schema you give it.
These pages document the jobs our pre-built templates cover. The catalogue is a starting point, not a gate — POST /v1/schemas declares your own target shape and the same cascade maps to it, with your own validators and your own required fields.
Ready when you are
You already know the file. Map it once.
Start with a $10 prepaid wallet. Every map draws a few tokens — including a fully deterministic one that never reaches a model.