Pack · HR & People

HR & People data, already modelled.

Regulated HR templates — employee master records, payroll, time off, and recruiting candidates.

Templates: 4
Gate on review: 3

The templates

Every template in this pack, printed as it ships.

Canonical column names, field counts, validator ids and risk level — read straight from the shipped template definition. Paste the header row from your own export and the deterministic layers will show you, column by column, which of these 4 it lands on.

Paste your header row

Or try:

Nothing is uploaded. The match runs in this tab against the shipped template vocabulary, using the same normaliser and fuzzy scorer the Worker runs on layers 2 and 3.

Risk

Employees

high

Employee master records with identity, contact, and bank details. Contains PII.

8 fields39 hintsemailregex

employee_id · legal_name · email · national_id · iban · +3

employees_v1View

Payroll

high

Payroll runs: gross salary, pay period, payout bank details. Contains sensitive PII.

6 fields28 hintsiban

employee_id · gross_salary · currency · pay_period · iban · +1

payroll_v1View

Time off

low

Leave and absence records: type, dates, and approval status.

6 fields28 hints

employee_id · type · start_date · end_date · days · +1

time_off_v1View

Candidates

medium

Recruiting pipeline: applicant contact, role, and stage.

7 fields34 hintsemailphone

candidate_id · full_name · email · phone · role · +2

candidates_v1View

4 templates
4 validators in this pack
104 header hints across 5 languages
27 canonical fields

Side by side

The whole pack as counted facts.

Same information the cards carry, in one scannable block — for the moment you are choosing between two templates that both look plausible. Every number is derived from the shipped definition at build time.

Template	Fields	Required	Validated	Hints	Risk	FHIR
Employees`employees_v1`	8	2	3	39	high	—
Payroll`payroll_v1`	6	3	1	28	high	—
Time off`time_off_v1`	6	3	0	28	low	—
Candidates`candidates_v1`	7	2	2	34	medium	—

27 canonical columns and 104 distinct header hints across the pack. "Validated" counts columns carrying at least one field-level validator; "hints" counts the distinct multilingual header names the deterministic layers resolve for free.

Validators

The checks that fire before you commit.

4 validators run on this pack. They are pure functions — the same code runs in the Worker, in the browser widget and in the MCP validate_row tool, so a dry run and a commit cannot disagree.

Validator	What it checks	Templates in this pack
`email`	RFC-style address shape.	employees_v1 · candidates_v1
`iban`	mod-97 checksum on the reordered value, with per-country length from the SWIFT IBAN Registry.	employees_v1 · payroll_v1
`phone`	libphonenumber-js in strict mode, with an optional country allowlist.	candidates_v1
`regex`	Pattern match against the template-supplied expression.	employees_v1

Empty values bypass a validator — required-ness is checked separately. LOINC / ICD-10 / ATC additionally try to resolve a free-text value to a canonical code before failing.

Review gating

3 of 4 come back flagged for review.

A template's risk level is the only input to the flag. Medium and high templates make PATCH /uploads/:id/mappings return requires_hitl so your own workflow can hold the commit — it is a flag, not a queue. Native AgentGate HITL integration is on the roadmap for Q3 2026 and is not wired in v1.

low1

Commits straight through. No review flag on the mappings response.

time_off_v1

medium1

Flagged `requires_hitl: true` with `hitl_status: "pending_review"` so you can gate your own commit workflow.

candidates_v1

high2

Flagged `requires_hitl: true` with `hitl_status: "pending_review"`. Regulated identifiers — card data, IBANs, payroll, KYC.

employees_v1 · payroll_v1

Try it

One call maps a file onto any of them.

Name the template and POST the file. The cascade resolves what it can on the deterministic layers — statistics, heuristic, fuzzy — and only the leftovers reach the metered LLM.

bash

curl -X POST https://api.adaptivmapr.com/v1/uploads \
  -H "Authorization: Bearer $ADAPTIVMAPR_API_KEY" \
  -F "template=employees_v1" \
  -F "file=@your_export.csv"

→ upload created · mappings ready · confirm before commit

Schema-only mode sends column headers plus at most three sample rows, each clamped to 80 characters — a data-minimization mode enforced at the HTTP edge. Full-data mode routes the metered layer-5 call in-region under a BAA and costs 20% more, and stays locked until the workspace accepts the BAA/NDA in Settings → Security & Data.

Read the quickstart

employees_v1Employees8 fields
payroll_v1Payroll6 fields
time_off_v1Time off6 fields
candidates_v1Candidates7 fields

Put the hr & people pack to work — without shipping raw records.

Schema-only mode leaves only headers and up to three clamped sample rows. Full-data adds row-level AI, routed in-region under a BAA.

Get an API key See pricing