Crossary — AI Source-to-Target Data Mapping
Who it's for<br>If you hand-build the mapping sheet someone else implements — this is for you.
01Integration & interface engineers<br>Mapping heterogeneous specs — PDF, XML, EDI-style guides, Excel — to a target schema.
02Implementation & onboarding consultants<br>Turning a client's messy spec into a reviewed workbook on day one — not week three.
03Data & migration engineers<br>Building the field inventory and design before any records move.
04EDI & interface analysts<br>Turning implementation-guide PDFs into evidence-backed rows where the “why” has to be defensible later.
How it works<br>A strict five-stage pipeline.<br>Then a round-trip.<br>Upload to signed workbook in five steps — and back again, without losing a note.
01<br>Artifacts<br>Drop in your source + target specs. If a file can't be fully read, it tells you exactly how much it dropped.<br>xlsx · pdf · csv · json · xml · xsd · sql · yaml
02<br>Fields<br>A field inventory is extracted from both sides — every path, every column — so you map against the real surface.
03<br>Mapping<br>For each target: a proposed source, type, verbatim evidence, reasoning, and confidence. Abstains when unsure.
04<br>Validation<br>A deterministic check for structural & cardinality blockers. Zero AI, zero spend.
05<br>Export<br>A signed .xlsx your team can open anywhere — that reconciles cleanly when it comes back.
Anatomy of a reviewed row<br>Six things every row tells you.<br>Nothing taken on faith.<br>Open any proposed mapping and you see exactly why the AI suggested it — and how sure it says it is. The evidence, not the confidence, is the product.
target field ①<br>order_date *
confidence ④<br>high
source field ②<br>S_SHIP_DATE
mapping type ③<br>transformation
to_date(S_SHIP_DATE)<br>evidence — verbatim from the source ⑤<br>— ship date, ISO-8601 string. Target is a date type.
See it actually happen<br>The honest gap it won't guess —<br>and the round-trip that holds.<br>The real sample, end to end: where the AI withdraws a tempting guess and asks instead, and where your edits survive a trip through Excel and back.
the sample<br>hubspot → salesforce<br>ArtifactsFieldsMappingValidationExport
target fieldlow confidenceno confidence<br>Region<br>←Countryno clear source
No HubSpot field tracks sales territory, and it must not be guessed from Country.<br>?Region (sales territory) isn't in the HubSpot export. Assign it in Salesforce, or point me at a source?
When it isn't sure, it says so.<br>confidence: none · no guess
Mapping memory<br>Every mapping you approve makes the next one faster.<br>Sign off an export and your approved field-pairs become a private, workspace-scoped library. On the next run it gap-fills only the targets the AI abstained on — inserted as suggestions you still review, never auto-applied.<br>Scoped to your workspace — it never crosses to another.<br>Captures the decision only — no evidence, values, or client data.<br>It never trains a shared model.
next run · a gap, pre-filled<br>Industry<br>library
Trust & data<br>Trust isn't asked for here — it's enforced in code, and written down.
Guaranteed in code<br>Honest about what it read<br>If more than ~10% of a source is dropped during ingestion, it stays flagged — in the app and on the export cover sheet. A partial read is never reported as complete.
“Validated” means one thing<br>Validation is deterministic and checks structure and cardinality only. It does not claim semantic correctness — and the UI says exactly that.
Never loses your note<br>On re-import it applies what matched, skips what changed underneath you, and turns every reviewer note into a tracked question. Nothing is silently overwritten.
Schema-validated, or rejected<br>Every AI response is checked against a strict schema before it can touch your data. A malformed result is thrown away, never persisted.
Your data<br>Specs in, not your records<br>Crossary maps from your source and target specs — schemas, dictionaries, guides. It's built to work from the spec, not your data, so in most cases there's no need to upload production records or PII.
Pricing
Start free. Pay for AI runs, never for reviewing.<br>Reviewing, validating, exporting, and round-trip re-import don't call the AI — so they're always free, on every plan.
MonthlyAnnual2 months free
Free<br>$0<br>For your first real integration.<br>Start free3 integration credits<br>Free review, validate & export<br>Round-trip re-import<br>Mapping Memory included<br>1 workspace · up to 2 members
Most teams start herePro<br>$99/ month<br>~20 integrations a month.<br>Start with ProEverything in Free<br>~20 integration credits / mo<br>Higher-accuracy pass<br>Unused credits roll over<br>3 workspaces · up to 3 members
Team<br>$399/ month<br>~75 integrations a month.<br>Start with TeamEverything in Pro<br>~75 integration credits / mo<br>Unlimited workspaces · up to 10 members<br>Shared mapping library
Plus applicable taxes.<br>Run out? Existing work is never blocked — review, validate, export & re-import stay free. Unused credits roll over, you can buy more anytime, or upgrade. Only new AI runs pause.
Questions, answered straight<br>The...