Technical overview

MTN FieldMap: a map of what your data means, maintained outside your data path, honest about what it does not know.

Schedule a Technical Session

Where Guide sits

Above the data path, not inside it. Your records never route through MTN.

Your sourcesEHRs, claims, devicesschemas, docs,anonymized payloadsMTN Guidethe map: concepts, evidenceroutes and mappings,not resultsYour stackwarehouse, BI, modelsyour data, never through MTN

What Guide reads

Guide builds MTN FieldMap from descriptions of your systems rather than from their contents. Schema-level evidence is enough to begin, which is what lets an engagement start before a data agreement is in place.

Structural

DDL, JSON Schema, OpenAPI specs, data dictionaries, and warehouse catalogs

Prose

Documentation, integration guides, and vendor references

Examples

Synthetic or anonymized payloads, where values clarify meaning

Human answers

Answers to specific questions, recorded as evidence in their own right

Each modality keeps an evidence shape faithful to the artifact it came from.

MTN FieldMap

Concepts and the relationships between them, assembled from assertions. Every one records what it rests on.

hasattended byoccurs atbillsends withPatient3 sources agreeProviderderivedEncountercorroborated ×4Claim linederivedFacility2 sources?Dispositionthin evidencemodelrulepersonunresolvedcontour spacing = weight of evidence

Layers and change containment

Each source is a layer, and layers compose recursively.

CANONICALCanonical modela composite layer like any otherCOMPOSITECLINICALpatient_id ↔ pat_idencounter ↔ visitBILLINGclaim ↔ encounterSOURCESEpicathenaClaims!A schema change in Epic re-evaluates onecorrespondence. Everything else stands.

Uncertainty and human review

An answer is only as good as the weakest assertion underneath it.

The answer“What was production across all five practices?”
  • patient_id maps across all five systems
    0.98
  • production = sum(billed_amount)
    certain
  • “adjustment” as defined in Practice C
    0.41
  • location_id mapped from site_code, Practice E
    0.62

The answer inherits 0.41, the weakest assertion it rests on, not the average of the four.

That one assertion becomes the review queue: what does “adjustment” mean in Practice C? Answer it, and the whole conclusion moves.

person rule modelDeterministic derivations are certain by construction, and say so.

Calibrated confidence and guided review

Trust levels are validated against outcomes rather than asserted by the model that produced them, and guided elicitation ranks which questions are worth a person’s attention. Where the evidence does not support a score, the engine declines to invent one.

Security and regulatory posture

The strongest control is architectural: the sensitive data mostly isn’t there.

Schema-first by default

Schemas, documentation, and synthetic examples are enough to begin, with no PHI and no production access. That materially shortens security review, and it is a design property rather than a configuration option.

When deeper access is warranted

Some work needs more than schemas: value-level disambiguation, or drift detection against live data. That is a separate, explicit step taken under a BAA, scoped to the specific need, and never a precondition for getting started.

Audit and traceability

Traceability is how the map is built, not a logging layer added around it.

Model independence

Guide is not tied to one model vendor. Providers are configured per deployment, so model choice follows your procurement and data agreements rather than dictating them.

Integration surface

If you are an engineer or SI technical lead, here is what you get to build against.

Your agentYour appor a personMCP toolsHTTPOne internal APIidentical semanticsStructured answerconsume directlyoptionalProse narrationoptional

Map export

The evidence and attribution behind every assertion

Mappings and specs

Yours to implement in your own pipeline

Sandbox

Pre-engagement schema introspection

Ready to discuss architecture?

We'll walk through how this fits your stack, what a bounded evaluation looks like, and where the boundaries of the system actually are.

Schedule a Technical Session