The vocabulary
The words this category needs, defined by the people creating it.
A category is owned by whoever publishes its yardstick and its vocabulary. These definitions are offered openly, including to our competitors, because a shared vocabulary is worth more to us than a private one.
The category
- Agreement layer
- The layer above an enterprise's systems of record where those systems are compared to one another. Distinct from integration, which moves data between systems, and from a warehouse, which stores it. The agreement layer asks a different question: when these systems describe the same object, do they say the same thing, and if not, which one counts.
- System of record
- An authoritative source for a class of fact. Each one is internally correct. The problem this category addresses is that being internally correct does not make a set of them collectively consistent.
- Disagreement
- Two or more sources reporting different values for the same canonical object. Not an error, and not a data-quality defect. A disagreement is a fact about the estate that must be preserved rather than resolved away.
- Contested tie
- Two sources reporting different values for the same object at the same timestamp, so recency cannot arbitrate. The system must surface the conflict rather than select a winner. This is the single most important behavior in the category: a recoverable error is survivable, a confident wrong number is not.
- Canonical object
- The single representation of a real-world thing across every system that describes it, holding each source's latest reported value rather than a merged average or a last-writer-wins overwrite.
Evidence
- Evidence pack
- The complete trace behind a material figure: claim, source, timestamp, transformation, rule version, calculation, and the record reference. Its defining property is that it reconstructs later, by someone who was not there.
- Provenance
- The recorded origin and derivation path of a value. Provenance answers where a number came from. Evidence answers whether you should believe it.
- Decision ledger
- An append-only record of decisions, each carrying the authority that made it, the request and the evidence it decided, and the timestamp. A ledger that records only outcomes cannot explain a decision months later; keeping the options that were not chosen is specified, not built yet.
- Receipt root
- A content hash over a shipped tree, re-derivable with no vendor credentials. A release with a receipt root can be checked. One without can only be believed.
- Outcome record
- What was expected at the point of decision, what was measured afterward, and the gap between them, retained rather than absorbed. Without it a system can be confidently wrong indefinitely.
Super Intelligence (SI)
- Super Intelligence (SI)
- Super Intelligence, SI, is the intelligence layer above every system of record: it reads them all, preserves where they disagree, reasons only over evidenced, reconciled state, labels every claim by what it rests on, and acts only on a named person's approval. The name is positional, from super, above: the layer above the systems, governed. It is not a claim that a model outthinks people. EOS Intelligence is Super Intelligence for the enterprise, native to EOS.
- Claim adjudication
- Ranking competing answers to the same question by the strength of what supports them rather than by the confidence of whichever system produced them.
- Claim ranking order
- Source evidence, then deterministic calculation, then verified derivation, then model consensus, then single model output. Model agreement ranks below arithmetic. Two models agreeing is a fact about the models, not about the world.
- Truth categories
- Observed, derived, inferred, assumed, scenario, recommendation, decision, action, outcome. Every material output carries exactly one. Representing one category as another is the defining failure mode of enterprise AI.
- Refusal
- A recorded declination to answer, with its reason. A system that has never refused anything has never been tested. Refusals belong in the record alongside answers.
Status labels
Every product, capability, connector and figure carries exactly one primary status from this list, shown on its face. A figure that is not observed says so where it appears.
- LIVE
- In service for real users today.
- VERIFIED
- Passed its stated, reproducible test; the test and its result are published with it.
- CONFORMED
- Passed the conformance suite for its published contract. Not by itself a claim about any one vendor installation.
- DEMO
- Working software running on sample or synthetic data, labeled as such.
- SCAFFOLD
- Built and running, and not yet through its promotion tests.
- DESIGN
- Specified and scheduled; not yet built.
- PLANNED
- On the roadmap; not yet specified in full.
- MODELED
- Calculated from stated assumptions; an estimate, not an observed result.
- SIMULATED
- Produced by a simulation or a synthetic scenario; not an observed result.
- NOT CLAIMED
- Deliberately not asserted. Published as prominently as everything else.
A status may carry one qualifier where it carries meaning: sample data, synthetic tenant, live tenant, self-verified, independently verified, preview, proof of concept, interest list. The list is published at /data/statuses.json.
License
These definitions are published openly. Adopt them, adapt them, argue with them, and hold us to them. If a competitor uses this vocabulary the category gets clearer, which is worth more to us than the vocabulary being ours alone. See The Verify Standard for the same offer applied to verification itself.