You can check the worked example below in two minutes. Everything else on this page is either checkable by you, or labeled as something we can’t check either.
Generic advice on a greenlight sounds like this: Format B is the strongest concept. The team will support it. Budget risk is manageable.
Same decision. Ranked paths, with the person who can block each one:
The ranking is an internal order, not a probability. We do not publish how often rankings like this have been right.
AI-generated simulation by Timepoint AI. The scenario, actors and outcomes are invented to demonstrate the method — not reporting, not a transcript, not a prediction service.
Every company in this category leads with one.
The ceiling for this kind of work is how closely a person matches their own answer when asked the same question twice. People don’t match themselves. A percentage without that denominator, its question set, and its holdout protocol is unbounded — it can mean almost anything.
We have no published calibration record. Until we do, we won’t imply one exists.
The record format is published. Timepoint Telemetry — tt-ontology/1.0
v2.1.0 — with committed inputs, canonical bytes and hashes, and tests run in CI on every push.
Rerun the vectors and check the hashes byte for byte.
→ github.com/timepointai/timepoint-telemetry
· source-available under BSL 1.1
Governance runs on a schedule, in public. Change classes, release windows at NYSE close, retirement only by deprecation, published compatibility criteria. Each version converts to Apache-2.0 four years after its own publication, so you can read your permissive date off a calendar.
Every simulated output is labeled. Fictional examples say so in the first line, not a footnote. No simulated result is presented as a real outcome, real traction, or a case study.
Ranked branches with the uncertainty written out in words. Where repeated runs disagree, the disagreement is reported rather than averaged away.
Someone at Timepoint reads every client deliverable against your stated boundaries before it reaches you, for what it’s arguing rather than what it says. The engine will route around a stated constraint semantically if you let it.
Give us a decision your organisation made at least a year ago whose outcome never became public. Tell us what you knew at the time and nothing about what happened. We simulate it blind and hand you the ranked branches. You compare against what actually occurred.
The non-public part is the whole test. A decision whose outcome was reported anywhere is inside the training data of every model we run — we’d be measuring recall, not simulation. Most real decisions were never public, which is why this works.
If you’d rather not take our word for the blindness, have someone on your side hold the outcome and compare the result against what happened.
You keep the result either way. If it misses, you find that out too.
The ontology identifier is tt-ontology/1.0 v2.1.0. Shape, vectors, and tests live in the
published taxonomy — read them at source rather than from a marketing page. We do not publish node,
edge, or mechanism counts here; those figures have been wrong before.
| Claim | Source | How it was checked |
|---|---|---|
| BSL 1.1, converting to Apache-2.0 four years after each version’s own publication | The repository’s LICENSE |
Read at source |
| Governance — change classes, NYSE-close windows, deprecation-only retirement | The Timepoint Telemetry README | Read at source |
| The engine routes around stated constraints semantically | Our own testing record | Internal observation, reproduced twice. Nobody outside Timepoint has confirmed it |
| The engine has relabeled which side a named person was on | The same record | The same — internal, unconfirmed externally |