> ## Documentation Index > Fetch the complete documentation index at: https://docs.toorow.com/llms.txt > Use this file to discover all available pages before exploring further. # What toorow Says When Nobody Asked > The rules a claim must satisfy when the product volunteers it — provenance, derived confidence, disclosed silence, and no invented causes. Most of toorow answers questions. Three surfaces do something else: they make a claim nobody requested. * the **nightly briefing** behind `get_daily_report` — what changed since yesterday, and what is worth looking at; * **anomaly detection** — this value is outside its own recent behaviour; * the **daily insight** — a model-authored reading of the day, with a recommended action. That changes the burden of proof, and everything on this page follows from it: > When a person asks a question, a wrong answer is a wrong answer. When the > product volunteers a claim, a wrong claim is **also an interruption the person > did not choose** — arriving with the authority of having been selected as worth > saying. *** ## It never invents a cause A correlation observed in the data is not an explanation. Where no governed context event covers the window, the assertion says *context missing* and stops. A context event may name the metric it concerns. When it does, a claim about a different metric will not quote it — and a claim that could not compare says so, rather than treating "no metric named" as a match. *** ## Every claimed number carries its provenance, and an absent one is not zero A figure in a proactive claim carries the pull that produced it and how fresh it is. A measure that was not collected is reported as absent — never rendered as `0`, which is a value somebody could act on. A comparison names **both** of its terms. "Up 12%" without saying against what is not a comparison. *** ## Silence is a state, and it is disclosed A detector that cannot yet fire is not a quiet detector — it is an absent one, and the surface says so. A z-score computed over a window that includes the point being tested cannot exceed `(n−1)/√n`. With the default threshold, that makes the detector mathematically unable to fire below **eleven** observations, and unable to reach the `error` severity below **twenty-seven**. The bound is derived from the configured threshold, not hard-coded: move the threshold and the number moves with it, on every surface that discloses it. So a project with nine days of history is not told "no anomalies". It is told the detector cannot speak yet. *** ## Confidence is derived, never self-declared A confidence level chosen by the author of a claim measures nothing — and that applies to a model exactly as it applies to a person. An insight names its evidence, and the publication gate refuses a reference the server did not measure for this project over this window. Confidence is then computed from **the rows carrying the members the claim actually cited**, restricted to the insight's own period — not the project's rows at large: | Term | What it measures | | ------------ | --------------------------------------------------------------------------------- | | Completeness | The share of the cited members the server measured over the insight's own period. | | Freshness | The stalest contributing source decides. | | Provenance | The share of supporting rows carrying a pull identifier. | The reading is the **band of the limiting term** — never a blend. Completeness cannot buy back staleness. And `unmeasurable` is a legitimate reading, not a level: an insight whose evidence cannot be scoped says so instead of scoring itself. *** ## Model-authored prose carries one marker Where a model wrote the sentence, the surface says so — once, not on every clause. Cited data carries no marker, because the data was not authored. A proactive claim stays a **springboard, never a verdict**: it points at something worth opening, and the opening is where the answer is defended. *** ## Publishing, retracting, and leaving the platform | Act | What the platform does | | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Publish** | The insight is persisted with its evidence references, each one checked against what the server measured. | | **Retract** | An audited transition, never a deletion. What was said stays readable as having been said, and withdrawn. | | **Share externally** | Refused by default. Sending an assertion outside the platform needs the project capability **and** a confirmation by a *second* role holder — the requester and the confirmer cannot be the same person. | Over MCP: `get_daily_insight_readiness` says whether there is anything worth publishing, `preview_daily_insight` composes it, `publish_daily_insights` publishes it, and `retract_daily_insight` withdraws it. *** ## Next Steps & Cross-References The z-score method, its baseline window, and the bound behind the disclosure. The nightly run that produces the claim. Rule 5: context events are candidates, never causes. The same two-person rule, applied to a figure leaving the platform.