What we measure, and how we know

Configured phone paths are checked by an automated canary that records its result. We would rather show a failed check than treat missing evidence as success. Tool failures are logged through the same evidence path instead of being omitted.

source: event ledger — canary_run + voice_call + tool_failure classes · counters render when the aggregation feed is attached; until then, honest “measuring”.

Calls answered, appointments booked, and forms captured are counted from the event ledger. These are aggregate totals only: no company name, no caller, no per-client breakdown ever appears here. And we hold each counter back until it clears a floor — a number too small to mean anything reads “measuring,” because a tiny count paraded as a milestone would argue against us, not for us.

source: event ledger — voice_call · booking_created · form_capture classes, a counter renders only once it clears its display floor · the metric is the receipt: each published number ships with its event class and window.

The honest way to know whether an AER agent actually helped is to hold a portion of leads back untouched and compare. That is a holdout: for a client cohort, some contacts are worked by the agent and a matched set is held, and we report the difference — worked versus held — only after a full measurement window closes. We never model the lift, back-fill it, or show a projection.

source: holdout measurement engine — per-cohort worked/held delta · published only on window completion · zero synthetic numbers.

Some numbers cannot be measured honestly, so we do not publish them — even when a competitor would. Keeping this list public is the point.

• No unsupported callback stat. Recovery events carry machine timestamps, but no public timing figure is published here without an independently verified certification ledger and adjacent own-test disclosure.
• No outcome-timeline promise. Delivery scope and timing are reviewed privately. Outcome timelines depend on the contractor's market, so we do not publish a result timeline.
• No counts below a floor. A small tally is not a milestone. Until a metric clears its display floor it reads “measuring” here rather than borrowing weight it has not earned.
• No caller data, recordings, or transcripts. Call recordings and transcripts never appear on this surface, by design — this page shows aggregates and self-checks only.

source: CLAIMS-CANONICAL — the single quotable source for every external Vectrion claim · corrections to public claims are logged and reflected here.

Pre-launch system testing is own-test evidence, not a client result.

The certification corpus is synthetic test traffic recorded in separate banked ledgers. One ledger exercises the recovery path; the other exercises controlled dispatch timing. Neither is presented as customer traffic, client volume, or a completed-job result. No public count is published without independent ledger verification.

sources: banked synthetic recovery-path ledger + banked controlled dispatch-timing ledger · classification: certification traffic, never client traffic · registered certification class in the Vectrion stat registry.