Tool Gate · How it works
How the Canary Call Library gate works
How the Canary Call Library rolls a release's canary calls up to its worst against your own baseline: a canary that slips below baseline drops the release to SLIPS TO REVIEW, and a broken barge-in or escalation escalates it to REGRESSIONS FOUND — so a mostly-green release still needs a look when one canary regresses.
How the gate works
This tool grades every canary test call this release against your own baseline run on the voice behaviors a prompt-text diff never sees, then rolls the library up to its worst canary. It reads 4 canaries and rolls them into one verdict — the worst, never the average — and then a gate that can only make it worse.
The 4 canaries
| Canary | Verdict |
|---|---|
| CN-001 · Booking · hours | ON BASELINEmatches the run you shipped |
| CN-002 · Booking · appointmentreview first | BELOW BASELINElatency 1250ms > baseline 950ms + slack |
| CN-004 · Pricing question | ON BASELINEanswer correct · barge-in 5/5 |
| CN-007 · Escalation demand | ON BASELINEscripted escalation fired |
The verdict bands
Some drills don't bend: barge-in below 5 of 5, or a scripted escalation that didn't fire, forces CANARY BROKE regardless of how correct the answers were — an agent that talks over callers fails the call, the words being right doesn't save it. Every canary rolls up worst-first, and a single broken canary escalates the whole library past SLIPS TO REVIEW to REGRESSIONS FOUND.
In the worked sample it reads SLIPS TO REVIEW — Three canaries match the run you shipped. One — CN-002 — is below baseline: its p95 latency jumped from 950ms to 1250ms, past the slack, while the answer stayed perfectly correct. A prompt-text diff sees no change; the call just got slower. No canary broke a dispositive drill, so the library rolls up to SLIPS TO REVIEW rather than REGRESSIONS FOUND. Marked fix first on this sample: CN-002 (Booking · appointment) — the only canary below baseline, and it slipped on a latency tail a text diff can't see. Review that latency regression before the release goes out; correctness held, but the call got slower.
Common questions
Can every canary look survivable on the Canary Call Library and the company still read SLIPS TO REVIEW?
Yes. The roll-up takes the worst of 4 canaries — never the average — then a worsen-only gate, the Dispositive-drill break gate, escalates when trouble clusters. In the worked sample it reads SLIPS TO REVIEW because three canaries match the run you shipped. One — CN-002 — is below baseline: its p95 latency jumped from 950ms to 1250ms, past the slack, while the answer stayed perfectly correct. A prompt-text diff sees no change; the call just got slower. No canary broke a dispositive drill, so the library rolls up to SLIPS TO REVIEW rather than REGRESSIONS FOUND.
What is a worsen-only gate?
A rule that can only lower a verdict, never raise it. One gate-triggering gap overrides an otherwise-set of survivable lines, because a single gate-triggering gap shouldn't hide behind an average of the healthy ones. Where something is short, the fix-first row names it — here, "CN-002 (Booking · appointment) — the only canary below baseline, and it slipped on a latency tail a text diff can't see. Review that latency regression before the release goes out; correctness held, but the call got slower.".
Scope note. The Canary Call Library scores runs you record against your own baseline; it places no calls, connects to nothing, and grades no person. It is a release-quality aid, not a certification, and not legal advice.
Embed this diagram
Free to share and embed with attribution (CC BY 4.0) — keep the link to redhub.ai.
Interactive — renders the live diagram
<iframe src="https://redhub.ai/visuals/tool/canary-call-library.html" title="How the Canary Call Library gate works — RedHub AI" width="760" height="1780" loading="lazy" style="border:0;width:100%;max-width:760px"></iframe>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai/visuals/tool/canary-call-library">How the Canary Call Library gate works</a> — by <a href="https://redhub.ai">RedHub AI</a>, the AI that tells you when to doubt it.</p>Image + link — a static picture for any blog
<a href="https://redhub.ai/visuals/tool/canary-call-library"><img src="https://redhub.ai/visuals/tool/canary-call-library-share.png" alt="Diagram of the Canary Call Library: canary calls rolled up worst-not-average against a baseline, and the release reading SLIPS TO REVIEW when one canary is below baseline." width="760" loading="lazy" style="max-width:100%;height:auto;border-radius:16px"></a>
<p style="font:14px/1.5 system-ui,sans-serif"><a href="https://redhub.ai">RedHub AI</a> — the AI that tells you when to doubt it.</p>
This is how Canary Call Library works. More diagrams in the Visual Field Guide.