Recent feedback — owner & operator notes across the fleet
Moat
↻ Refresh
Where the moat is built. Per-tenant feedback tunes its own agents automatically (Lessons, below); cross-tenant lessons are promoted here — and ONLY here — after you abstract & sanitize them by hand. Owner feedback never auto-generalizes.
Needs you0decisions waiting right now — everything below this band is monitoring, not deciding
Turns raw feedback into candidates & Lessons items. Safe to re-run.
Goes liveresolving one of these changes what a real customer hears, now — full commit weight
Promotion candidates 0
Conflicts 0
Two tenant rules that overlap, contradict, or sit in tension. Keep as-is, replace the loser, split by scope, or kick to the owner.
Prune proposals 0
Live rules sitting dead past the maturity gate (100+ loads, zero applies, 30-day mature). Retiring one is reversible.
Route to Coderesolving one of these files a product signal — nothing changes for a customer
Cross-tenant signals 0
Breadth (tenants asking) outranks depth (times asked) — one loud owner is not a pattern. The handoff is one-directional by construction: a Goes-live card can route here; nothing here ever becomes a rule.
Monitoring glance, don't decide — nothing here is waiting on you
Transfer health
Where each promoted directive actually landed. A universal rule demoted at several destinations is the evidence trail working — the pattern doesn't travel; the mechanism didn't fail.
Graduation
Promoted (system learnings)
Lessons — per-tenant rule review 0
Every note S4ge distilled sits here as a pending candidate until you promote, edit, or reject it — scoped to its own tenant, not the fleet. Compliance-quarantined items need human/legal review and can never be promoted.
Pending ↻
Accumulating 0↻
Below-threshold observations — visible, never applied. A situational note needs 3 concept-matched instances (or one deliberate confirmation) before it becomes a real candidate.
Awaiting owner 0↻
This tenant's graduation dial is at Rung 1 for this rule class — the owner confirms in their own dashboard, not here. You can still pull a proposal back before they see it.
Live ↻
Fleet
↻ Refresh
Every tenant, always glanceable. Opening a tenant's dashboard is a plain new-tab link to that tenant's own live surface — there is no reason-bound, time-boxed, or audited drill-in session today; that's a real gap, not a design choice, flagged for a future build.
Platform
↻ Refresh
Agent health, the governed-action log, the R0n sandbox, and live-surface launchers — condensed onto one page. Read-only except R0n (synthetic sandbox only, no real sends).
Agent health
Sweep & error rate
Last full health sweep and the platform-wide error rate it measured. Auto-resolves server-side; nothing to act on here.
Incidents open 0
Advisories open 0
Governed actions — the same promotions shown in Moat, framed as an audit trail. There is no separate governed-action log table today.
R0n sandbox
Drives the real agents against synthetic tenants. No live SMS/email, no real charges — every run auto-archives.