Three releases shipped this week: a dashboard surface for usage alert rules so an operator can define a spend or delivery alert without writing API calls, an anomaly-forensics page for usage and delivery deviations, and two voice-agent controls — backchannel cues and a sensitive-words redaction list — that close the gap between a scripted agent and a believable one.
Set a usage alert rule from the dashboard, not the API
The usage-anomaly alert engine already shipped on the API as /usage/alert-rules; the missing piece was a place to manage the rules without a curl command. Insights → Usage alert rules now exposes the full surface: define a rule on SMS delivery rate, outbound message volume, or spend, as either a threshold ("spend above $50/day") or a learned-baseline anomaly that fires without you picking a number. Every rule shows its last-evaluation status and an enable/disable switch, and a breach lands in the in-app notification dropdown with a deep link to the metric. A Evaluate now button runs all active rules on demand for owner, admin, and developer roles. A one-click suggested throttle preset — "alert when daily spend crosses $50" — appears in the create dialog, so an operator's first spend guard is set up in under a minute. Route: dashboard → insights → usage-alert-rules. Docs: Usage anomaly alert rules guide.
See a usage or delivery anomaly as the detectors raise it
The new Insights → Usage & delivery anomaly page reads the same anomaly-insights ledger the API has been returning and turns it into an operator surface. A summary strip shows totals in the current window, the open-anomaly count, and the high/critical severity count. A per-day stacked trendline puts wallet-spend and webhook/inbound scopes on the same chart so a burst in one reads against the other. Below that, a ledger lists every detector raise — category, severity, scope, summary, GMT timestamp — newest first, with a scope filter and a 7d/30d/90d window that resizes the whole view. It is a read-only projection of the ledger (/insights/anomalies), so one tenant can never read another's anomalies. Route: dashboard → insights → anomalies. Api: `by-scope`, `timeseries`, `history`.
Make a voice agent sound like it is listening
Two opt-in controls landed on every agent:
- Backchannel cues. In an agent's voice settings, an intensity toggle (low, medium, high) turns on short acknowledgements — "got it", "I see" — that fire while the caller is still mid-utterance on a long turn. Cues never interrupt the agent's own speech and are cooldown-spaced so they stay sparse; a caller hears active listening instead of dead air.
- Sensitive words. Up to 64 literal words or phrases per agent — competitor names, regulated claim phrasing, anything that should never leave a model's mouth. Every match in the agent's generated output is replaced with
[REDACTED]before it is spoken on a live voice call or returned in text. Both ship off by default and configured per agent, so nothing changes for an agent that does not opt in. Routes: dashboard → agents → <agent> → settings. Docs: Agents overview and Sensitive words guardrail.
Where this shows up
All three ship this week and are live now: the usage-alert-rules page under Insights, the anomalies ledger under the same hub, and the two agent controls on the agent settings surface. The canonical release history stays at orbit.devotel.io/en/changelog — the entries above mirror the 2026-08-27 publish there, and no future capability is promised here before it ships.