LoginSign Up
← Back to all sparks
R

Rootly

INFRA · APIS
Velocity6.3

Rootly keeps widening what its AI observes — now the incident call itself, in any language.

incident-responseagent-nativemeeting-transcriptionon-callobservability-integrations
◆Current state
The AI work runs along two lines: evidence gathering across the observability stack, and the incident call itself. Meeting Scribe now detects the language spoken on a call and transcribes it with no configuration, removing the setup step that made the feature single-language in practice. Around it sits the routine platform work — catalog sync, alert-storm muting, on-call widgets, retrospective templates.
◆Where it's heading
The pattern is consistent: every artifact an incident produces — telemetry, chat, the call — becomes something Rootly's AI reads and turns into retrospective material. Language detection is a small change with a specific consequence: distributed teams whose incident calls are not held in English now get the same automated record as everyone else. The catalog and alerting work underneath keeps making that record attributable to a service and an owner.
◆Prediction
Expect Scribe output to feed the retrospective AI-blocks directly, closing the loop from call to written retrospective without a manual step.

◆Recent moves

  1. 8d ago

    Meeting Scribe speaks your language.

    Meeting Scribe now detects the language spoken on an incident call and transcribes it with no setup. A narrow change with a clear consequence for the arc: non-English incident calls now produce the same machine-readable record that the retrospective tooling is built to consume.

  2. 15d ago

    Sync your catalog, and mute pages during Alert storms.

    A CLI that syncs the catalog from GitHub, Backstage, and others, plus mobile alert muting and an Upwind integration. This is the supply side of the AI work — the agent is only as good as how current the service and ownership data underneath it is.

  3. 22d ago

    Rootly AI now gathers incident evidence across your entire stack.

    ⚡ SPARK

    The pivot point of the last month. Rootly AI stops waiting for a human to supply context and goes to get it across observability, code, infrastructure, feature flags, ticketing, and docs, which is what the catalog investment was building toward.

  4. 22d ago

    Rootly AI connects to your observability stack and beyond.

    A duplicate row for the same 28 July release as the entry above, where the crawler captured both the headline and a variant of it. Same change: read-only connections spanning the observability, code, and ticketing stack.

  5. 27d ago

    From sign up to incident-ready in minutes.

    One command sets up team, on-call, alerting, and status page, then pages the operator's phone to prove it works. Onboarding speed matters more once the product's value depends on the catalog and integrations actually being populated.

  6. 1mo ago

    The on-call widget, 24-hour time, and a new Alerts table.

    A live on-call widget in the sidebar, 24-hour time, and a customisable Alerts table. Unglamorous, but this is the surface responders stare at while an incident is running, and it had been lagging the AI work.