Skip to main content
Rootly AI applies generative AI across the entire incident lifecycle — from the moment an alert fires through post-incident analysis. Rather than acting as a separate tool, Rootly AI is embedded directly into incident workflows, helping responders understand what is happening, decide what to do next, and document outcomes with minimal manual effort. Rootly AI provides proactive guidance, accurate summaries, and contextual insights using simple conversational prompts in Slack, the web app, and the mobile app. All capabilities are designed to fit naturally into existing incident response processes without disrupting established workflows.
Rootly AI augments incident responders — it doesn’t replace them. Rootly AI provides context, suggestions, and summaries while keeping humans in control of decisions and actions.

​
What Rootly AI Can Do

Rootly AI supports a focused set of capabilities that map directly to common incident-response needs. Each feature can be used independently and is available when both enabled at the team level and permitted for the specific incident based on privacy settings.

​
Rootly AI in Slack, Web, and Mobile

Rootly AI lets responders ask contextual questions using natural language across three surfaces:
  • Rootly AI in Slack is a conversational assistant inside your incident channels. Beyond answering questions, Rootly AI can take actions on your behalf — paging, updating severity and status, managing action items, and drafting comms — always as your user and with your existing Rootly permissions.
  • Rootly AI in Web is the same conversational assistant in the incident page of the web app. Use it to catch up, understand impact, and draft communications without leaving the incident.
  • Rootly AI on Mobile puts a live Incident Summary and the conversational assistant into the Rootly mobile app — so on-call responders can get oriented and take action from their phone. Mobile is enabled by a separate toggle from the web assistant.

​
Generated Incident Titles

Rootly AI automatically generates concise, descriptive incident titles from available incident context. Teams quickly understand the nature of an incident without manually crafting a summary under pressure. Titles are designed to be short, consistent, and informative, making dashboards, timelines, and retrospectives easier to scan.

​
Incident Summarization

Rootly AI produces a single, coherent summary of what happened during an incident. The summary is generated from incident metadata, timeline events, alerts, action items, and relevant communications. It captures the problem, impact, trigger or cause when available, resolution steps, and key participants in plain language. Summaries can be generated and updated during an active incident or after resolution, and improve as more information becomes available. Generate summaries using /rootly summary in Slack or the Generate Summary button in the web application.

​
Incident Catchup

Rootly AI helps responders who join an incident after it has already started quickly get oriented. Instead of scrolling through long Slack threads, responders can request a catchup summary that reflects the current state of the incident. Request a catchup summary using /rootly catchup in Slack or the catchup feature in the web application. This is especially useful for long-running or high-severity incidents with heavy communication volume.

​
Mitigation and Resolution Summaries

When an incident transitions through key lifecycle stages such as mitigation, resolution, cancellation, or closure, Rootly AI drafts short explanations of what actions were taken and why. These summaries ensure that incident timelines and retrospectives accurately reflect decision-making and outcomes without requiring responders to write detailed explanations during or after an incident.

​
Rootly AI Editor

The Rootly AI Editor is available in all text fields throughout the platform, including incident descriptions, summaries, communications, retrospectives, and more. It improves written content by fixing grammar, simplifying language, expanding details, or shortening text while preserving meaning.

​
Rootly AI Meeting Scribe

Rootly AI automatically joins incident bridge calls on supported meeting platforms — Zoom, Google Meet, Webex, Microsoft Teams, and GoToMeeting. During meetings, it captures live transcripts and produces post-meeting summaries. Transcripts and summaries are attached to the incident and can be incorporated into Rootly AI summaries and retrospectives.

​
Rootly AI in Retrospectives

Rootly AI drafts entire sections of a retrospective document for you — Summary, Impact, Root Cause, Mitigation, Resolution, a Curated Timeline, or a custom section you define. Each block is generated from the incident’s data, the incident Slack channel, and bridge-call transcripts, and stays editable: regenerate it, edit it inline, convert it to plain text, or rate the output. Add AI blocks to a template so every retrospective generates them automatically, or insert them on the fly in the editor. See Rootly AI in Retrospectives. This feature is in research preview and enabled per team.

​
Privacy, Security, and Control

Rootly AI is designed with privacy and data isolation as first-class principles. All Rootly AI functionality is controlled through team-level settings, allowing organizations to opt in or out of individual features. Rootly AI access is evaluated on a per-incident basis and respects incident visibility and Slack message-scoping rules. For private incidents, Rootly AI features are only available when explicitly permitted by configuration. Sensitive information such as links, emails, and passwords is automatically redacted before being sent to AI providers, and all requests are authenticated and scoped to the requesting organization. Organizations can also bring their own LLM API keys, including OpenAI or IBM Watsonx, for additional data privacy and segmentation. BYOK currently applies to the single-turn Rootly AI features (titles, summaries, catchup); BYOK for the conversational Rootly AI assistant is on the roadmap and not yet available.
Rootly AI never uses customer data to train models or improve results for other customers. Data sent to AI providers is used solely to deliver Rootly AI functionality.

​
Learn More

​
Frequently Asked Questions

No. Rootly AI is controlled through team-level configuration settings and can be enabled or disabled per feature. Rootly AI access is also evaluated on a per-incident basis and respects incident visibility and privacy rules.
Most Rootly AI features — titles, summaries, catchup, and the Rootly AI Editor — only suggest content and never change incident data on their own. The exception is Rootly AI in Slack, which can take actions on your behalf (paging, severity and status changes, action items, comms). It always acts as your user, with your existing Rootly permissions, and confirms destructive actions before they run.
No. Rootly AI never uses customer data to train models or improve results for other customers. Data sent to AI providers is used solely to deliver Rootly AI functionality.
Rootly AI can be used in private incidents only when explicitly permitted by configuration. Access depends on incident visibility settings and Slack message scope controls.
Rootly AI settings are managed at the team level in the Rootly web application. Each Rootly AI capability can be enabled or disabled independently.
Need help or have a question? Contact us anytime at support@rootly.com, use the /rootly support Slack command, or visit Getting Help to start a chat.