> ## Documentation Index > Fetch the complete documentation index at: https://docs.rootly.com/llms.txt > Use this file to discover all available pages before exploring further. # What to Use Rootly AI For > Example prompts for Rootly AI in Slack, from getting oriented and checking who is on call to multi-step requests, plus what it deliberately will not do. ## Overview Rootly AI in Slack answers questions grounded in your Rootly data and takes actions on your behalf, confirming destructive actions before they fire. Everything below requires an [Incident Response role](/ai/rootly-in-slack/overview#who-can-use-rootly-ai-in-slack). *** ## Everyday Questions ### Getting Oriented | **You ask** | **What Rootly AI does** | | :- | :- | | "Catch me up" | Gives you a brief of the problem, status, theory, open action items, and who's involved | | "What's happened in the last hour?" | An activity digest of timeline events and channel discussion | | "Who's the commander?" | Names the current commander and other assigned roles | | "What services are impacted?" | Lists affected services, environments, and functionalities | | "Are any action items still open?" | Lists open action items with assignees and due dates | | "ELI5" or "Catch me up as a non-technical member" | Adapts tone and technical depth for different audiences | ### Look Up People, Teams, On-Call | **You ask** | **What Rootly AI does** | | :- | :- | | "Who's on call for payments?" | Current on-call for the named team, escalation policy, or service | | "Who was on call when this started?" | Historical on-call for the incident's start time | | "What's the escalation chain for the SRE team?" | Full escalation policy with each step | | "Are there coverage gaps in the SRE rotation?" | Schedule and shadow analysis surfacing gaps | | "Find Sam in the team" | Searches for "Sam" across name, preferred name, and email | | "Who's pageable on the payments team right now?" | Filters team members by pageable status | ### Page, Escalate, Run the Incident Write actions are capped at your existing Rootly permissions. | **You ask** | **What Rootly AI does** | | :- | :- | | "Page the payments on-call" | Looks up the team, finds the current on-call, pages them through Rootly On-Call | | "Page Sam" | Resolves the user, confirms, pages | | "Page the SRE escalation policy" | Triggers the named escalation policy | | "Make me commander" | Self-assigns the commander role | | "Mark this SEV1" | Updates severity, confirms in reply | | "Mark this mitigated" | Moves the incident to the mitigated state with required-field check | | "Resolve this" | Resolves the incident | | "Set the impacted service to checkout-api" | Updates the impacted service list using discovery, no hallucinated names | | "Make this incident private" | Changes visibility | | "Request coverage for my shift on Friday" | Files an on-call coverage request | ### Action Items, Retros, Comms | **You ask** | **What Rootly AI does** | | :- | :- | | "Create an action item: investigate the cache miss; assign to Andy" | Parses intent, resolves the assignee, creates the item | | "Reassign the cache item to Rigel and add 4 more reviewers" | Updates assignee and adds reviewers in one go | | "Mark the rollback item done" | Closes the action item | | "Delete that duplicate action item" | Removes the item after confirmation | | "Draft a customer update" | Composes a Slack-ready or status-page-ready update from current state | | "Post a status page update saying we're investigating" | Drafts and (after confirmation) publishes a status page update | | "Add a timeline event for the rollback at 3:42 PM" | Creates a custom timeline event; backdating supported | | "Generate the retro summary" | Drafts a starter retrospective the team can add to their Retrospective document | Rootly AI drafting a status page update in Slack: title, post copy, and a suggested status with the reasoning behind it ### Search and Lookups | **You ask** | **What Rootly AI does** | | :- | :- | | "Show me open SEV1s" | Filters by status and severity | | "How many incidents touched checkout-service this quarter?" | Searches by service and date range, counts results | | "What's our average time-to-mitigate for SEV1s this year?" | Searches incidents and reasons over the result set | | "What custom fields are on this incident?" | Lists configured custom fields and their values | | "What status can I move this to from here?" | Lists valid next statuses given the incident's current state, team config, and sub-status rules | | "List my teams" | Returns teams the requesting user belongs to | | "What's 3:47 PM UTC in my time zone?" | Converts using your configured zone or a named IANA zone | *** ## More Complex Requests Rootly AI in Slack can also run several operations at once to answer your question, and it reasons over the results to handle requests that don't map to one specific ask. ### Critical Timeline Analysis Ask Rootly AI *"What's missing from this timeline? Be critical."* Rootly AI reads the timeline, channel discussion, roles, and standard process expectations, then identifies gaps a senior responder would catch in a retro. Things like: no commander formally assigned, no root cause documented, the incident was resolved before the fix was merged, no status page update. ### Severity Second Opinion Ask *"was SEV3 the right call?"* Rootly AI looks at the affected services, duration, the responder pattern, and customer-impact signals in the channel, then gives a nuanced opinion, pushing back when the evidence supports it. ### Extended Retrospective Conversations Rootly AI supports back-and-forth conversations during a retrospective. Ask "what could have gone better?" → "how did comms look?" → "who should have taken what role?" → "similar past incidents?" → "was the severity call right?" → "how could we have resolved faster?" Rootly AI maintains context across the thread. ### Adaptive Technical Depth Rootly AI adapts to the asker. *"Catch me up"* produces a structured exec brief. *"Catch me up, I'm a Staff Engineer"* produces a technical response naming the failing code path, the relevant error codes, and the race condition. Same incident, different audience. ### Multi-Step Actions Rootly AI can chain multiple write actions in a single conversation. For example: "page the on-call for payments, then mark this SEV1, and create an action item to investigate." Each destructive step confirms separately. The final reply summarizes everything Rootly AI did. *** ## What Rootly AI Can't Do * **Rootly writes only happen inside incident channels.** The Slack side pane and DMs cannot page responders or change Rootly records. Connector and [Private Agent](/private-agent) actions have separate boundaries. Most built-in connectors expose Rootly-reviewed tools, some pass through the provider's full catalog, and Custom MCP uses a customer tool allowlist. Private Agent is an Early Preview for approved teams with AI SRE enabled; its capabilities follow your Rootly role and the agent's local policy. Provider permissions and command controls still govern what an available tool can do. [Devin's supported read-only platform actions](/ai/connectors/devin#slack-ai-platform-tools), for example, are available across Slack; actions that change Devin resources additionally require permission to manage AI connectors. * **Native paging is through Rootly On-Call only.** Rootly AI does not use existing PagerDuty, Opsgenie, or JSM Ops integrations for its native paging action. An available connector tool or authorized Private Agent capability that pages can define a separate boundary under its own permissions. * **No native production runtime actions.** Rootly AI's native tools do not run kubectl, roll back a deploy, restart a pod, or flip a feature flag. An available connector tool or authorized Private Agent capability can expose external runtime actions under its own permission model. * **No native code generation or PR creation.** Rootly AI does not write code itself. When Devin is connected, an authorized user can ask Slack AI to launch and guide a Devin session under the connected service user's permissions. * **Reactive, with one exception.** Rootly AI answers when asked rather than volunteering. The exception is [Related Incidents](/ai/related-incidents), which posts a card into the channel as an incident opens — when your team has turned it on. * **It won't invent data.** If the answer isn't in your Rootly data, the channel discussion, or a connected external source, Rootly AI says so rather than guessing. *** ## Related Pages What Rootly AI in Slack is and everything it can do. Turn on Rootly AI in Slack and walk through your first interaction. Where to invoke Rootly AI, how clarification cards work, and how actions run. Common symptoms and how to resolve them. This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.