Everyday questions
Here are examples of exact questions you can ask @Rootly in Slack for different use cases, and what it gives you in return.Getting oriented
| You ask | What the assistant 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” | It can adapt its tone and technical depth for different audiences |
Look up people, teams, on-call
| You ask | What the assistant 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 execute as you, with your existing Rootly permissions. Anything destructive confirms before firing.| You ask | What the assistant 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 the assistant 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 the starter retrospective the team can add copy to their Retrospective document |
Search and lookups
| You ask | What the assistant 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 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 the assistant “What’s missing from this timeline? Be critical.” It 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?” The assistant 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
The assistant 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?” The assistant maintains context across the thread and pulls all of the relevant data points to give you a picture from its perspective.Adaptive technical depth
The assistant 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
The assistant can chain multiple write actions in a single conversation. For example, Ask “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 it did.What the assistant can’t do
- Writes only happen inside incident channels. The Slack side pane and DMs are read-only by design.
- Paging is through Rootly On-Call only. Even if PagerDuty, Opsgenie, or JSM Ops are connected elsewhere in Rootly, the assistant will not page through them.
- No production runtime actions. The assistant won’t run kubectl, roll back a deploy, restart a pod, or flip a feature flag. It can create an action item and page someone who will.
- No code generation or PR creation. The assistant doesn’t write code.
- Reactive by default. The assistant responds when asked. Proactive nudges and ambient listening are not part of the default experience.
- Slack-only. The Rootly web app’s AI features (retrospective AI blocks, meeting summary) are separate surfaces.
- It won’t invent data. If the answer isn’t in your Rootly data, the channel discussion, or a connected external source, the assistant says so rather than guessing.