Skip to main content
Public beta: AI SRE is in public beta, rolling out gradually to accounts on On-call Pro or higher, at no additional charge during the beta. To get access, submit the AI SRE beta application form. Features and the UI may continue to change.

​
Key Concepts (30 Seconds)

Four things to know before you start:

​
Three Entry Points

There’s no single way into AI SRE — start from wherever you already are:

​
Chat

For actively investigating an issue, digging deeper, or building up knowledge. Go to AI SRE → Chat → New Chat. Suggestion chips below the composer fill in a ready-made prompt; type @ to reference an incident. → See Chat

​
Automations

For work that shouldn’t need a human watching it — scheduled inspections, weekly insight reports, alert-noise cleanup. Go to AI SRE → Automations and create one from a built-in template (Alert Noise Analysis, Incident Response Review, Weekly On-call Insights, and more) or build one from scratch. Each run happens in a hidden session in the background, and the result lands in the run history where you can open the full trail any time. → See Automations

​
IM (@ Mentions + Automatic War Room Diagnosis)

Where incidents actually happen. In any Slack, Feishu, DingTalk, or WeCom group with the bot connected, @ AI SRE to start or continue an investigation — it replies in-thread. Open a war room for an incident and AI SRE automatically runs an initial diagnosis and posts the conclusion back. → See IM

​
Your First Investigation (~5 min)

Prerequisite: an account on On-call Pro or higher with at least one incident. AI SRE access rolls out gradually during the public beta, so your account also needs to be enabled — if it isn’t yet, submit the AI SRE beta application form.
Plan requirement: AI SRE requires an On-call Pro or higher subscription. Learn more
If you don’t have an incident on hand right now, skip ahead to “Growing It Into Your SRE” below.
1

Start a new session

Go to AI SRE → Chat and click New Chat in the sidebar.
2

Bring in the incident context

Type @ in the composer to open incident search, then pick the incident you want to investigate — it’s inserted as a reference chip. You can also click the Investigate an incident chip below the composer: it fills the input with a ready-made prompt, and you can still append an @ incident reference before sending.
3

Send your instruction

Send something like:
4

Watch the investigation unfold

The agent streams its plan, tool calls, and intermediate findings, then delivers a conclusion backed by evidence.
You’re done when: you’ve received a reply with an investigation plan, a trail of tool calls, and an evidence-backed conclusion — and you can keep asking follow-up questions about it. If it doesn’t work, check:
  • @ doesn’t find the incident — confirm it actually exists in this account and the name or ID is spelled correctly;
  • No response for a while, or it’s stuck on “environment initialization” — the cloud Sandbox or Runner is probably still starting up; give it a moment. For persistent unresponsiveness, see the troubleshooting section in Environments;
  • The reply only has a conclusion, no plan — just ask “give me an investigation plan first, then evidence for each point” and the agent will follow up;
  • You can’t find the AI SRE entry at all — confirm the account has an On-call Pro or higher subscription; it may also not be gradually enabled yet, so submit the AI SRE beta application form to request access.
Next: for streaming, cancellation, forking a session, and context compaction, see Chat.

​
Growing It Into Your SRE (As Needed)

Your first investigation is just the starting point. How well AI SRE diagnoses depends on how much it knows about your systems and how much real data it can reach — both are things you build up over time, not all at once.

​
Build a team knowledge base

If the agent has to guess “what service is this,” “who owns it,” and “how was this handled last time” on every investigation, it won’t get much sharper. Type /init in a session and the agent interviews you to map out your services, runbooks, on-call routing, and more — confirming each write before it saves anything, and loading it automatically in future sessions. See the full interview flow in Setup (/init) and the knowledge base structure and best practices in Knowledge.

​
Connect real data sources

By default the agent only sees Flashduty’s own data. To let it query your actual systems — logs, metrics, code repositories, internal databases — connect an MCP server or deploy a BYOC Runner. Publicly reachable services (observability platforms, GitHub, and similar) install and authorize in one click from the MCP directory; VPCs, internal databases, or local commands need a Runner deployed on a machine that can reach them. See MCP and Environments.

​
What’s Next

Product Overview

What AI SRE is, its full capability set, and console navigation.

Chat

Creating and managing sessions, streaming, forking, and context compaction.

IM Platform

@ the agent in IM to troubleshoot, and learn about automatic war room diagnostics.

Environments

Cloud Sandbox vs. BYOC Runner, deployment, and permission configuration.