What is AI SRE
AI SRE is Flashduty’s autonomous SRE agent platform. You give the AI instructions through conversation. It investigates incidents, diagnoses root causes, and calls tools to run diagnostics on its own. It also saves the operational knowledge from each investigation for later reuse. It plans its own steps, reads and writes files, queries monitoring and logs, runs commands, calls external tools (MCP), and delegates subtasks when needed. Its conclusions come with the investigation trail. AI SRE is deeply integrated with Flashduty’s incident response system. When Flashduty generates an incident or opens a war room, you can directly trigger an AI SRE session so the agent starts with the incident context. You can collaborate in the console or by @ mentioning it directly in your IM group (Slack / Feishu / DingTalk / WeCom).Conversation as Troubleshooting
Describe the problem in natural language. The agent plans autonomously, calls tools, and delivers an investigation trail and conclusion — no manual scripting required.
Integrated with Incident Response
Launch a session with one click from an incident or war room. The agent enters the investigation with full incident context, and the knowledge it accumulates feeds back into the next response.
Typical use cases
AI SRE has an entry point from incident trigger to retrospective:Conversational Troubleshooting
Ask questions proactively in the console’s Chat workspace: why a service is behaving abnormally, the root cause of an alert, or the blast radius of a change. The agent streams its planning, tool calls, and intermediate findings before delivering a final conclusion.
On-Demand in IM
No context switching needed — in Slack, Feishu, DingTalk, or WeCom group chats or direct messages, @ AI SRE to start or continue an investigation. It replies in-thread so all team members stay in the loop. See IM Integration.
Automatic War Room Diagnosis
When someone opens a war room for an incident and an enabled automation rule with the War room created trigger matches it, AI SRE automatically runs an initial diagnostic and posts the conclusion to the war room. A first-pass analysis is already in the channel when your team starts investigating.
Usage Insights
Use
/insight to review the past 30 days of sessions, quantify where you’re spending time, identify missing runbooks and repeatedly copy-pasted context, and receive actionable improvement suggestions.Activation and billing
AI SRE is available on every plan. Activate it separately in the console before use; charges are based on actual usage. It does not require an On-call subscription or occupy a member license. Members still need the appropriate permissions.Billing
Billing
AI SRE is settled in credits (1 credit = ¥1). Metered items are model usage, sandbox online time, and web search. Activation is free, and eligible accounts get gift credits each billing period. You can also buy credit packages, valid 365 days from payment (sizes and prices are in the purchase agreement). Pay-as-you-go is off by default; an admin can turn it on and optionally set a per-period cap. Full terms: AI SRE Credit Package Purchase Agreement.When gift credits, credit packages, and the wallet balance are all used up, AI SRE pauses new conversations. It shows the reason above the composer, with a Go to AI SRE billing button. An admin can turn on pay-as-you-go, buy a credit package or top up there, and you can then continue.
Activating and closing AI SRE
In the console, open Payment → Plan and select the AI SRE tab to activate or close AI SRE yourself. This is available on SaaS only and requires the Payment Read and wallet purchase permissions.
After closing:
- Gift credits and purchased credit packages keep their balances and validity, and you can use them again when you re-activate. Gift credits are still valid only in the billing period they were granted for.
- Credit package refunds follow the AI SRE Credits Package Purchase Agreement.
- You can close AI SRE even with an overdue balance or a lapsed subscription.
- If closing fails, retry.
Independent billing periods and IM applications
Billing and gift-credit periods run in consecutive 30-day windows from the first AI SRE activation. Disabling and re-enabling the service does not reset the period or grant that period’s gift credits again. Existing accounts retain their current period and continue with independent 30-day periods when it ends. IM applications can be created, authorized, and enabled on every plan for AI SRE direct or group conversations. Using an application as an On-call notification target, including escalation policies and on-call reminders, still requires an active On-call Pro plan. Otherwise, selection is disabled, the server rejects the configuration, and restricted notifications from existing configurations are not sent. On-call expiry or downgrade does not interrupt AI SRE conversations. On-call actions such as acknowledging or resolving an incident retain their existing permission and license requirements. AI SRE analysis does not grant additional incident-management permissions.Core capabilities
You can configure and manage all of the following in the console.Conversational Troubleshooting
Collaborate with the agent session by session. A session handles your messages one at a time, with streaming output, cancellation at any time, automatic compaction for long conversations, and one-click launch from an incident.
IM Platform
@ the agent in Slack / Feishu / DingTalk / WeCom to start or continue an investigation, and receive rule-driven initial diagnostics in incident war rooms.
Skills
Skill packages that the agent can invoke, encapsulating reusable troubleshooting workflows. Scope can be set to Shared (account-level) or Team; once enabled, they are loaded on demand during sessions.
Manage Knowledge
Knowledge indexed through DUTY.md as the entry point and @-reference links, carrying service catalogs, runbooks, on-call routing, and other long-lived context — loaded in layers by account and team.
MCP (External Tools)
Connect external tools and data sources through the Model Context Protocol.
Agent
Delegate tasks to external remote agents through the standard A2A protocol. AI SRE also exposes its own Agent Card so external clients can invoke it in reverse.
Environments
Where the agent runs commands: Flashduty-managed cloud sandboxes by default, or a self-hosted Runner on your own machine so investigations can reach your private network.
Usage Insights
Use /insight to review the past 30 days of AI SRE sessions and receive a quantified overview, narrative summary, and actionable operational improvement suggestions (read-only; nothing is applied automatically).
Automations
Have AI SRE run a hidden session on a cron schedule, through an API call, or on an On-call incident to automatically produce periodic inspections, insights, or post-mortems.
Apps
Authorize GitHub, GitLab, or a Kubernetes cluster so AI SRE can work in your code repositories and clusters. It can understand code, investigate PRs / MRs and commits, open a PR or file an issue on request, or act within the scope you set on a cluster.
Console navigation
After entering AI SRE, the left sidebar has four entries (menu names match the console):
The three groups under Customize:
Menus or sub-tabs you do not have permission for are not shown.
Quick start
For the full walkthrough from activating access to finishing your first investigation, see Quickstart.Next steps
Console Chat
Learn about sessions, streaming output, cancellation and context compaction, and how to launch an investigation from an incident.
IM Platform
@ the agent in Slack / Feishu / DingTalk / WeCom, and learn about automatic war room diagnostics.
Usage Insights
Use /insight to review the past 30 days of sessions and surface operational friction such as repeated context and missing runbooks.