> ## Documentation Index > Fetch the complete documentation index at: https://docs.flashduty.com/llms.txt > Use this file to discover all available pages before exploring further. # AI SRE Product Overview > Flashduty's autonomous SRE agent platform — use natural language to let AI independently investigate incidents, diagnose root causes, and accumulate reusable operational knowledge, deeply integrated with Flashduty's incident response system and IM collaboration **Private beta**: AI SRE is currently in private beta. Pro or higher accounts can apply for free beta access through the [AI SRE private beta application form](https://c9xudyniiq.feishu.cn/share/base/form/shrcn0ngCfdoygiaHnAT80BfZiH); after approval, Flashduty will add your account to the whitelist. Features and the UI may change during the beta. ## What Is AI SRE *** AI SRE is Flashduty's autonomous SRE agent platform. You give the AI instructions through conversation, and it independently investigates incidents, diagnoses root causes, calls tools to run diagnostics, and captures the operational knowledge gained from each investigation for future reuse. It is not a simple Q\&A chatbot — it is a **hands-on troubleshooting worker**: it plans its own steps, reads and writes files, queries monitoring and logs, executes commands, calls external tools (MCP), and delegates subtasks when needed, ultimately delivering conclusions backed by a full 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 enters the investigation with full incident context — you can collaborate either in the console or by **@ mentioning it directly in your IM group (Slack / Feishu / DingTalk / WeCom)**. Describe the problem in natural language. The agent plans autonomously, calls tools, and delivers an investigation trail and conclusion — no manual scripting required. 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 is more than a chat box in the console — it covers multiple collaboration entry points across the full lifecycle from incident trigger to retrospective: 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. 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](/en/ai-sre/im). When a war room is opened for an incident, AI SRE **automatically runs an initial diagnostic** and posts the conclusion back to the war room — by the time your team starts investigating, a first-pass analysis is already in the channel. Use [`/insight`](/en/ai-sre/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. ## Beta Access & Activation *** AI SRE is currently in private beta. Activation requires both of the following conditions to be met: AI SRE requires a **Pro or higher** subscription. Consistent with other professional capabilities such as Status Page and alert ingestion, it is unavailable on lower tiers, and the UI will prompt you to upgrade. During the private beta, AI SRE is available only to accounts approved through the beta application process and must be whitelisted by Flashduty for your account. Even with a Pro subscription, accounts not on the whitelist will not see the AI SRE entry point. AI SRE is **free** during the private beta and is not billed separately. It will become a paid capability after commercialization starts. Before billing begins, Flashduty will share the product billing information, and you can choose whether to formally activate AI SRE or pause usage. No AI SRE charges are incurred before you confirm activation. To join the private beta, submit the [AI SRE private beta application form](https://c9xudyniiq.feishu.cn/share/base/form/shrcn0ngCfdoygiaHnAT80BfZiH). After approval, Flashduty will add your account to the whitelist. ## Core Capabilities *** AI SRE is built around "conversational troubleshooting + knowledge accumulation + autonomous execution," with every capability configurable and manageable from the console. Collaborate with the agent session by session. A session handles your messages one at a time, with streaming output, cancellation at any time, automatic context compaction for long conversations, and one-click launch from an incident. @ the agent in Slack / Feishu / DingTalk / WeCom to start or continue an investigation, and receive automatic initial diagnostics in incident war rooms. Skill packages that the agent can invoke, encapsulating reusable troubleshooting workflows. Scope can be set to account or team; once enabled, they are loaded on demand during sessions. Knowledge packages indexed via 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. Connect external tools and data sources via the Model Context Protocol. MCP servers are not pre-connected; the agent establishes, uses, and closes connections on demand when making a call. Delegate tasks to external remote agents via the standard A2A protocol. AI SRE also exposes its own Agent Card so external clients can invoke it in reverse. The execution layer for the agent: uses Flashduty-managed cloud sandboxes by default, or deploy a persistent Runner on your own machine to let investigations reach your private network. 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). Have AI SRE run a hidden session on a cron schedule or via an API trigger to automatically produce periodic inspections, insights, or post-mortems. Authorize external applications (currently GitHub) so AI SRE can work directly inside your code repositories: understand code, investigate PRs and commits, and open a PR or file an issue on request. ## Console Navigation *** After entering AI SRE, the top navigation is organized into the following four areas (menu names match the console): | Area | Menu Name | Purpose | | ------------ | ---------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | Chat | **Chat** | The primary workspace for collaborating with the agent on troubleshooting. The left panel shows your session list (with search, filtering, pinning, and archiving); the right panel shows the conversation and investigation trail. | | Plugins | **Plugins** | Manage extensible resources the agent can invoke, organized into four sub-tabs: **Apps** (authorized external applications, e.g. GitHub), **Skill** (skill packages), **Agents** (A2A remote agents), **MCP** (external tools). | | Knowledges | **Knowledges** | Manage Knowledge Packs. At most one per target: account-level (visible to all agents) plus per-team (loaded only in that team's sessions). | | Environments | **Environments** | Manage self-hosted Runners. The persistent process handles the agent's tool, Skill, and MCP calls; if none is available, sessions fall back to the cloud sandbox. | Visibility of each area is determined by your access permissions in the account: menus or sub-tabs you do not have permission for will not appear in the navigation. ## Quick Start *** Confirm your account has a Pro or higher subscription, then submit the [AI SRE private beta application form](https://c9xudyniiq.feishu.cn/share/base/form/shrcn0ngCfdoygiaHnAT80BfZiH). After approval, your account is added to the AI SRE private beta whitelist. In the Flashduty console sidebar, open **AI SRE**. You will land in the **Chat** workspace by default. Click "New Chat" to create a session. Sessions use the `app_name=ai-sre` agent by default and automatically select an online environment (falling back to the cloud sandbox if none is available). Describe the problem you want to investigate in the chat box — for example, why a service is misbehaving, the root cause of an alert, or the blast radius of a change. The agent streams its planning, tool calls, and intermediate findings, then delivers a final conclusion. You can ask follow-up questions, cancel at any time, or relaunch the session with context from an incident or war room. Reusable knowledge distilled during an investigation can be saved as a Knowledge Pack so subsequent sessions load it automatically; frequently used troubleshooting workflows can be packaged as Skills. ## Next Steps *** Learn about sessions, streaming output, cancellation and context compaction, and how to launch an investigation from an incident. @ the agent in Slack / Feishu / DingTalk / WeCom, and learn about automatic war room diagnostics. Use /insight to review the past 30 days of sessions and surface operational friction such as repeated context and missing runbooks.