> ## Documentation Index > Fetch the complete documentation index at: https://metoro.io/docs/llms.txt > Use this file to discover all available pages before exploring further. # Overview > Understand Guardian, Metoro's AI SRE, and its workflows for deployment verification, issue detection, investigation, and root cause analysis ## What is Guardian? Guardian is Metoro's AI SRE. Guardian can verify deployments, investigate production issues, root cause alerts, generate fixes, and more. ## Key Features Track recurring issues in one place with the root cause, symptoms, impact and resolution steps. Automatically verify deployments for regressions by comparing pre- and post-deployment telemetry and infrastructure health. Detect unexpected production issues without preconfigured thresholds and continue investigating them automatically. Investigate firing alerts with AI to separate noisy alerts from real incidents and return root cause with supporting evidence. Define investigation tasks for Guardian to execute when alerts fire so it gathers the context your team needs most. Ask Guardian questions directly and gather debugging context across telemetry, infrastructure state, and code changes. When connected to GitHub, Guardian can inspect code changes, recommend fixes, and create pull requests for review. Route deployment results, investigations, and issue findings to the right teams and systems. Use your own AWS Bedrock credentials for complete control over AI processing and billing. ## Pricing AI SRE usage can be billed in two different ways depending on whether you provide your own model credentials. * **Bring your own model credentials**: If you provide your own LLM credentials, such as your own AWS Bedrock access keys, you only pay Metoro's normal ingest price. Your model usage is billed directly by your provider. * **Use Metoro-managed model credentials**: If you do not provide your own key, Metoro calculates the LLM usage for your account based on the tokens consumed and passes that usage through to you at cost, with no markup added. ## Core AI SRE Workflows Guardian operates through several interconnected workflows that turn telemetry, code, and infrastructure context into action. ### Deployment Monitoring & Verification Metoro automatically tracks all releases across your Kubernetes clusters. When you deploy a new image tag: 1. A `new_deployment` event is created for the service 2. If given access to code, Guardian will read code changes and use this information to do a more thorough analysis 3. Guardian compares pre- and post-deployment telemetry, log patterns, latency, and infrastructure signals 4. If issues are found, Guardian notifies you with evidence 5. If not, Guardian marks the deployment as healthy [Learn more about Deployment Verification →](/ai-sre/deployment-verification) ### Autonomous Issue Detection & Root Cause Analysis Guardian continuously monitors your systems for anomalous behavior: 1. Detects anomalies like error rate spikes automatically 2. Runs an investigation to determine if the behavior reflects a real production issue 3. Identifies the root cause using logs, traces, and metrics 4. Posts to Slack with findings if an issue is confirmed [Learn more about Autonomous Investigation →](/ai-sre/anomaly-detection) ### Alert Investigations Guardian can investigate alerts that your team already configured: 1. An alert fires from a known threshold or condition 2. Guardian determines whether the alert is noisy or a real incident 3. If it is real, Guardian continues investigating to the likely root cause 4. Metoro sends the findings with supporting evidence [Learn more about AI Alert Investigations →](/ai-sre/alert-investigations) ### AI Runbooks When you configure alerts, you can attach runbooks for Guardian to execute: 1. Alert fires based on your configured thresholds 2. Guardian executes the runbook you've defined 3. Creates an investigation document with all gathered data 4. Links the investigation from the alert notification [Learn more about AI Runbooks →](/ai-sre/runbooks) ## Getting Started Start with [Getting Started](/getting-started/getting-started) to decide whether Metoro will be your full observability and AI SRE platform or run side by side with your current stack. Once you know your adoption path and deployment model, install Metoro and wait for telemetry to arrive. Guardian AI is the umbrella setting for Metoro's AI SRE workflows. During onboarding you will be asked whether you want to enable `Guardian AI`. You can also enable this later in the **Settings** → **Features** → **Guardian AI** section. [Take me there](https://us-east.metoro.io/settings?tab=features\&subtab=guardian-ai) Enable deployment verification so Metoro automatically checks whether new rollouts are healthy or regressed. During onboarding you will be asked whether you want to enable `AI Deployment Verification`. You can also enable this later in the **Settings** → **Features** → **Deployment Monitoring** section. [Take me there](https://us-east.metoro.io/settings?tab=features\&subtab=deployment-monitoring) Enable autonomous issue detection so Guardian can proactively detect and investigate unexpected production issues. During onboarding you will be asked whether you want to enable `Autonomous Issue Detection`. You can also enable this later in the **Settings** → **Features** → **Autonomous Issue Detection** section. [Take me there](https://us-east.metoro.io/settings?tab=features\&subtab=autonomous-investigation) Connect repositories and allow Metoro to **automatically** map your services to repositories so Guardian can use code context during investigations, deployment analysis, and suggested fixes. During onboarding you will be asked whether you want to connect `GitHub` and map services to repositories. You can also do this later in the **Settings** → **Integrations** -> **Third-party Integrations** section. [Take me there](https://us-east.metoro.io/settings?tab=integrations\&subtab=third-party-integrations) In the final step of onboarding, you will be asked if you want to run issue finder. If you do so, this will start your first AI investigation(s) in Metoro to demonstrate how Guardian investigates issues. ## Next Steps Review recurring Guardian findings and their latest investigations Set up automatic deployment verification Enable autonomous issue detection and root cause analysis Investigate firing alerts with Guardian AI Ask questions directly in chat and gather debugging context quickly Add repository context and generated fixes