AI & DevOps · Operations
AI SRE and agentic ops, in reading order
The articles on this site about putting AI agents to work in operations, arranged as one path: agents that investigate incidents, the MCP servers that let them reach your tools, agents inside CI, and the infrastructure code they change.
By Matthews WongReviewed on
Key takeaway
This path starts with AI SRE agents that investigate alerts, from HolmesGPT and Grafana to the AWS, Azure, Google, Datadog, Elastic and PagerDuty offerings, then covers the MCP servers that give agents scoped access to ops tools, the agentic workflows that triage and fix CI, and the Terraform, OpenTofu, Pulumi, Argo CD and Flux changes underneath.
Reading path · 25 articles
Read in this order
Each stage builds on the one before. If you already know a stage, skip ahead; the line under each title says what that article adds.
Stages 1 / 4
AI SRE agents on call
Agents that pick up an alert and come back with a hypothesis: what each one does, what it costs to run, and where its guardrails stop.
- 01DevOps12 min readHolmesGPT Kubernetes Alerts: Runbooks Beat the Model ChoiceWhy this step: Start here: a two-person SRE team routes Prometheus alerts through HolmesGPT into Slack, and finds runbooks matter more than the model.
- 02DevOps11 min readGrafana Assistant Investigations: Alert-Triggered RCA SetupWhy this step: Every page arrives with a hypothesis report: alert-triggered investigations in Grafana, scoped and costed safely.
- 03AI11 min readElastic nightshift AI SRE: Start With the Investigation EngineWhy this step: Elastic splits its AI SRE into four engines; why investigation alone, on existing alerts, is the safest start.
- 04AI/ML12 min readDatadog Scout 1.0: What Cheaper AI SRE Investigations MeanWhy this step: A close reading of Datadog's claim of cheaper investigations, the benchmarks behind it, its credits and a budget script.
- 05Cloud12 min readAWS DevOps Agent: Incident Investigation, Cost and AccuracyWhy this step: How AWS DevOps Agent triages and bills incidents, a daily cost alarm, and a way to test its accuracy claim on your stack.
- 06Cloud12 min readAzure SRE Agent: Tool Permissions, Hooks and Approval GatesWhy this step: Allow, ask and deny rules, hooks and run modes in Azure SRE Agent, and where Ask fails in Autonomous mode.
- 07Cloud12 min readGemini Cloud Assist Investigations: Proactive RCA and FinOpsWhy this step: Google's investigations and proactive agents in Gemini Cloud Assist: setup, Eventarc routing, MCP and failure modes.
- 08DevOps12 min readPagerDuty SRE Agent: Virtual Responder Setup and GuardrailsWhy this step: Put an AI agent on the escalation policy as a virtual responder, and the approve-before-act gaps to know.
Stages 2 / 4
MCP servers for the ops stack
How agents reach observability, cloud, infrastructure and portal tools, and how to scope that access before they do.
- 09DevOps11 min readGrafana MCP Server: OAuth Scopes for Claude Code and CursorWhy this step: Connect Claude Code or Cursor to Grafana Cloud over OAuth, and what the Read, Query and Write scopes allow.
- 10Cloud12 min readAWS MCP Server in Claude Code: OAuth, SigV4 and IAM ScopingWhy this step: Reach AWS from an agent through OAuth or the SigV4 proxy, then scope IAM so it cannot delete.
- 11Cloud11 min readAmazon EKS MCP Server: SigV4, CloudTrail and Write-Mode RisksWhy this step: The managed EKS MCP server: IAM tool permissions, what CloudTrail records, and why write mode stays off in production.
- 12DevOps11 min readTerraform MCP Server GA: A Safe Agent Setup Since 1.1.0Why this step: Run the Terraform MCP server with operations off, an organisation allowlist and a pinned version.
- 13AI12 min readBackstage MCP Actions Backend: Secure AI Access to Your PortalWhy this step: Expose catalog and scaffolder actions to agents through Backstage, with the filters and auth to set first.
- 14AI12 min readCloudflare Code Mode MCP: Two Tools, 1,000 Tokens, a SandboxWhy this step: A whole cloud API behind two MCP tools, search and execute, and the sandbox and OAuth scoping behind them.
Stages 3 / 4
Agents in CI and code review
Agents that run inside the pipeline, and what the research says about the review load they create.
- 15DevOps12 min readGitHub Agentic Workflows: Markdown Automation with gh awWhy this step: GitHub Agentic Workflows compile Markdown into locked Actions YAML; the safe outputs, engines and where it fails.
- 16DevOps12 min readAgentic Workflow CI Failure Triage with gh-aw CI DoctorWhy this step: A read-only agent that triages failing CI runs into one deduplicated issue per failure.
- 17DevOps12 min readCopilot Fix Failing GitHub Actions: Setup and Review RulesWhy this step: Copilot's fix button for failing Actions runs: admin setup, workflow approval and the review rules to keep.
- 18DevOps12 min readAI Code Review Bottleneck: What CMU and Stanford MeasuredWhy this step: Output per developer grew faster than review capacity; what a large study of pull requests measured about review feedback.
- 19DevOps12 min readDORA AI-Assisted Development: Throughput Up, Instability UpWhy this step: DORA ties AI adoption to more throughput and more instability; what to measure and gate as agents join CI/CD.
Stages 4 / 4
The infrastructure code agents act on
The safe pattern for agents on infrastructure, then the Terraform, OpenTofu, Argo CD and Flux releases to plan for.
- 20Security11 min readPulumi Neo Security: Read-Only Scans, Fixes Only as a PRWhy this step: The pattern to copy: scan infrastructure read-only and propose fixes only as a pull request.
- 21DevOps11 min readTerraform 1.16: What's New and How to Upgrade SafelyWhy this step: What Terraform 1.16 adds, from module import blocks to destroy = false, and what to test first.
- 22DevOps11 min readOpenTofu 1.13: convert, assume and Upgrade Breaking ChangesWhy this step: The OpenTofu 1.13 breaking changes and new functions to check before you upgrade.
- 23DevOps12 min readOpenTofu Ephemeral Resources and Write-Only AttributesWhy this step: Keep secrets out of state with ephemeral resources, ephemeral variables and write-only attributes.
- 24DevOps11 min readArgo CD 3.5: mTLS, Source Integrity and Helm 4 Upgrade GuideWhy this step: Argo CD 3.5's repo-server mTLS, source integrity checks and Helm 4 changes, with a pre-upgrade checklist.
- 25DevOps12 min readFlux 2.9: CLI Plugins, SSA Ignore Rules and OIDC WebhooksWhy this step: Flux 2.9's CLI plugins, server-side apply ignore rules and OIDC webhook receivers, and the upgrade traps.
The AI & DevOps field guide
More from the AI & DevOps guide
The other reading paths in this section.
- MCP & Agent SecurityPrompt injection, the 2026 MCP incidents, access controls, sandboxes and vetting agent skills.
- LLM Inference ServingvLLM and SGLang, disaggregated serving, llm-d and KServe, autoscaling and cost per token.
- Kubernetes for AIThe 1.36 and 1.37 upgrades, DRA and gang scheduling, Gateway API routing and agents in the cluster.
- Supply Chain & Regulationnpm and PyPI worms, model signing and AIBOM, secrets in agent commits, the CRA and EU AI Act.