Skip to content

Guides

Run production with AI, carefully.

Practical guides on AI-assisted operations: what the tools do, and how to give an agent access without it becoming the incident. For setup steps, see the docs.

  1. 6 min read

    How to give AI coding agents safe production access

    Give coding agents production access with scoped read-only tokens, human approval for destructive actions, a full audit trail and a kill switch you can use.

    • AI agents
    • Security
    • Permissions
  2. 6 min read

    Using an MCP server to operate infrastructure

    How an MCP server lets AI agents discover and call infrastructure operations, which setup to choose, and the security checks to make before your first write.

    • MCP
    • Infrastructure
    • AI agents
  3. 6 min read

    What AI SRE tools do, and how to evaluate one

    AI SRE tools triage alerts, correlate deploys with errors and propose fixes. What they do, where they stop, and a two-week plan for evaluating one.

    • AI SRE
    • Incident response
    • Evaluation

Put it into practice

Step-by-step use cases built on the same ideas, each linked to the docs.

Weighing up tools? See how Escanor compares.