The Safest Way I've Found to Let AI Coding Agents Run Real Infrastructure
Sep 8, 2026Cole Medin
Summary
This post introduces a secure method for AI coding agents to interact with real infrastructure by leveraging Kestra's flow-based execution. Instead of granting direct credentials, agents are given a list of allowed flows defined in YAML and stored in Git. Each execution is logged as a readable event, significantly reducing the risk of unauthorized actions. This approach enhances the safety of AI agents operating on production systems.
More from the Team-level AI knowledge base with access control trail
- You Built Your AI Second Brain. Now What? (Here's How to Evolve It)
- My NEW FAVORITE Skill - Claude Code Drives My Whole Computer (Better Computer Use)
- GPT-6 Astra Just Made AI Software Factories Real (Here's How to Run One)
- No One Talks Enough About Security for AI Coding. Here's How I Do It in My Workflows
- AI Software Factories Are the Next Big Thing (And I'm Building You One)