Episode
Running AI agents on your production server is the new FTP
- Podcast
- No Compromises
- Published
- Jul 18, 2026
- Duration seconds
- 905
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/c6778465
Actions
POST https://stenobird.com/v1/public/podcasts/no-compromises-1309932/episodes/running-ai-agents-on-your-production-server-is-the-new-ftp/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/no-compromises-1309932/running-ai-agents-on-your-production-server-is-the-new-ftp.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
Have you ever let an AI agent run commands on your production server because you were stuck, telling yourself it would be fine? In the latest episode of the No Compromises podcast, we discuss why giving AI agents access to your production environment is as reckless as the bad old days of FTPing code straight to your server. We make the case that AI agents are non-deterministic and carry no responsibility, which makes them far more dangerous than a developer making a manual mistake on a live server. We also cover why you should never blindly run complex chained commands that an agent suggests, how to verify what your agent is actually doing, and why a little friction in your workflow is worth the safety it buys you. (00:00) - FTPing to production is still wrong in 2026 (01:50) - Running Tinker on production is no better (02:28) - AI agents on production servers is even worse (07:11) - How to verify what your agent is actually doing (move from 07:00) (11:03) - Silly bit Stop letting non-deterministic tools make deterministic mistakes in your codebase. Get a code review . Subscribe to our newsletter and get practical Laravel tips delivered to your inbox every day.