# Santiago says agents monitoring production systems save money and need trust checks

> Original title: We've been running a few agents to monitor production systems for a few weeks now.

- Source: Santiago
- Published: 2026-10-27T13:52:35.000Z
- Bad Influence: https://badinfluence.news/items/xli31qnjcscao5aqxr1cejdsv
- Original: https://x.com/svpino/status/2115079215582429355

## Summary

Santiago says his team has run several agents for a few weeks to monitor production systems around the clock, diagnosing failures, suggesting causes, and recommending fixes. He says the agents save a lot of money and handle tasks the team could not do before. He lists five questions to answer before trusting such agents, including whether they understand the systems, can see what happened, can access recent code changes, and can have their evidence verified.

## Post

We've been running a few agents to monitor production systems for a few weeks now.

Agents working 24/7, looking at failures, suggesting potential causes, and recommending fixes.

We're not only saving a ton of money, but we are also doing things we couldn't before.

But to set this up, you need to trust these agents. Here are a few questions you need to answer:

• Do your agents understand how your systems work?
• Can they see what actually happened?
• Do they have access to the code that changed recently?
• Can you verify the evidence behind the agent's recommendations?
• Do these agents recognize when they need help?

You can't automate production monitoring without all of this.

Here is what you want to do next:

[Video](https://badinfluence.news/api/img-proxy?u=https%3A%2F%2Fpbs.twimg.com%2Famplify_video_thumb%2F2115079067649355776%2Fimg%2FugyhFCiCf4R6vZrH.jpg&mode=thumb&exp=1793404800&sig=0455419c943f57cf)