“If you build your own agentic systems and you use tokens through API, you might see that you will have to pay 10, 20 times more in real cost for the same capabilities. … There is no audit on the agentic usage. No one knows where it is used, what kind of prompts people are running. Are there agentic loops that just got stuck and using money for no reason?”
Ship It Weekly - DevOps, SRE, Platform and Cloud Engineering News · Hands-On Engineering Podcasts · November 2026
Context
The host asked how companies handle the financial side of running agentic workflows. The guest says subscriptions from the big AI providers are heavily subsidized, so teams running agents on API tokens face much higher real costs, and agent usage mostly goes unaudited.
Transcript
…these drifts and then use agents to help clean it up, right? And bring everything into infrastructure as a code to following your standards. So having that, if you have that kind of information, then dealing with drift is pretty simple. And you can build it yourself, this kind of logic as well.
…What we haven't really touched on is the financial aspect of running agents in cloud. How do companies deal with the financial implications of running models? It's saving them time. It's maybe helping with velocity. But how do they manage that cost when it comes to running agentec workflows?
…few hundred thousand of not a few tens, thousands of dollars worth of tokens, or other cases where the budget was used up within three months, the budget that was planned to be used for a year. And I think also the disconnect also comes from that we may be used to using AI from ChatGPT, from OpenAI, from Cloud Code, through subscriptions, and they subsidize them a lot. So if you use, let's say, if you build your own Agentic systems and you use tokens through API, you might see that you will have to pay 10, 20 times more in real cost for the same capabilities. So this makes it, of course, challenging. To invest into this kind of your own, building your own workflows. And this is also something that we, you know, we also offer subsidized in a way service right now, right? But for companies to be able to build, let's say, same capabilities internally, if they want similar to Cloud Genie, they would have to pay 10 to 20 times more to enable the same…
How do you correlate the spend in the API calls for the agent versus the production output that you're getting from that? How do you correlate those two?
Yeah. Yeah, right now it is more wipes, I would say, than hard data, definitely. But we can see it already in our own case, for example, right? We are able to achieve quite a lot with extremely small engineering teams, right? We don't basically have a dedicated DevOps engineer. We run everything…
Okay, so given the cost aspect, given the guardrails, given the models, is there anything that you wouldn't trust an AI Agent with yet that you think it's maybe not great at solving? Maybe a person, whether it doesn't have the context or just a person better suited for solving it?
More from Ship It Weekly - DevOps, SRE, Platform and Cloud Engineering News
