Connect your Claude, Codex or OpenClaw for full transcripts on millions of podcasts. Two week free trial, cancel anytime.

Start free trial →
DD Davlet Dzhakishev On Ship It Weekly - DevOps, SRE, Platform and Cloud Engineering News

“If you have a well-engineered system with good access, you already have a process of onboarding junior engineers, where they start with little permissions and you grow from there as their autonomy increases. The same principles can be applied to introducing a new teammate, and in this case it's AI. And if you have immature processes, then AI agents make those things even worse.”

Ship It Weekly - DevOps, SRE, Platform and Cloud Engineering News · Hands-On Engineering Podcasts · November 2026

“If you have a well-engineered system with good access, you already have a process of onboarding junior engineers, where they start with little permissions and you grow from there as their autonomy increases. The same principles can be applied to introducing a new teammate, and in this case it's AI. And if you have immature processes, then AI agents make those things even worse.” — Davlet Dzhakishev, Ship It Weekly - DevOps, SRE, Platform and Cloud Engineering News

Context

The host remarked that this sounds like the familiar basics of least privilege and time-bound access. The guest frames agent onboarding like onboarding a junior engineer, and warns that teams without tight control will have the hardest time.

Transcript

Ship It Weekly - DevOps, SRE, Platform and Cloud Engineering News Around 07:29 into the episode
Davlet Dzhakishev

Yeah.

Brian Teller

Yeah. Okay.

Davlet Dzhakishev

And that's a fun part of it, right? I think this is where good engineering is becoming even more important. I can't remember who said it, but it was definitely a notable quote that, you know, if you have a well-engineered system, right, with good access, you already have a process of onboarding junior engineers, right? Where they start with little permissions and then you can grow from there as their autonomy increases. You know, same principles can be applied to introducing a new teammate, right? In this case, it's AI. And of course, if you have not mature processes, then AI Agent make those things even worse. And I think, you know, the platform teams will probably suffer even more if they don't have a tight grip and control already on those kind of systems.

Brian Teller

Do you think that agents should get direct cloud credentials? Or like in practice, if they are not. In practice, you

Davlet Dzhakishev

create, yeah, you create a special, you know, service principles or whatever way that is designed for your cloud of choice, but you limit the access to RAID only if you want to make sure that it doesn't change your infrastructure directly, right? It should be able to see it. And then your changes…

Brian Teller

What kind of context should that agent have?

Speaker names come from our own diarization. The position is estimated from where the line sits in the episode.

More from Ship It Weekly - DevOps, SRE, Platform and Cloud Engineering News