Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

DevOps Paradox

DevOps Paradox artwork

DOP 358: Just-in-Time Access for AI Agents

Jul 8, 202650 minAudio

#358: Production is on fire. You need access to one table you have never touched. So you file an access request, then phone the desk to say you filed it, then Slack them to say you phoned, then walk over to say you Slacked. Twenty-five minutes later the incident has resolved itself and the customer has already left. That is the setup, and Ofir Stein has lived the other side of it. He is the CTO and co-founder of Apono, and before that he was an engineering leader who felt the same pain every day - not because he hated security, but because he hated being blocked. There is a difference, and the whole conversation turns on it. Put productivity on one side, security risk on the other, and access management in the middle. Tighten one and you starve the other. Nobody wants to be slower and nobody wants to be breached, so the honest answer is there is no clean answer. Then AI agents show up and break the last assumption standing. Software used to be deterministic - your computer could not decide to do something other than what it was told. LLMs can. They can be socially engineered the way people are. Ofir's team built a full AWS environment run by AI agents, opened a Discord channel, and invited anyone to try to trick them. People could. That is the new attack surface, and it moves at machine speed - far too fast for the access reviews and approval chains built for humans. The guardrails everyone is now scrambling to build for agents should have been there for humans all along. Access is the one thing in your stack that never went dynamic. Servers scale up and down, pipelines rebuild everything, and then access is a static policy someone set two weeks ago when security sat with your manager and guessed what you would need. That is the opposite of how the rest of DevOps works. Ofir's argument is that access should change with context - who you are, whether you are on call, whether there is an open incident - evaluated in real time. For a human that is a faster request. For an AI agent, the decision has to live inside the loop, made by silicon, because no person can approve thousands of operations a minute. If access is per-operation and every operation is already a specific API call, what is left to scope? If the business context changes by the minute, how do you write guardrails in advance? And once the human is out of the loop, are you not just left with one AI deciding what another AI is allowed to do? Ofir does not pretend that part is solved. What he is sure of is the direction: the doors at the mall open when you walk up and close when you leave, and you never think about them. That is where access is headed - and there is a lot of road between here and there. Ofir's contact information: LinkedIn: https://www.linkedin.com/in/ofir-stein/ YouTube channel: https://youtube.com/devopsparadox Review the podcast on Apple Podcasts: https://www.devopsparadox.com/review-podcast/ Slack: https://www.devopsparadox.com/slack/ Connect with us at: https://www.devopsparadox.com/contact/

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. DOP 377: KubeCon North America 2026 Review

    Nov 18, 202637 minAudio

    #377: Every software company that ever thought about sponsoring KubeCon already sponsors KubeCon. So where does it grow from here? Ask what on the expo floor wasn't AI, and you get two answers: the coffee and the puppy...

    Credit the people on this episode

  2. DOP 376: Secrets Management for AI Agents

    Nov 11, 202641 minAudio

    #376: How many secrets can your coding agent reach right now? You gave it a token so it could get work done. It might have passed that token to every agent it spun up. Somewhere along the way, you stopped reading the...

    Credit the people on this episode

  3. DOP 375: AI Writes the Code. Who Understands It?

    Nov 4, 202649 minAudio

    #375: An agent can crank out 200 or 300 lines of code a minute. You can maybe review 40. So who's actually supposed to understand what just got merged? Maybe nobody ever did. Did you really read every line of every PR...

    Credit the people on this episode

  4. DOP 374: Does AI Make Companies More Productive?

    Oct 28, 202656 minAudio

    #374: Your company is paying for the AI licenses, and now there's a number attached. Two to three times the output, every day, or else. Can you hit it? If they're counting lines of code, sure. But you aren't the...

    Credit the people on this episode

  5. DOP 373: Are Layoffs Really Because of AI?

    Oct 21, 202645 minAudio

    #373: A company lays off 4,000 people the same day it posts record revenue, and the stock jumps. Is that really because of AI? Or just a really good press release? Layoffs used to mean a company was bleeding cash. Now...

    Credit the people on this episode