Four Months Felt Like Four Years - Agentic DevOps Podcast

Bret Fisher Docker and DevOps
Bret Fisher Docker and DevOpsMar 26, 2026

Why It Matters

Without robust DevOps automation and agentic tooling, the surge of AI‑generated applications will overwhelm operations, turning AI’s productivity promise into a hidden cost for enterprises.

Key Takeaways

  • AI models now produce far fewer hallucinations than six months ago.
  • Non‑technical users will generate apps, intensifying shadow‑IT risks.
  • DevOps must automate end‑to‑end pipelines to handle application surge.
  • New Claude Opus and Sonnet models are considered game‑changers.
  • Platform engineering must evolve to support rapid, developer‑driven deployments.

Summary

The Agentic DevOps podcast returns for a season‑two kickoff, focusing on how generative AI—especially the latest Claude Opus, Sonnet, and Gemini models—has reshaped software delivery and amplified shadow‑IT concerns. Hosts Brett Fischer and Nurmal Ma reflect on the rapid evolution since their last episode, noting that AI hallucinations have dropped dramatically and that new "agentic" tools now guide infrastructure tasks with minimal prompting.

Key insights include the emergence of high‑performing frontier models (Opus 4.6, Sonnet 4.6, Gemini 3.1 Pro) that cut error rates and accelerate the inner development loop. Solo developers can now juggle multiple projects simultaneously, while enterprise teams face a looming tsunami of applications that will stress existing CI/CD pipelines and operational capacity. The hosts warn of growing "ops debt" if automation and platform engineering do not keep pace.

A memorable moment comes when Fischer demonstrates an AI‑driven ECS cluster build, highlighting how the model asks clarifying questions and fills gaps without manual scripting—a stark contrast to the painstaking shepherding required six months earlier. Ma emphasizes that shadow‑IT is no longer a niche issue; generative AI enables non‑technical users to spin up production workloads, raising governance and security challenges.

The implication for businesses is clear: to harness AI’s productivity gains without drowning in unmanaged services, organizations must double down on end‑to‑end automation, adopt agentic tooling, and reinforce platform engineering practices. Failure to do so could exacerbate operational overload and erode the promised efficiency of AI‑augmented development.

Original Description

It’s been 6 months since the last episode, and it feels like everything has changed. Bret and Nirmal catch you up on the increasing pace of AI change, how it will likely affect DevOps engineers and platform builders, and what’s coming on the podcast.
Check out the audio podcast version here: https://share.transistor.fm/s/261092e6
{{campaign_start}}
Show Links
=========
Agent Harness Skills https://agentskills.io
Video of Gradel CEO "You can write code faster, can you deliver it faster?" https://www.youtube.com/watch?v=VOXNJ9_sHuM
🙌 I've launched the Agentic DevOps Guild, which is my premium community for accelerating your AI adoption for DevOps, CI/CD, platform engineering, and SRE. It includes courses, regular meetups, workshops, and mentorship. 🍾 https://www.bretfisher.com/theguild
🗞️ Sign up for my weekly newsletter for the latest on upcoming guests and what I'm releasing: https://www.bretfisher.com/newsletters/cloud-native-devops
Bret Fisher
=========
Join my Community 🤜🤛
================
💌 Weekly newsletter on upcoming guests and stuff I'm working on: https://www.bretfisher.com/newsletters/cloud-native-devops
💬 Join the discussion on our Discord chat server https://discord.com/invite/devops
👨‍🏫 Coupons for my Docker and Kubernetes courses https://www.bretfisher.com/courses/
#agenticdevops #devops

Comments

Want to join the conversation?

Loading comments...