{"podcast":{"title":"Agentic DevOps : AI Engineering for Infrastructure","slug":"agentic-devops","podcast_index_feed_id":7351100,"rss_url":"https://feeds.transistor.fm/agentic-devops","website_url":"https://agenticdevops.fm","image_url":"https://img.transistorcdn.com/scfZTdWGzzHd49MpOiduVkac3R3yY0f-h0LBO3yfhQg/rs:fill:0:0:1/w:1400/h:1400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS83MDc2/ZmQxYmZkMjk0NTcx/OTg5MmY2YjBkZjQy/NzYwZS5qcGc.jpg","author":"Bret Fisher","episode_count":11,"summary":"Where LLMs, AI Agents, and MCP tools meet DevOps and platform engineering. How can we humans use non-deterministic, often hallucinating LLMs to automate our infrastructure and help us with the job of software lifecycle management? I’m Bret Fisher, and this is the Agentic DevOps podcast. After the invention of AI Agents and the MCP standard in late 2024, I started this podcast in early '25 with a narrow topic focus… to document and advise how AI Agents, MCP tools, and large language models can be used in the real world for assisting with DevOps automation, platform engineering, and day to day systems operations… a podcast series hopefully without the hand-wavy AI hype or dreams of a pure AI workforce. I'm joined by my co-host, Nirmal Mehta, and expert guests trying to make use of crazy texting robots.","last_synced_at":null,"page_url":"https://stenobird.com/podcast/agentic-devops"},"episode":{"title":"Four Months Felt Like Four Years","slug":"four-months-felt-like-four-years","published_at":"2026-03-26T08:54:34+00:00","page_url":"https://stenobird.com/podcast/agentic-devops/four-months-felt-like-four-years","show_page_url":"https://stenobird.com/podcast/agentic-devops","url":"https://agenticdevops.fm/episodes/four-months-felt-like-four-years","audio_url":"https://media.transistor.fm/261092e6/0fbab0d5.mp3","summary":"The rapid evolution of frontier models is shifting AI from a simple coding assistant to an autonomous agent capable of managing complex infrastructure. This episode explores how DevOps engineers can transition from manual prompting to building 'skills' as programmable SOPs.","meta_description":"Explore the shift from AI assistants to Agentic DevOps. Learn how to use AI agents for infrastructure automation, managing 'app tsunamis', and scaling SRE.","key_points":["Main idea: AI is moving from a chat interface to 'agentic workflows' that can execute multi-step infrastructure tasks","Practical takeaway: Convert tribal knowledge and manual processes into Markdown-based 'skills' that act as programmable SOPs for agents","Failure mode: The 'App Tsunami'—the massive influx of AI-generated applications will create unprecedented automation debt and shadow IT risks","Practical takeaway: Use tools like GitHub Copilot and specialized agents to act as 'custodians' for repository maintenance and CVE remediation","Main idea: The future of DevOps lies in managing the orchestration of agents that can handle thousands of containers autonomously"],"chapters":[{"start_ms":70000,"title":"Beyond Prompting and Hallucinations","summary":"A look at how recent frontier models have significantly reduced hallucinations, making AI reliable enough for actual engineering tasks."},{"start_ms":620000,"title":"The App Tsunami and Automation Debt","summary":"Discussing the massive wave of new applications being built by AI and the resulting pressure on CI/CD and infrastructure."},{"start_ms":1170000,"title":"The Rise of Agentic Workflows","summary":"How the role of DevOps is shifting from manual automation to managing AI agents that can run longer, more complex tasks."},{"start_ms":1990000,"title":"Skills as Programmable SOPs","summary":"A strategy for turning standard operating procedures into Markdown files that serve as training data for AI agents."},{"start_ms":2260000,"title":"Agent Orchestration and Shadow IT","summary":"The risks of non-technical users building infrastructure via AI and the need for guardrails in an agent-driven ecosystem."},{"start_ms":2530000,"title":"AI as the Repository Custodian","summary":"Using specialized agents to automate the 'janitorial' work of DevOps, such as monitoring CVEs and managing PRs."},{"start_ms":3080000,"title":"Scaling to the Future of Operations","summary":"Reflecting on how the shift from VMs to Cloud prepared us for the current shift toward managing massive-scale containerized environments with agents."}],"topics":["Agentic DevOps","Infrastructure Automation","AI Engineering","CI/CD","SRE","GitHub Copilot","Platform Engineering","Cloud Native"],"duration_seconds":3652,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/agentic-devops/episodes/four-months-felt-like-four-years/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/agentic-devops/four-months-felt-like-four-years.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}