{"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":"Can AI Agents Safely Become DevOps Engineers?","slug":"can-ai-agents-safely-become-devops-engineers","published_at":"2026-04-29T17:12:06+00:00","page_url":"https://stenobird.com/podcast/agentic-devops/can-ai-agents-safely-become-devops-engineers","show_page_url":"https://stenobird.com/podcast/agentic-devops","url":"https://agenticdevops.fm/episodes/can-ai-agents-safely-become-devops-engineers","audio_url":"https://media.transistor.fm/f10d5fc2/672db84b.mp3","summary":"AI agents are moving beyond simple code completion to act as autonomous junior DevOps engineers. This discussion explores how Mendral uses LLMs to manage GitHub Actions, remediate CI failures, and automate infrastructure maintenance.","meta_description":"Explore the future of Agentic DevOps with Sam Alba. Learn how AI agents can automate GitHub Actions, manage CI/CD failures, and act as junior DevOps engin…","key_points":["Main idea: AI agents function as non-deterministic 'junior engineers' capable of managing the middle space between development and production","Practical takeaway: Use specialized agents to automate repetitive 'janitorial' tasks like updating linters, fixing failed tests, and managing dependencies","Failure mode: Relying on a single model for all tasks; the future requires multi-model architectures to balance reasoning depth with speed","Technical insight: Effective agentic DevOps requires providing context across entire organizations rather than just individual repositories","Future vision: The evolution from simple automation to 'sub-agents' that can be triggered by external events like Sentry exceptions"],"chapters":[{"start_ms":60000,"title":"The Agentic DevOps Vision","summary":"An introduction to Mendral and the concept of AI agents acting as junior DevOps engineers within GitHub ecosystems."},{"start_ms":440000,"title":"The Evolution of CI/CD","summary":"Comparing traditional CI runners and GUIs to the new landscape of automated infrastructure management."},{"start_ms":800000,"title":"AI as the DevOps Janitor","summary":"Discussing how agents can handle the toil of managing large-scale repository environments and reducing manual overhead."},{"start_ms":1180000,"title":"The Agentic DevOps Guild","summary":"An overview of training and community efforts to move engineers toward an agent-first mindset in automation."},{"start_ms":1560000,"title":"Architecting Intelligent Agents","summary":"A deep dive into the implementation of agents that can interpret complex, undocumented tribal knowledge within an organization."},{"start_ms":1930000,"title":"Managing Context and Tribal Knowledge","summary":"How to bridge the gap between undocumented system configurations and the agent's operational awareness."},{"start_ms":2310000,"title":"Automating Issue Remediation","summary":"Using agents to raise issues and identify patterns in infrastructure failures to reduce manual checking fatigue."}],"topics":["DevOps","AI Agents","GitHub Actions","CI/CD Automation","Infrastructure as Code","LLMs","Platform Engineering","Software Delivery"],"duration_seconds":4894,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/agentic-devops/episodes/can-ai-agents-safely-become-devops-engineers/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/agentic-devops/can-ai-agents-safely-become-devops-engineers.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}