{"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":"AI SREs, Chat With Your Infrastructure with Anyshift","slug":"ai-sres-chat-with-your-infrastructure-with-anyshift","published_at":"2026-05-06T22:03:55+00:00","page_url":"https://stenobird.com/podcast/agentic-devops/ai-sres-chat-with-your-infrastructure-with-anyshift","show_page_url":"https://stenobird.com/podcast/agentic-devops","url":"https://agenticdevops.fm/episodes/ai-sres-chat-with-your-infrastructure-with-anyshift","audio_url":"https://media.transistor.fm/014eae35/7a476100.mp3","summary":"Moving beyond simple chatbots, Anyshift introduces an AI SRE designed to manage the complex context of production infrastructure. The discussion explores how agentic workflows use context graphs and memory to proactively identify risks and automate incident resolution.","meta_description":"Explore the future of Agentic DevOps with Anyshift. Learn how AI agents use context engineering and memory to automate SRE tasks and manage infrastructure.","key_points":["Main idea: The shift from LLM chat interfaces to autonomous agents capable of managing infrastructure context","Practical takeaway: Using context graphs and memory allows agents to learn production patterns and avoid false positives","Failure mode: Inadequate permissions or fragmented documentation can lead to agent hallucinations and incorrect decisions","Main idea: Agentic DevOps requires integrating disparate data sources like AWS, GitHub, and monitoring tools into a unified context window","Practical takeaway: Implementing a 'plan and build' mode allows engineers to safely onboard agents with read-only access before granting write permissions"],"chapters":[{"start_ms":60000,"title":"Beyond Chatbots to Agentic DevOps","summary":"The transition from simple text completion to agents that can generate and manage YAML, HCL, and complex infrastructure code."},{"start_ms":300000,"title":"The Need for AI SREs","summary":"Addressing the challenge of managing modern infrastructure with shrinking engineering teams through capable autonomous services."},{"start_ms":790000,"title":"Real-world Impact and Use Cases","summary":"Discussing how AI agents can reduce PagerDuty fatigue and the 'aha' moments experienced by early customers."},{"start_ms":1270000,"title":"Context Engineering and Memory","summary":"How providing agents with specific, high-quality infrastructure data is central to solving production problems quickly."},{"start_ms":1770000,"title":"The Infrastructure Context Graph","summary":"Building a 'time machine' of production resources, dependencies, and historical connections to provide agents with deep visibility."},{"start_ms":2030000,"title":"Permissions, Auditing, and Trust","summary":"Navigating the security implications of granting agents access to Kubernetes APIs and cloud credentials."},{"start_ms":3010000,"title":"The Future of Autonomous Operations","summary":"A vision of a future where agents proactively detect and fix problems, allowing engineers to focus on higher-level architecture."}],"topics":["Agentic DevOps","SRE","AI Agents","Infrastructure as Code","Context Engineering","Incident Management","Cloud Automation","Platform Engineering"],"duration_seconds":3258,"processing_state":"processed","actions":[{"name":"request_transcript","method":"POST","url":"https://stenobird.com/v1/public/podcasts/agentic-devops/episodes/ai-sres-chat-with-your-infrastructure-with-anyshift/transcription-requests","description":"Idempotently request low-priority transcript generation for this episode."},{"name":"read_markdown","method":"GET","url":"https://stenobird.com/podcast/agentic-devops/ai-sres-chat-with-your-infrastructure-with-anyshift.md","description":"Read the agent-friendly Markdown representation of this episode resource."}]}}