Episode

SE Radio 719: Birol Yildiz on Building an Agentic AI SRE

Podcast
Software Engineering Radio - The Podcast for Professional Software Developers
Published
May 6, 2026
Duration seconds
3237
Processing state
failed
Canonical source
https://se-radio.net/2026/05/se-radio-719-birol-yildiz-on-building-an-agentic-ai-sre/
Audio
https://traffic.libsyn.com/secure/seradio/719-birol-yildiz-agentic-ai-sre.mp3?dest-id=23379
JSON
/v1/public/podcasts/software-engineering-radio/episodes/se-radio-719-birol-yildiz-on-building-an-agentic-ai-sre
Markdown
/podcast/software-engineering-radio/se-radio-719-birol-yildiz-on-building-an-agentic-ai-sre.md

Actions

  • POST https://stenobird.com/v1/public/podcasts/software-engineering-radio/episodes/se-radio-719-birol-yildiz-on-building-an-agentic-ai-sre/transcription-requests
    Idempotently request low-priority transcript generation for this episode.
  • GET https://stenobird.com/podcast/software-engineering-radio/se-radio-719-birol-yildiz-on-building-an-agentic-ai-sre.md
    Read the agent-friendly Markdown representation of this episode resource.

Summary

Birol Yildiz, CEO and co-founder of iLert, joins host Kanchan Shringi to explore how iLert built an AI SRE — an autonomous agent for handling production incidents — and what the experience revealed about building AI agents in the real world. Birol explains why incident response is a fundamentally agentic problem, where the unpredictability of novel incidents makes rule-based runbooks insufficient and reasoning models essential. He describes how the AI SRE evolved from an early browser-based approach to its current architecture, built around two key ingredients: reasoning models and the Model Context Protocol. The conversation examines the four layers of the AI SRE in depth: an orchestration layer that routes requests and abstracts model providers; a knowledge layer built on plain text memory and agentic search rather than vector databases; an evaluation framework based on recorded live investigations replayed against new model versions; and a human-in-the-loop constraint layer. The episode concludes with practical advice for teams building agents: own your context completely, avoid off-the-shelf frameworks that obscure what enters the model, and get out of the way of the reasoning model rather than over-prescribing its steps.