AI-Augmented DevOps with Platform Engineering
summary
Describes a working platform that integrates Azure OpenAI and LLMs behind a developer portal and CLI, with a floating platform design that plugs into GitHub/GitLab and Argo CD via adapters. Shows a deployed container image analyzer LLM, namespace lockfile analysis, and a searchable reference finder built on vector DBs. Quantifies a testing bottleneck with 336 hours lead time versus 8 hours process time and 50% rework, and demonstrates live use by developers with plans for PR auto-fixes and a Visual Studio co‑pilot.
AI-written summary · about
chapters (9)
- 0:00intro
- 0:14speaker background and experience
- 2:41understanding the need for ai in devops
- 3:43value stream mapping and identifying bottlenecks
- 8:30ai use cases in devops
- 10:58the importance of platform engineering
- 15:34building a floating platform
- 18:16real-world implementation and demo
- 26:15summary and closing remarks
related talks
40mAI-Augmented DevOps with Platform Engineering
25mAI for Platform Engineering
39mSimplify, speed and improve development with DevOps
24mAIGenOps: Integrating Generative AI into Platform Engineering
26mOrganize AI Chaos With Platform Engineering
44mBeyond Metrics: Orchestrating Developer Delight with AI driven Platform Engineering
41mEfficient DevSecOps workflows with a little help from AI
38mPlatform Engineering in the Age of AI Teammates