Posts

First post in a two-part series on Azure postmortems. Incidents are inevitable. Repeat incidents are optional. A lot of teams say they do postmortems, but what they really have is a short meeting, a vague document, and a backlog item nobody revisits. A good Azure postmortem is different: it is blameless, evidence-based, and tightly connected to telemetry. If you already use Azure Monitor, Application Insights, Log Analytics, and Azure Activity Logs, you already have most of the raw material you need. ...

Chapter 2: The Deterministic 429 Watchdog In the previous post I explained what MCP is and how an agent decides its next move from the tools available. Now for something you could actually ship over a weekend: an MCP server that watches token consumption on your Azure OpenAI or Foundry deployment and warns you on Slack or email before the 429 lands in production. tl;dr Watch Azure Monitor metrics before the client hits the first 429. Start with a deterministic threshold plus a rising-trend check. Add agent reasoning later, after the telemetry and alert path prove they work. Why this is subtler than it looks The first reaction from anyone who’s never been bitten by a 429 is “easy, just measure usage and compare it to the quota.” The problem is that TPM (tokens per minute) and RPM (requests per minute) on Azure OpenAI are evaluated over short rolling windows, not a smooth average across the minute. That means you can blow the limit even while staying “under quota” in aggregate, simply because requests arrived in a burst instead of spread out. That’s why teams report 429s “even within the documented limit”: the problem isn’t total volume, it’s distribution over time. ...

You build a RAG pipeline, connect it to Azure OpenAI, and the answers come back… meh. Generic. Sometimes it ignores the context you sent. Sometimes it makes things up. The model is powerful, but input quality usually determines most of the result. Context engineering is the discipline of assembling that input so the model gives you what you actually need. It is not just “prompt engineering” with a fresher label. It is engineering: structure, constraints, and trade-offs. ...

Final post in the series. In the previous one, we built the 6-phase adoption framework. This one is the cheat sheet. You already speak infrastructure fluently. AI is not a foreign language. It is infrastructure with worse naming and more hype. This glossary maps each AI term to something you already understand. tl;dr This glossary maps AI jargon to infra concepts so you can reason about AI systems without switching mental models. Use it as a translation sheet for conversations about models, data, compute, serving, and ops. When a term drives architecture or cost, check the underlying docs before repeating exact numbers. How to use this Every entry has: the AI term, the infra analogy in parentheses, a concise definition, and when you’ll encounter it in your work. It is split into 6 categories so you can find things fast instead of pretending you remember all of it. ...

Three years ago, the question I heard most was: “what’s the best prompt?” Two years ago, it shifted to: “how do I do RAG?” Last year: “how do I build an agent?” This year, the conversation is different. People are asking how to transform an entire organization to operate with agents. Not a chatbot on the website. Dozens of agents embedded in business processes, with governance, observability, granular permissions. That progression tells a story, and we often discuss each phase as if it appeared out of nowhere. ...

The VP of Product walks into the daily standup: “I want the chatbot to answer questions about our internal documentation. We have 2,000 pages of runbooks, policies, and procedures. ChatGPT doesn’t know any of that.” The ML team says: “We’ll implement RAG.” Everyone nods. You get the job of provisioning the infrastructure. Before you start creating resources, you should know what RAG is actually doing under the hood. tl;dr RAG is search plus an LLM. The retrieval layer determines whether the answer is grounded or generic. The main moving parts are chunking, embeddings, vector storage, and hybrid search. In production, watch retrieval quality and pricing before you obsess over the model. The map for infra engineers RAG concept What it does Infra equivalent Retrieval Finds relevant documents Search engine query Augmentation Adds docs to the LLM prompt Build the request payload Generation LLM produces an answer using the context The model response Chunking Splits documents into smaller pieces Data partitioning, sharding Indexing pipeline Processes docs and generates embeddings ETL/data pipeline Hybrid search Combines semantic search + keyword search Using CDN + origin server together The problem RAG solves LLMs have two fundamental limitations: ...

Fourteenth post in the series. In the previous one, we used AI for our own infrastructure work. This time the scope is bigger: how to take an entire organization from “let’s use AI” to a governed platform that can survive contact with finance, security, and production support. tl;dr AI adoption fails when teams skip readiness, guardrails, and cost controls. A workable path is assessment, enablement, platform prep, controlled experimentation, production governance, and continuous review. Treat AI as an operating capability with budgets, runbooks, and policies from day 1. Best intentions, worst outcomes Your CTO walks into the all-hands and says: “We’re going all-in on AI.” The room buzzes. Teams start brainstorming use cases before the meeting ends. Within two weeks, Slack is full of threads about GPU availability. ...

Chapter 1: MCP and AI Agents 101 At some point in the last few months, someone on your team probably showed up talking about an “AI agent” or an “MCP server” and asked for cluster access, a deployment, or an explanation for the CISO. I wish I’d had a clean mental model before I touched any of this. That’s what this post is: no hype, and a real Azure example so this does not stay in slideware. ...

Thirteenth post in the series. In the previous one, we dealt with the incidents that wake you up at 2 AM. This time the angle flips: using AI to make the infrastructure work itself less miserable. tl;dr AI helps with summarizing, drafting, and finding patterns across noisy data. Do not hand it deterministic enforcement, compliance evidence, or unattended production actions. Flipping the perspective Over the past 12 posts, you’ve been building infra for AI: GPUs, clusters, pipelines, security, monitoring, cost management. You know how to keep the runway paved for data scientists. ...

Twelfth post in the series. In the previous one, we ran Azure OpenAI with HA and sane retry patterns. This one is for when the nice diagram meets real life. This post is organized as real-world failure scenarios. Each follows: Symptoms → Diagnosis → Root Cause → Resolution → Prevention. Read it once for pattern recognition. Then bookmark it. You will need it again. tl;dr Most late-night AI infra incidents come down to driver drift, memory pressure, scheduler mismatch, throttling, or cold starts. Start with the first check that rules out the biggest class of failure. Scenario 1: NVIDIA driver crash after kernel update Symptoms Monday morning. The ML team reports that all GPU workloads failed over the weekend. Nobody deployed anything. You SSH in: ...