Chapter 3: From Script to Agent In the previous post, the Azure OpenAI quota watchdog was a script with if pct_of_tpm > 0.8: alert. That works, but it has the same flaw every blunt monitoring rule has: context does not exist. A batch job that predictably eats 90% of TPM for 10 minutes at month-end looks identical to an agent gone feral and burning tokens all afternoon. Both cross the threshold. Only one should wake somebody up. ...
Second post in the Azure postmortem series. In Part 1, we built the foundation: blameless culture, a reusable template, KQL-based evidence collection, and Logic Apps automation. Now we move from documentation to operations. A mature postmortem process should leave traces in the engineering system: linked work items, measurable trends, dashboards, and visible feedback into reliability practices such as SLOs, alert tuning, and chaos experiments. If a postmortem ends as a document nobody operationalizes, the process failed. ...
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. ...