Thomas Thornton Blog

Part 1 covered the consumption side of an AI gateway: rate limits, token quotas, usage attribution and the telemetry needed to understand them.

Putting APIM in front of a model endpoint does not give you useful runtime governance on its own.

I blogged recently about building an Azure AI Landing Zone without slowing teams down and the split I use between resource governance and runtime governance.

Deploying a model endpoint in Microsoft Foundry or Azure OpenAI is easy enough.

AI-assisted engineering is easy to measure badly and the usual numbers appear first: active users, accepted completions, generated lines of code, tokens consumed, agent sessions and pull requests opened.

I have created a broader Draw.io MCP Diagramming Agent Skill for generating clear, structured and editable diagrams across a range of use cases, including cloud architecture, network topology, CI/CD pipelines, Kubernetes platforms, event-driven systems, C…

Agent skills are a practical way to capture reusable engineering judgement for AI coding agents, whether that judgement relates to reviewing Terraform, creating architecture diagrams, writing API Management policies, checking pull requests or following a…

I’ve been using HolmesGPT lately and wanted to put together a quick demo using Azure AI Foundry.

A , , custom instruction file, or MCP configuration can affect how an agent reads a repository, calls tools, writes code, updates infrastructure, or explains a design.

The previous post made the case that AI-assisted engineering is becoming a platform concern.