simkjels wires Mike up to Azure OpenAI

A third AI engine joins Claude and Gemini - this one running inside Microsoft's cloud.

integrationinfrastructure

simkjels has added Azure OpenAI as a third model provider alongside the Claude and Gemini options Mike already shipped with. For legal teams, the appeal is straightforward: many firms and in-house departments already have their data, identity, and compliance posture sitting inside Microsoft Azure, and routing AI calls through an Azure-hosted OpenAI deployment keeps everything inside that perimeter rather than sending prompts to a separate vendor.

The work went through a few iterations. An early version used Microsoft's older, Azure-specific connection style; simkjels reworked it to use Azure's newer endpoint that behaves just like the standard OpenAI one, which is simpler and likely to age better. A small follow-up fixed a bug where the new provider didn't actually show up in the model picker - the kind of plumbing detail that's easy to miss until a user tries to switch models.

So what Useful for any legal-tech team whose clients require their AI traffic to stay inside an existing Azure tenancy rather than going to a third party.

View this fork on GitHub →

Spotted something wrong? Or know the PR text has fresher detail than the writeup above?

Commits in this thread

3 commits from simkjels/mike, oldest first. Source extracted verbatim from the harvested git log.

SHA Subject Author Date
6de8751c Add Azure Foundry model support Simen Kjelsrud 2026-05-04 ↗ GitHub
832920a9 Use Azure OpenAI v1 endpoint flow Simen Kjelsrud 2026-05-04 ↗ GitHub
ffad9905 Fix Azure model picker env reads Simen Kjelsrud 2026-05-04 ↗ GitHub

Capture this thread into my fork

Download a single Markdown prompt that tells Claude how to port every commit above into your working tree — adapting paths and structure to match your repo. Run it via claude -p < capture-thread-94.md from inside the repo you want the changes in.

⬇ Download capture-thread-94.md