A tiny config tweak lets Dovetail run Mike against their own Azure-hosted GPT deployments instead of calling OpenAI directly.
geoffdavies-dt/mike
A lightly-customized Mike fork by geoffdavies-dt, wired up to run on Azure-hosted OpenAI deployments instead of the default OpenAI service.
This fork of Mike comes from geoffdavies-dt, and so far the story is a focused one: making Mike comfortable in an Azure OpenAI environment. If your organisation already has GPT models deployed through Azure - common in regulated industries and enterprise legal shops - this fork makes it straightforward to point Mike at that deployment rather than the public OpenAI API.
The handle suggests a Dovetail connection, and the work to date reads like a practical enablement effort: get Mike running against the AI infrastructure the team already has, rather than standing up a parallel one.
Beyond that single thread, there isn't much to report yet. It's a small, targeted divergence - the kind of fork that exists to unblock a specific deployment rather than to chart a new product direction.
What's in it
- Azure OpenAI support Point Mike at your own Azure-hosted GPT deployment instead of the default OpenAI service - useful for teams whose AI stack already lives in Azure.
Direction
integrationinfrastructure
Activity
Threads of work (detailed view)
geoffdavies-dt wires Mike up to Azure OpenAI
A tiny config tweak lets Dovetail run Mike against their own Azure-hosted GPT deployments instead of calling OpenAI directly.