Build your own CoPilot

Room 4
15:00 - 16:00

Talk (60 min)

AI CoPilots are all the rage - but none quite offer that personalised butler service SciFi told us we might one day have.

To understand what it takes to train a CoPilot, we will see how training a model works under-the-hood; discuss the importance of quality training data to craft a truly powerful and personalised experience, and safety or security concerns to consider when training a model on a public service.

Moving beyond the (chat) box, we will leverage Azure's OpenAI Service and Semantic Kernel in .NET to create a custom AI CoPilot for internal applications or data. We will see how to train our own custom Codex model, for generating code and commands to perform bespoke tasks against a non-public API, plus some innovative ways to glue this together with a nice user experience.

You will leave feeling excited about the power of custom CoPilots, and armed with the knowledge to build your own!

Callum Whyte

Callum Whyte is a x4 Microsoft MVP and x6 Umbraco MVP specialising in building robust scalable solutions on Azure and the .NET stack, as well as websites with the open-source Umbraco CMS.

Away from his desk you can find him organising community events; from local meetups and hackathons, to global conferences and roadshows. He’s an active contributor to open source projects, a regular speaker at events all over the world, as well as co-host of a weekly YouTube series “UmbraCoffee”!