Blog posts

As AI adoption continues to accelerate, organizations are increasingly relying on Large Language Models (LLMs) to power intelligent applications—from chatbots to copilots to knowledge assistants. But building an AI system is just the beginning. One of the most critical, yet often overlooked, aspects of the AI development lifecycle is evaluation: understanding how well your system performs, identifying failure modes, and making informed decisions about models, prompts, and architecture.

As you have seen in my previous articles, we are doing a ton of work around Azure OpenAI. When dealing with OpenAI, I truly recommend the use of the open source library Semantic Kernel (https://github.com/microsoft/semantic-kernel).

In the past few months, I have been fortunate to work on Atlas AI. This has provided me with deeper insight into AI token counter libraries and I thought I would share some of my learnings. 

Recently, we had the need to deny External (also referred to as Guest) users to consume some endpoints of our Atlas API. You should be aware that if your Tenant has enabled external users, an external user can get a valid token and call your AAD secured API. This might or might not be what you want.

As mentioned in my previous article, we have integrated ChatGPT in our Atlas product. This was both challenging and fun. The OpenAI API is well documented, so is the Azure OpenAI service. However, one of the things that is not completely documented, is the Stream option. This allows you to call the API and get the response as a stream of data, so you are getting data from the very first second, and you don´t have to wait for the entire response. Note that depending on your request, ChatGPT can take some seconds until you get the response, so from a UX point of view, it is potentially a better experience if you start showing data while the response is fully completed.

Unless you are in a desert island with no internet connection, you have heard about ChatGPT. In its own words (and I really mean it, as I have asked ChatGPT for a short summary about it):

In this follow-up blog to using Microsoft Kiota to create a client for any API described using OpenAPI, Luis Mañez looks at using a Typescript client in a SharePoint framework solution.

Hi. I’m Luis Mañez, Atlas Chief Architect, and in this article, I am going to tell you about a new tool created by Microsoft, called Kiota. Kiota allows you to create a client for any API described using OpenApi.

Would it not be cool to engage your Modern Workplace users with content appearing like in your favourite social network? In my latest community sample, I built an SPFx webpart to do so. Here is how I did it, but first, this is how it looks: