As demand for business tokens continues to grow today, building applications from scratch is inefficient; instead, the better approach is to extend existing products and services – such as Microsoft 365 Copilot […]
Microsoft Foundry: Tool’s on-behalf-of (OBO) authentication in Toolbox
Here I describe how to use on-behalf-of (OBO) authentication with Microsoft Foundry toolbox and explain how it works.
Mastering Microsoft Entra Agent Identity Through the Protocol
In this post, we’ll explore how agent identities can be used at raw HTTP level. By learning these procedures, you can use agent identities for secure agents even in your own code, and manage not only no-code/low-code agents but your pro-code agents in one control plane.
Computer Use Agent (Considerations and Limitations) – toward Generalist AI Systems
Computer Use Agents (shortly, CUA) are gathering attentions, because it has the potential to perform any interactions in computer systems, not only searching.
In this post, I briefly discuss several topics to consider in CUA adoption.
Reinforcement Learning Explained for LLM Practitioners
The purpose of this post is to give you fundamental insights for reinforcement learning (RL) adoption in LLM’s training – such as, “what is RL for ?” and “how RL matters in LLM’s training ?” – with theoretical background.
Custom Metrics for Evaluation in LLM (Azure AI Studio)
In this post, I’ll show you how to use your own custom metrics (both statistical code metrics and LLM-measured prompt metrics) working with Azure AI Studio.
Improve accuracy for vision tasks with OCR assisted in multimodal models
Unfortunately the quality of text extraction in multimodal models (such as, GPT-4v, GPT-4o, Claude, etc) is not as well as today’s state-of-the-art (SOTA) OCR model. This post introduce how to improve text extraction quality in these models with the help of OCR models.
Improve AI Safety in LLM Apps – Prompt example, Red teaming, etc
In this post, I’ll briefly show you risk mitigation architecture for adversarial prompting and prompt’s example for safety.
Implement Model Parallelism in LLMs
In this post, I will break down the techniques for scaling of large model’s training in a step-by-step manner.
Implement Advanced Reasoning in Semantic Kernel
In this blog post, I’ll show you how to implement custom Planner for advanced reasoning in Semantic Kernel. Reasoning will be a key to create an intelligent autonomous agent.
tsmatz 