Cargo Load optimisation (powered by Gemini 3 Pro), to arrange small, medium and large parcels within a cargo van, with an interactive 3D visualisation.

Jupyter notebooks to ramp up (Level 200) and build practical knowledge of Microsoft Semantic Kernel's Python SDK.

Practical implementation of Azure AI Foundry agent with Azure Function as its tool.

Demo of "encrypted reasoning" capabilities, when using Responses API in a stateless mode.

Practical implementation of Azure AI Foundry agent with Logic Apps as its tool, using function calling or OpenAPI schema (with both SAS token and Managed Identity's OAuth options).

Demo on the use of Azure AI Foundry agent service's Deep Research tool for in-depth, multi-step research on public Web data.

Attempts to decrypt the famous CIA's Kryptos sculpture's remaining K4 message, before its solution is auctioned in November 2025.

Files upload into Azure AI Foundry's built-in Vector Store and analysis of requests submission and completion rates.

Demo on how to retrieve raw outputs from Azure AI Foundry agent service's tool calls, for the data flow analysis and debugging.

Practical Jupyter notebook to demo the analysis of Entra ID tokens generated for Azure AI Foundry resource scope.

Practical Jupyter notebook to demo the use of REST APIs with the Azure AI Foundry's Agents Service

Demo on how to use the Code Interpreter tool in Azure AI Foundry (Azure OpenAI) via Responses API and then extract generated files.

Hackster Learning Series about AI Agentic protocols (MCP, A2A, ACP) with practical code examples.

MCP Client and Server apps to demo integration of Azure OpenAI-based AI agent with a Data Warehouse, exposed through GraphQL in Microsoft Fabric.

Fine-tuning Mistral-7B model in Azure AI Foundry.

Web-UI wrapper for the Microsoft Research's Biomolecular Emulator (BioEmu) AI model to predict 3D protein structures.

Practical demo of image editing with Azure OpenAI's GPT-image-1 via direct API calls and Azure Entra ID auths.

BGE Reranker v2 m3 demo with Hugging Face transformers for local and Azure cloud use.

Fine-tuning Mistral-7B model in Azure Machine Learning studio.

MLOps with model registry across Azure Machine Learning workspaces.

Bicep template to deploy DeepSeek R1 model to a serverless (realtime) endpoint in Azure Machine Learning workspace.

ARM template to provision an Azure OpenAI resource and specific GPT model / deployment type, e.g. GlobalBatch.

Notebooks to demo the use of Azure AI Python SDK / LangChain with DeepSeek R1 reasoning model in Azure AI Foundry.