Semantic Kernel: Building Production AI Agents
After building agents with LangChain, AutoGen, and custom solutions, I finally gave Semantic Kernel a proper try. Here's what I learned building production…
58 articles
After building agents with LangChain, AutoGen, and custom solutions, I finally gave Semantic Kernel a proper try. Here's what I learned building production…
Ignite 2025 promises to be a pivotal event for enterprise AI adoption. The convergence of Azure AI, Fabric, and Copilot technologies creates opportunities…
Semantic Kernel is an SDK that integrates Large Language Models (LLMs) with conventional programming languages. Version 2.x introduces a more streamlined…
Semantic Kernel v2 brings enterprise-grade patterns to AI development, making it easier to build maintainable, testable AI applications.
Start with non-critical systems to validate changes before production deployment.
Semantic Kernel 2.0 provides enterprise-ready AI orchestration with improved developer experience.
Full agentic coding experience directly in VS. These tools transform the development experience with AI assistance at every step.
The Copilot Stack makes it straightforward to build AI-powered applications across the Microsoft ecosystem.
The new orchestration engine supports complex multi-agent workflows with built-in state management.
New agent capabilities with improved reasoning Enhanced model routing and orchestration Expanded model catalog with latest versions Simplified deployment…
Power BI Copilot makes data analysis accessible to everyone through natural language.
Phi-3 enables powerful AI capabilities entirely on-device with no cloud dependency.
Windows AI brings powerful on-device intelligence to every application.
Custom Copilot plugins bring your business data into the AI conversation.
Build 2025 will likely be the most AI-focused Build ever. Prepare to learn and adapt quickly.
GraphRAG excels at complex questions requiring synthesis across multiple documents.
Semantic Kernel provides a clean abstraction for building AI applications with plugins and natural language orchestration.
Phi models represent the future of practical AI - powerful enough for real tasks, small enough to deploy anywhere. Start with Phi-3-mini for most use cases…
Windows AI brings intelligence to the edge. For data professionals, this means faster, more private analytics on your desktop.
The next generation of Copilot will transform how we build software. Start exploring the current capabilities to be ready for what's coming.
Phi-3 uses high-quality training data (textbooks, filtered web content) rather than raw internet scale.
NPU wins on efficiency, crucial for battery life.
I've used AutoGen to prototype multi-agent workflows that handle planning, tool use, and execution. This practical introduction focuses on the patterns that…
Responsible AI isn't merely compliance box-ticking; it's product design that protects people and preserves trust. In practice I've found that pairing…
Microsoft's 2023 felt like an all-in moment: platform bets, product integration, and commercial commitments that reshaped the enterprise AI landscape. From…
Azure ML continues to evolve as a comprehensive platform for both traditional ML and GenAI workloads. Tomorrow, I will cover Responsible AI improvements in…
Azure AI Studio provides a comprehensive environment for building, testing, and deploying AI applications. Tomorrow, I will cover Prompt Flow in more detail.
Azure OpenAI is becoming the enterprise-grade platform for building generative AI applications. Tomorrow, I will cover building plugins for ChatGPT.
Microsoft Build 2023 is scheduled for May 23–25, 2023, in Seattle—and based on the product roadmap signals Microsoft had been sending through Ignite 2022…
Edge Copilot brings AI assistance to every webpage, transforming passive browsing into active learning and productivity.
Bing Chat represents the future of search: not just finding links, but synthesizing answers from the web with AI understanding.
Security Copilot addresses the security skills gap by augmenting analysts with AI-powered investigation and response capabilities.
Dynamics 365 Copilot transforms business applications from data systems into intelligent assistants that augment human decision-making.
Power Platform Copilot makes citizen development more accessible than ever. Combined with proper governance, it enables rapid digital transformation.
Microsoft 365 Copilot will fundamentally change how knowledge workers interact with productivity tools. Organizations should start preparing now.
Microsoft's strategy is clear: every product gets an AI assistant. These aren't separate products but integrated capabilities powered by Azure OpenAI.
GPT 4 integration in Azure OpenAI More neural voice options Enhanced document understanding Improved multi modal capabilities What's New in Azure AI Azure…
Define AI functions using natural language prompts: Create reusable prompts: Add Python functions as skills: Combine functions into pipelines: Store and…
The biggest story of the year bringing GPT 3, Codex, and DALL E to enterprise: General availability expanded New models including GPT 3.5 Content filtering…
Microsoft's framework provides a solid foundation: 1. Fairness : AI should treat all people fairly 2. Reliability & Safety : AI should perform reliably and…
Power Virtual Agents now can generate responses using GPT models: Topics now support more complex logic: Create complex workflows triggered by chatbot…
Bot Framework Composer now supports more advanced dialog patterns: Azure Bot Service provides a comprehensive platform for building conversational AI. With…
.NET 7 continues the tradition of making .NET faster and more cloud-native with each release. Here's a preview of the key improvements we'll see at GA.
Cloud based developer workstations with instant provisioning: Pre configured development environments Self service portal for developers Cost management…
Arc-enabled data services brought Azure SQL and PostgreSQL Hyperscale to any infrastructure, a game-changer for hybrid scenarios.
Ignite Fall 2021 was dense with announcements—Azure Container Apps, Chaos Studio, Load Testing, Service Connector, Azure Developer CLI, Arc-enabled data…
Responsible AI isn't a one-time checkbox - it's an ongoing commitment that must be embedded in every stage of the AI lifecycle. Microsoft's tools and…
Power BI Deployment Pipelines transform how organizations manage their analytics lifecycle. By bringing CI/CD practices to BI, teams can deliver insights…
Premium capacities offer: Dedicated compute : No sharing with other tenants Larger datasets : Up to 400GB per dataset Paginated reports : Enterprise…
Power Fx makes programming accessible to everyone who knows Excel. As it expands across the Power Platform and beyond, expect to see it become a standard…
Managed Environments represent a significant maturation of Power Platform governance. For enterprises that want to enable citizen development while…
Minimal APIs in ASP.NET Core 6 are the answer to the question "why do I need controllers, action filters, model binding, and routing tables just to expose a…
No Startup.cs, no Main method, no namespace declarations. This is possible thanks to C# 10's global usings and file-scoped namespaces.
Microsoft Ignite Fall 2021 brought a wave of announcements across Azure. While hybrid work and Microsoft Teams dominated the headlines, the data and AI…
The headline announcement for me was the integration of GPT-3 into Power Apps. You can now describe what you want in plain English, and GPT-3 generates the…
Applied AI Services are Microsoft's answer to "I need AI in this process, but I don't want to wire up five Cognitive Services and build the integration…
Dataflows are collections of entities (tables) that are created and managed in workspaces in the Power BI service. They allow you to: Connect to various…
Microsoft Ignite 2020 was different this year - a fully virtual 48-hour event instead of the usual 5-day in-person conference. Despite the condensed format…