Build a React chat interface that consumes Microsoft Foundry Responses streams, safely parses SSE events, appends text deltas, and suppresses stale output after cancellation or sign-out.
Learn how a BFF uses signed continuation tokens to bind Microsoft Foundry Responses conversations to authenticated users and prevent unauthorized reuse of response IDs.
Learn how a Backend for Frontend keeps Azure Foundry credentials out of a React app by validating application JWTs and acquiring server-owned Azure tokens.
Keeping conversational memory inside a single session is what makes GraphRAG answers actionable, because every turn depends on the classifier understanding the history it already routed. The earlier installments supplied those building blocks—routing patterns that coordinate sequential, concurrent, and handoff workflows; evaluation gates that locked in TaskAdherence 80% and IntentResolution 100%; and the Azure AI Foundry model router that selects Balanced, Cost, or Quality modes per request Use model router with Foundry agents. This part finishes the arc by layering checkpoint-aware session storage on top, letting Microsoft 365 Agents Playground resume the same conversation while the router contract stays intact.
Build deterministic, observable, and resilient prompt-routed workflows with Azure AI Foundry Model Router and Microsoft Agent Framework for robust orchestration.
Ensure agent reliability with Azure AI Evaluation SDK & Foundry. Measure quality, safety, & traceability for production GraphRAG agents. Detect regressions early!
Explore GraphRAG workflows: chain, parallelize, and route agents for complex queries. Learn prompt engineering, MCP concurrency, and optimize search strategy.
Build an intelligent conversational agent from your GraphRAG MCP server using Microsoft Agent Framework! Automate knowledge graph searches with GPT-4o and streamline tool routing.
Expose your GraphRAG knowledge graph as an MCP server using FastMCP! Enable AI agents to discover & query it automatically. Build a universal AI tool connector.
Unlock AI's potential with GraphRAG! Build knowledge graphs using Microsoft GraphRAG and Azure OpenAI to answer complex questions beyond standard RAG. Learn how!
Ace your tech interviews with AI Tech Interview! Practice communication skills using Next.js, Azure AI, and voice. Get instant, detailed feedback. Land your dream job!
In this article, we'll transform our agent into a real-time streaming experience, similar to ChatGPT. Users will see text appearing progressively as the AI generates it, creating a more engaging and responsive user experience.
Modernize your AI Task Agent! Learn to separate .NET backend from a Next.js frontend with Azure Static Web Apps. Boost UX, scalability, and development speed.
Master AI agent observability with .NET Aspire, Application Insights, and OpenTelemetry. Monitor performance, debug issues, and ensure production readiness. From local dev to Azure!
Secure your AI Task Agent with Azure AI Content Safety! This article details how to implement a two-layer defense against prompt injection attacks and harmful content. Learn to protect your AI applications with prompt shields and content moderation, ensuring responsible AI development and user trust. Optimize performance with parallel execution and configurable thresholds for hate speech, violence, sexual content, and self-harm.
Discover how to build intelligent AI agents using the Microsoft Agentic AI Framework and Azure OpenAI. This guide covers setting up Azure resources, deploying models like gpt-4o-mini, creating function tools, and building production-ready web applications. Learn to leverage autonomous function calling and tool orchestration for adaptive, scalable AI solutions, reducing complexity and enhancing user experiences.
Discover how the Azure AI Speech Pronunciation Assessment enhances language learning by providing real-time feedback on pronunciation accuracy, fluency, and intonation.
Azure AI Video Indexer (VI) is a cloud-based service that helps businesses and developers extract valuable insights from videos using artificial intelligence (AI). This tool can automatically analyze video content, recognize faces, detect emotions, extract speech-to-text transcriptions, and even generate summaries.
Azure AI Text-to-Speech Avatar is a tool designed to create digital avatars that can speak in a remarkably human-like manner. This innovation is changing the way we interact with AI, making virtual assistants, automated customer service, and even gaming characters more lifelike than ever.
This guide covers integrating Azure Cognitive Services for seamless language translation, enabling real-time multilingual support. Discover how to use AI-powered translation for efficient and scalable applications.
This article explores how we built a demo application using Azure AI Content Safety to detect harmful content like hate speech, sexual content, and violence within a social media platform. We combined the power of an Angular frontend and a .NET backend API to create a system that analyzes text and images for potential harm
Cut ML inference costs by 99% using AWS Lambda and ONNX! This guide details serverless deployment, model comparison, dark mode, and engineering lessons learned. Optimize your ML workflow!
Build a serverless AutoML platform on AWS for just $10-25/month! Train models by uploading CSVs. A cost-effective alternative to SageMaker endpoints.
Amazon Bedrock enables developers to generate images and more using foundation models. This guide walks through implementing an API and UI with Node.js to generate images, leveraging Amazon Titan Image Generator and AWS credentials.
Automatic picture analysis is used by image moderation systems to find and mark potentially offensive or dangerous content. This post will discuss how to use AWS Rekognition, Nest.js, and React to create a reliable image moderation system.Conclusion
DevSocialUpcoming · 3rd editionAI Agents ConferenceNov 23–27, 2026Live onlineMembers only17days leftRegisterMembers onlyWrite an article and earn +1,000 SHARP when it is approved.
Write an article