Browse & Filter All Links
Use the filters below to find links across all categories by solution area, content type, audience, maturity, and more.
TIP
This page aggregates all links from every category in the library. Use the tag filters to narrow down to exactly what you need, or type a keyword to search titles and descriptions.
Filter by tags (116 of 116 links)
Solution Area
Content Type
Audience
Shareability
Maturity
Foundational explainer on AI agents in Microsoft Foundry — what agents are, core components (model, instructions, tools), how they reason, plan, and act autonomously. Covers the agent runtime, tool integration, and multi-agent workflows.
Microsoft's blog on the agentic AI paradigm — common use cases, design patterns (reflection, tool use, planning, multi-agent collaboration), and how Azure enables enterprise-scale agent solutions.
Microsoft Learn training module covering AI agent fundamentals — what agents are, how they work, when to use them, and the Azure services that support agent development.
The Azure Architecture Center hub for AI workloads — baseline reference architectures, design patterns (RAG, agent orchestration, MLOps), and best practices across the AI solution lifecycle.
Best practices for integrating AI code assistants into daily development workflows — prompt engineering, context management, and team adoption patterns.
How to move beyond brittle Playwright selectors to self-healing, agent-driven UI tests using GitHub Copilot and MCP — intelligent page analysis, dynamic fallbacks, and adaptive coverage.
A practical model for verifying high-volume agent output without overwhelming domain experts. It combines human review, AI checks, and deterministic tools into layered quality gates for modernization and code-generation work.
A curated library of skills for Dynamics 365 delivery teams. It covers a broad range of delivery scenarios — the AI First delivery skills specifically are located in the **D365 Configuration** section.
Official GitHub guide on running Copilot CLI inside Actions workflows — authentication, example YAML, and use cases like daily summaries, PR triage, and AI-assisted CI/CD tasks.
Azure DevOps platform overview — CI/CD pipelines, repos, boards, and test plans. A foundation for integrating AI-driven workflows into your delivery pipeline.
Agent orchestration patterns from Azure Architecture Center — from single-agent to multi-agent systems. Covers sequential, concurrent, group chat, handoff, and magentic patterns for cross-solution agentic implementations.
Microsoft's open-source multi-agent reference architecture — orchestrator patterns, agent registry, memory management, classifier integration, and MCP protocol support.
Microsoft Learn architecture guidance connecting Copilot Studio project planning, implementation, governance, improvement, and extension to reference architectures and practical solution ideas.
Define a clear, business‑aligned architecture strategy for Copilot Studio by mapping core agent capabilities, integrations, scalability needs, security requirements, lifecycle processes, and operational considerations.
GitHub repository with foundational design patterns for agentic AI on Azure — RAG agent, code generation agent, multi-domain agent patterns with implementation guidance and reference architectures.
Explains how the previously separate Microsoft 365 and Entra agent registries converge into Microsoft Agent 365, and how discovery and inventory relate to Entra Agent ID for identity and access. Essential for designing governable multi-agent estates.
Explains how Foundry agents connect to the Agent 365 control plane through registry sync, Entra Agent ID, governance, observability, and lifecycle management. It also identifies which agent types support registry, autopilot publishing, and activity collection.
Build 2026 guidance on grounding agents in enterprise data using Microsoft Fabric (Fabric IQ ontology) and Azure databases for retrieval and context. Shows partners how to ground agents in governed enterprise data, a common requirement for production RAG and agent scenarios.
Compare declarative agents that extend Microsoft 365 Copilot with custom engine agents built around a separately managed runtime. Helps solution architects and developers choose an agent approach that fits their control and integration needs.
Official Python SDK samples for Azure OpenAI — chat completions, embeddings, function calling, and the Responses API with both API key and Entra ID authentication.
Open-source SDK for building AI agents and integrating LLMs into applications. Supports C#, Python, and Java. Being unified with AutoGen into the Microsoft Agent Framework.
Official overview of Microsoft's framework for building, orchestrating, and deploying agents and multi-agent workflows in Python and .NET. It is the successor to Semantic Kernel and AutoGen for new Microsoft agent projects.
Concrete Python and .NET guidance for moving agents from Semantic Kernel to Microsoft Agent Framework. It maps namespace, session, invocation, tool registration, middleware, and credential changes with side-by-side code.
Microsoft Copilot Studio guidance for integrating an agent into web or native mobile apps with the Microsoft 365 Agents SDK. Useful for partners embedding conversational agents into custom application experiences.
Overview of the SDKs and endpoints available for building on Microsoft Foundry, including Microsoft Agent Framework for C#/.NET and Python, hosted agents, and how to choose the right client library for a project. Useful starting point for developers deciding which Foundry SDK and endpoint to use.
How to use the Azure OpenAI Responses API — the recommended API for new projects. Covers model inference, streaming, tool use, and integration with Microsoft Foundry.
Guidance for connecting Foundry IQ knowledge bases to Microsoft Foundry Agent Service, including agentic retrieval configuration and the associated REST API versions. Use it to ground agents in managed enterprise knowledge.
End-to-end Azure AI Foundry agentic AI lab for .NET developers — multi-agent architecture, agent service integration, tool binding, memory management, and evaluation.
Starter kit that rapidly deploys an Azure OpenAI instance with Python examples — Responses API, secure authentication, and production-ready patterns.
Comprehensive evaluation suite built on Microsoft Agent Framework (MAF) v1.0.0 for a Financial Advisor agent. Covers 7 evaluation categories — local, Azure AI Foundry cloud, multi-turn, traces, benchmarks, safety, and batch — with runnable Python scripts and step-by-step guidance for each pattern.
Web-based portal for managing AI projects — deploy models, build and test agents, run evaluations, monitor performance, and manage governance from a single pane of glass.
Python developer guide for Azure AI — SDK setup, authentication, building with Foundry Tools (language, vision, speech, document intelligence), and integrating AI services into applications.
Hands-on workshop for building a code-first agent with Azure AI Foundry Agent Service. Covers project setup, agent creation, tool binding, RAG integration, and deployment.
Comprehensive implementation guide for Microsoft Copilot Studio — covers architecture, development, security (slide 88+), monitoring, and governance for enterprise agent deployments.
Step-by-step guidance for deploying containerized agents to Foundry Agent Service with Azure Developer CLI, language SDKs, or the REST API. Helps development teams choose an automated or programmatic deployment approach.
Step-by-step guidance for configuring Anthropic's Claude Code to use Microsoft Foundry models, enabling developers to use its agentic coding workflows with Foundry-hosted model deployments.
Agent Skills package instructions, scripts, and resources that agents can discover and load when needed. The guide explains the open format and how to build reusable capabilities for Microsoft Agent Framework.
Explains how to connect a Microsoft Foundry agent to a remote Agent2Agent endpoint. Useful for partners building interoperable multi-agent solutions with standardized communication and authentication.
Explains how Fabric data agents answer natural-language questions over governed OneLake sources, including lakehouses, warehouses, and semantic models. Use it to plan configuration and permission-aware analytics experiences.
Shows how to configure a stable agent endpoint, select the active version, and share the agent with consumers. Useful when preparing Foundry agents for reliable downstream integration and governed access.
Learn how to use Agent Registry in the Microsoft 365 admin center to manage, govern, and audit agents across your organization.
Step-by-step guidance for deploying Anthropic's Claude models in Microsoft Foundry and calling them from your applications. Covers deployment options, authentication, and the supported APIs so teams can integrate Claude alongside other Foundry-hosted models.
Microsoft's AI learning hub — curated learning paths, certifications, and hands-on modules covering AI fundamentals, Azure AI services, generative AI, and responsible AI.
Official Microsoft study guide for the AB-100 certification, outlining the skills measured for designing agentic AI business solutions — agent design and testing strategies, validation criteria for custom AI models, Copilot prompt practices, and ALM for AI-powered solutions across Dynamics 365 and Copilot Studio.
Webinar series from Microsoft's Customer Architecture Team (CAT) covering real-world AI implementation patterns, architecture decisions, and lessons learned from production deployments.
How Microsoft Edge for Business combines AI features with enterprise controls for secure browsing and data protection.
Technical session covering platform, application, and agent security as one end-to-end architecture.
Practical guidance for building secure AI agents with Microsoft identity, threat protection, posture management, and governance capabilities.
Deep dive into using Microsoft Entra to discover, manage, govern, and protect agent identities and their access to resources.
Simulated partner demo experience — walk through AI risk posture assessment scenarios in a guided Microsoft demo environment. Requires CDX access.
Simulated partner demo experience — walk through cloud AI platform protection scenarios in a guided Microsoft demo environment. Requires CDX access.
Simulated partner demo experience — walk through AI agent security risk prevention scenarios in a guided Microsoft demo environment. Requires CDX access.
Simulated partner demo experience — walk through AI security posture improvement scenarios in a guided Microsoft demo environment. Requires CDX access.
Build 2026 roundup of Microsoft Foundry updates: Hosted Agents GA, Agent Framework 1.0, Toolboxes, advanced memory, evaluation, and distribution to Teams and Microsoft 365.
Official developer recap of Build 2026: the system-around-AI vision and the biggest launches across GitHub, Microsoft IQ, Foundry, Agent 365, and Security, plus top sessions.
Latest release notes for Microsoft Foundry — new features, model catalog updates, agent evaluation improvements, SDK enhancements, and governance capabilities.
Tracks Microsoft Entra releases and documentation changes, including Agent ID, identity governance, Conditional Access, and workload identity capabilities relevant to secure agent deployments.
Evergreen release notes for Microsoft Copilot Studio, covering new agent authoring, orchestration, knowledge, testing, governance, and deployment capabilities.
Discover Claude models in Microsoft Foundry. Compare available models, capabilities, hosting options, and supported regions to choose the right model.
End-to-end architecture for enterprise multi-agent workflow automation — Azure Container Apps for agent hosting, Semantic Kernel orchestration, Cosmos DB for state, and Foundry for AI reasoning.
Microsoft Developer blog on designing multi-agent intelligence — transitioning from monolithic to distributed agent systems, orchestration strategies, domain specialization, and enterprise governance.
Microsoft's end-to-end security model for AI agents — covers Agent 365, Entra, Defender, and Purview integration. Based on RSAC 2026 keynote content covering identity, posture management, threat protection, and data governance for autonomous agents.
Maps each OWASP Agentic AI Top 10 risk to specific mitigations across Agent 365, Copilot Studio, Entra, Defender, and Purview. Use this to build your threat mitigation strategy for agent deployments.
Deep technical guidance on defense-in-depth for autonomous agents — model layer, safety systems, and runtime controls. Grounded in Zero Trust principles for securing fully autonomous AI workloads.
Explains agent identity blueprints, runtime identities, OAuth token exchange, RBAC, and downstream tool authentication in Microsoft Foundry. Use it to design least-privilege access without embedding credentials in agent code or prompts.
Practical guidance for treating each agent as a lifecycle-managed principal with explicit roles, tightly scoped permissions, and controlled tool access. The scenarios show how quiet permission growth and combined tool access can create risks that individual integrations hide.
Microsoft Incident Response explains an MCP tool-poisoning attack against an agent with read-write access. It includes a practical playbook for detecting, containing, and preventing malicious tool metadata from triggering unauthorized actions.
Explains how persistent memory changes the agent threat model through delayed execution, memory poisoning, and reduced user awareness. It maps these risks to controls for memory creation, storage, observability, and user management.
Technical analysis of an AutoGen Studio exploit chain where untrusted web content reached an unauthenticated local MCP WebSocket and spawned processes. The broader design lesson applies to any browsing agent that can communicate with privileged localhost services.
Detailed investigation of the compromise of more than 140 packages in the Mastra agent framework ecosystem. It covers the malicious postinstall chain, affected developer and CI environments, detection guidance, and package-supply-chain controls.
How to build secure and governable AI agents using Microsoft Foundry — covers identity, access control, monitoring, and compliance patterns for agent development.
Security chapter of Microsoft's multi-agent reference architecture — covers agent identity, inter-agent trust, data boundaries, and threat models for multi-agent systems.
Explains how Microsoft Foundry hosted agents provide managed deployment and operation of AI agents, including the platform capabilities and considerations for secure agent workloads.
Reference for the permissions required to create, deploy, and use hosted agents in Microsoft Foundry. Use it to assign least-privilege roles to deployment users and agent identities.
Official product documentation for Microsoft Agent 365, the enterprise control plane for registering, observing, governing, and securing AI agents (Microsoft, open-source, and third-party) at scale.
Microsoft Agent 365 admin guidance for protecting agent identities with Microsoft Entra — applying Conditional Access, lifecycle controls, and Zero Trust to agent identities governed through Agent 365.
Microsoft's Cloud Adoption Framework guidance for AI governance — roles, responsibilities, risk management, policy enforcement, compliance monitoring, and alignment with NIST AI RMF.
Azure AI Content Safety service — detect and filter harmful content in text and images. Covers prompt shields, groundedness detection, protected material detection, custom categories, and content moderation APIs.
Cloud Adoption Framework reference architecture for agent governance — covers data, identity, observability, security, and development layers for enterprise-wide agent management.
Deployment model for securing and governing M365 Copilot agents using Microsoft Purview — covers data classification, DLP, and compliance controls for agent workloads.
How to detect and prevent data leakage to unauthorized AI services using Microsoft Purview — DLP policies, endpoint controls, and monitoring to protect sensitive data from shadow AI usage.
Official documentation on security and governance controls for Microsoft Copilot Studio — authentication, DLP, environment management, and audit logging for agent deployments.
A framework for assessing and advancing an organization's adoption of AI agents, with repeatable practices for scaling agentic AI securely, measurably, and into everyday work.
Azure governance for AI platform services — policy enforcement, model governance, risk detection, Entra Agent ID integration, and operational standards for AI environments.
Cloud Adoption Framework guidance for establishing responsible AI policies across development, deployment, and operations. It provides a structured approach to governance, risk assessment, and accountability for AI agents.
Comprehensive security best practices for Azure AI services — covers authentication, network isolation, data protection, and monitoring for AI workloads.
Landing page for Microsoft's Security for AI documentation — covers threat protection, posture management, data security, and governance for AI workloads.
Microsoft's central hub for securing and governing AI — links to guidance on threat protection, posture management, data security, and compliance across AI workloads.
Latest announcements and updates on Microsoft's Security for AI capabilities — new features, product updates, and roadmap for securing AI workloads.
Official documentation for Copilot Studio — build, test, and deploy conversational AI agents with a low-code experience. Covers agent creation, topics, actions, plugins, deployment, and governance.
Step-by-step quickstart for creating your first Copilot Studio agent — topics, entities, actions, testing, and publishing.
Guidance documentation covering design patterns, performance optimization, security, responsible AI, and enterprise deployment best practices for Copilot Studio agents.
Explains agent skills in Copilot Studio — portable packages of instructions, scripts, and resources that give agents specialized capabilities and domain expertise, and how to author, package, and reuse them across agents.
Discover Power CAT Copilot Agent Kit, a comprehensive set of tools to develop, govern, test, and optimize custom agents using AI and large language models.
Explains agents powered by the GitHub Copilot harness in Microsoft Copilot Studio — a redesigned authoring and runtime environment that replaces topic-and-flow authoring with a natural-language-first, unified single-surface experience and an enhanced orchestration model for improved response quality and reasoning.
Copilot Studio's multi-agent orchestration capabilities announced at Build 2025 — agent delegation, handoff, shared context, and how Copilot Studio connects with Microsoft Foundry for advanced reasoning.
Introduces closed-loop learning for agents connected to the Power Apps MCP server — user corrections made through the Agent feed are persisted as structured memory and automatically applied on future runs, with patterns consolidating into organization-wide learning over time. Enables partners to build enterprise agents that continuously improve without data pipelines or custom training infrastructure.
Power Platform blog announcement for Dataverse Admin Skills public preview. Shows how partners can expose Dataverse administrative operations as agent skills in GitHub Copilot or Claude Code, with guardrails for multi-environment settings, bulk delete, and retention workflows.
Official documentation hub for Microsoft Foundry — the unified platform for building, evaluating, and deploying AI models and agents. Covers project setup, SDKs, model catalog, agent service, evaluation, and governance.
Practical guidance for selecting, managing, and governing models in Microsoft Foundry, with concrete advice on balancing quality, performance, and cost in production AI solutions.
Introduces Foundry IQ, a new Microsoft Foundry capability that combines unified knowledge management with serverless retrieval, enabling partners to build retrieval-augmented agents without custom infrastructure. Explains how it simplifies knowledge ingestion, reduces build complexity, and accelerates enterprise agent delivery cycles.
Nine-module Microsoft Learn path covering agent creation, tool integration, multi-agent workflows, testing, and deployment with Microsoft Foundry.
Self-paced learning paths on Microsoft Learn — from AI fundamentals to intermediate and advanced Foundry topics including model deployment, agent development, evaluation, and responsible AI.
Official documentation for Semantic Kernel — AI agent framework, plugins, planners, memory, and multi-agent orchestration for .NET, Python, and Java.
How to secure AI agents with Microsoft Entra Agent ID — unique agent identities, lifecycle management, conditional access, Zero Trust enforcement, and audit capabilities for autonomous AI workloads.
Azure's Security and Responsible AI Guide — applying Zero Trust principles, threat modeling, and governance to AI systems. Covers identity, access control, data protection, and compliance frameworks.
Entra Agent ID gives every AI agent a managed identity — enabling authentication, authorization, and audit trails for agent-to-agent and agent-to-resource interactions.
Developer-first platform for AI agent integration with Entra — covers agent registration, consent flows, and delegated access patterns for secure agent-to-service communication.
Official Agent 365 documentation — the control plane for agent identity, posture management, governance, and runtime monitoring at enterprise scale.
Assess your organization's AI risk posture with the Security Dashboard for AI — visibility into AI asset inventory, misconfigurations, and threat signals across your AI workloads.
Microsoft's six responsible AI principles — fairness, reliability & safety, privacy & security, inclusiveness, transparency, and accountability. The foundational framework for all AI development at Microsoft.
Microsoft Learn module on operationalizing responsible AI — governance, policies, impact assessments, and practical controls for safe AI deployment.
High-level overview of Microsoft's unified AI platform — what Foundry is, how it brings together models, agents, tools, and governance for enterprise-grade agentic AI solutions.
Official Microsoft partner training hub for the "Protect Cloud AI Platform and Apps" solution play — courses, certifications, and learning paths for security partners.
Central hub for Microsoft security partners — go-to-market resources, partner programs, and enablement materials for building and selling security solutions.
Latest news, events, and announcements for Microsoft security partners — product updates, webinars, and community events.