Hello… :-) Try out the Azure AI Agent Service for free! 1 Join Discord 2 Join the channel #agentcon 3 Post a photo with #TryFoundryAgents 4 Follow the instructionsz in your DM aka.ms/agentcon/discord 

The Age of AI Agents Bethany Jepchumba | @bethanyjep 

Would you trust an AI to …? 

Write and send emails? 

Pick a movie or book you’d enjoy? 

Assist you in coding? 

Drive you in a busy Road Traffic? 

Recommend your next career move? 

And how AI agents can help… Where we are today….. 

It looks like there might be three different issues that could lead to too much noise: Unbalanced Load If the clothes inside are unevenly distributed, especially during the spin cycle, the drum can wobble and cause loud banging or thumping sounds. Worn Drum Bearings Over time, the bearings that help the drum spin smoothly can wear out, leading to grinding or rumbling noises, particularly during spinning. Loose or Damaged Parts Items like shock absorbers, suspension springs, or drive belts can become loose or damaged, resulting in clunking, squealing, or rattling sounds. Today, many customers use generative AI for knowledge retrieval (aka RAG)… Before AI Agents Search: W100 manual A customer is having an issue with their washing machine W100 making too much noise; can you help me diagnose the issue? You should create a ticket for a technician to take a look Customer Customer Support Emails, calls, or messages Searches internal knowledge base 

But most downstream processes are still brittle and require meaningful human involvement Before AI Agents Customer Customer Support Emails, calls, or messages Ticket form Creates ticket Database API RPA Automation Sends notification Searches internal knowledge base 

But most downstream processes are still brittle and require meaningful human involvement Before AI Agents Microsoft confidential 12 Automation cannot self- heal or handle novel cases RPA breaks whenever UI is updated or changed Employees waste time structuring data Teams must constantly monitor existing RPA scripts to ensure they do not break. Nearly all automation today starts with form over data which is slow and error prone. Complex logic is needed to handle unexpected edge cases within automation systems. 

LLMs update RPAs if the UI updates or changes Tool calling LLMs can self- heal or handle novel cases Here you go! Would you like me to submit the JSON to the API? With AI Agents, you can make your automation more resilient while removing the drudgery from work After AI Agents Microsoft confidential 13 { "name" : "John Clar "issue": ”Washing m } Convert the customer conversation into a JSON that looks like this… Transcript Click on the submit button for the scheduling form Looks like the ID of the order form is submit-order, I’ll go ahead and click it now. Submit form The form has been successfully submitted, is there anything else you need? Assign technician LLMs spend little time structuring data Update work order Let me try again with an available technician. Update work order Alex declined because they're on leave Successfully assigned Lindsay 

LLMs update RPAs if the UI updates or changes Tool calling LLMs can self- heal or handle novel cases And when combined with system events, you can fully automate business processes with AI Agents After AI Agents Microsoft confidential 14 Click on the submit button for the scheduling form Assign technician LLMs spend little time structuring data Convert the customer conversation into a JSON that looks like this… Transcript Here you go! Would you like me to submit the JSON to the API? { "name" : "John Clar "issue": ”Washing m } Looks like the ID of the order form is submit-order, I’ll go ahead and click it now. Submit form The form has been successfully submitted, is there anything else you need? Update work order Let me try again with an available technician. Update work order Alex declined because they're on leave Successfully assigned Lindsay 

A new frontier – Introducing… Agentic AI 

What is an AI agent? LLM Instructions Tools Agent + + An AI agent is a micro-service that takes unstructured messages, optionally invokes other APIs and returns messages 1 2 3 Input System events User messages Agent messages 1 Tool calls Knowledge Actions Memory 2 Output Agent messages Tool results 3 

Unlike previous tools, AI Agent can… reason, act and learn 

Agentic patterns Acting aka tool calling Learning aka memory Reasoning aka planning I’ve captured the underlying issue in the details { "name" : "John Clar "issue": ”Washing m Create a JSON describing the user issues Check logs Machine is past due for maintenance Go beyond transcriptions and slot filling by allowing agents to deduce the why I’ll look at the logs to see what happened Transcript Fill out and submit the workorder Populate field: name The form has been successfully Agents can take a simple request and chain multiple tool calls to complete the ask Only make a mistake once. With memory, agents can recall prior experiences Populate field: issue Name field populated Issue field populated Submit form Update work order Let me try again with an available technician. Update work order Alex is already booked at this same time Successfully assigned technician Assign technician Saved memory: Alex is OOF next week 

An AI agent in action… LLM Instructions Tools Agent User: My washer machine is making weird noises Agent: Recall user washing machine Tool: User has w100 with sn: 142352 Agent: I’ll see what could be causing your w100 issues Agent: Search manuals Agent: It looks like there are three common reasons Agent: I’ll check your machine if it has any notices Agent: Check logs for 142352 Agent: It looks like your machine is due for maintenance and is still under warranty. Want me to schedule an appointment? User: Sure! Let’s target early next week Agent: Look for available times Agent: Would Monday at 1:00pm work? User: Let’s do it! Agent: Create workorder Agent: Done! Is there anything else I could help you with? GPT-4o You’re responsible for helping customers with their appliances Appliance manuals Check appliance logs Create workorder Recall user details 

At the core are threads User: My washer machine is making weird noises Agent: Recall user washing machine Tool: User has w100 with sn: 142352 Agent: I’ll see what could be causing your w100 issues Agent: Search manuals Agent: It looks like there are three common reasons Agent: I’ll check your machine if it has any notices Agent: Check logs for 142352 Agent: It looks like your machine is due for maintenance and is still under warranty. Want me to schedule an appointment? User: Sure! Let’s target early next week Agent: Look for available times Agent: Would Monday at 1:00pm work? User: Let’s do it! Agent: Create workorder Agent: Done! Is there anything else I could help you with? An agent platform not only helps manage agents, but the underlying conversation state. With threads, you can… ▪ Secure conversation data ▪ Observe agent behavior ▪ Fine-tune agent models 

The opportunity for automated AI is growing… By 2028, at least 15% of day- to-day work decisions will be made autonomously through agentic AI. 

Making it real How to build AI Agents today 

Microsoft has different ways of building agents Control, visibility, and customization Platform Integrations, ease-of-use, and development speed IaaS PaaS SaaS Infrastructure-as-a-service Platform-as-a-service Software-as-a-service Azure AI Foundry Agent Service Copilot Studio Agents GPUs & Containers OSS LLMs and frameworks Bring your own 

In each case, you provide a model, instructions, and tools Azure AI Foundry Agent Service Copilot Studio Agents Copilot Studio manages the model for you GPUs & Containers OSS LLMs and frameworks 

SaaS Copilot Studio Quickly build agents in a fully managed service on top of Microsoft 365. 

Copilot Studio Copilot Studio is the solution to build agents that extend Microsoft 365 Copilot or operate standalone. Meet your users where they already are Access everything in one place Automate your workflows Integrate with your external apps Connect to your data in Microsoft 365 

Showcasing Copilot Studio pizza order agent 

PaaS Agent Service Build agents on a managed service on top of your own Azure resources. 

Azure AI Foundry Security • Identity • Management Foundry Models Foundry Agent Service Azure AI Search Foundry Observability Azure AI Services Azure Machine Learning Azure AI Content Safety Copilot Studio Visual Studio GitHub Foundry SDK Serverless Control Azure Kubernetes Service Azure Container Apps Azure App Service Azure Functions Cloud Azure Azure Arc Foundry Local Edge 

Foundry Agent Service Combine the best models, services, and tools in Azure AI Foundry into reusable, testable agentic components. Azure AI Foundry Foundry Models Hosted & sold by Microsoft & others Fine-tuned models BYO-models Azure AI Content Safety Content filters Cost management Governance Enterprise Security Development frameworks and toolkits Foundry SDK Semantic Kernel AutoGen LangGraph LangChain LlamaIndex CrewAI And more… Agent integrations Assistants API Activity protocol A2A Agent protocol Knowledge & Tools OpenAPI tools MCP tools Bing Azure AI Search SharePoint Microsoft Fabric Logic Apps Azure Functions Foundry Observability Tracing Logging Monitoring Evaluation Experimentation Foundry Agent Service Managed orchestration Managed threads Network isolation OBO-auth integration 

The Agent Factory Trust Customization Observability Orchestration 2 5 4 6 3 Knowledge & Tools Models 1 Azure AI Foundry 

1 Models Model choice Don’t lock yourself into a single model provider Azure OpenAI Service o3-mini, o3, o4-mini, GPT- 4.1, 4o, etc Models-as-a-Service Llama 3.1-405B-Instruct Mistral Large Cohere-Command-R-Plus 

1 2 Customization Models Customization Use the data in your threads to fine-tune and distill models 

Knowledge and tools 1 2 3 Customization Models AI tools Give your agents the skills to retrieve data and act Knowledge Actions Logic Apps OpenAPI Azure functions MCP* Connected agents A2A* Agent service Copilot Studio 

Knowledge and tools Orchestration 1 2 3 4 Customization Orchestration We’ll automatically invoke tools and store results in your thread Agent Tool calls Knowledge Actions Memory 

Knowledge and tools Orchestration Trust 1 2 3 4 5 Trust Reduce risk by controlling your data and by leveraging RAI ▪ BYO-thread storage ▪ BYO-file storage ▪ BYO-search index ▪ BYO-virtual network ▪ OBO authentication ▪ Content filtering 

Knowledge and tools Orchestration Trust Observability 1 2 3 4 5 6 Observability Watch everything your agent does within a thread 

Showcasing Azure AI Foundry pizza order agent 

PaaS Foundry Local Bring your agents on device 

Foundry Local Comprehensive support for managing models, agents, and their components on Windows and MacOS devices. • Accelerate on-device inferencing • Ship local AI apps, not just explore • Bring the power of Azure AI Foundry locally 

Showcasing Foundry Local pizza order agent 

IaaS Semantic Kernel Taking your agents to production 

Semantic Kernel AI and Agent Orchestration AI Services Azure OpenAI Foundry Catalog OpenAI Hugging Face NVIDIA Deepseek Google Gemini AWS Bedrock Plugins OpenAPI MCP A2A Logic Apps Filters and telemetry OpenTelemetry Azure Monitor Aspire Dashboard Azure AI Content Safety Z Memory Services Azure AI Search Azure CosmosDB Elasticsearch MongoDB Pinecone Qdrant Redis Local models Ollama ONNX LM Studio Phi SLM Model Family Prompts YAML Semantic Kernel Python Java .NET Agent Services Azure AI Agent Service Bedrock Agents AutoGen Crew AI 

Microsoft’s Agent frameworks Orchestrate agents with AutoGen and Semantic Kernel State-of-the-art research SDK Production-ready and stable SDK Research Production Shared Agent Runtime Deploy them to Foundry Agent Service Supports both single and multi-agent workflows 

Converging the two popular OSS frameworks Semantic Kernel AutoGen Full SDK designed to build AI agents with ease, excellent for single agents and can be extended for multi-agents with integrations to AutoGen Powerful multi-agent research framework with prebuild conversation orchestration patterns for handling complex agent systems Microsoft Agent Framework (coming soon) 

Common AI Agents Use Cases 

AI Agent workflows can enhance efficiency, accuracy, and customer satisfaction Key Use Cases Across Industries • Assists employees in booking business trips • Integrates with Tripadvisor, Outlook, and SharePoint • Books via Teams chat or email • Uses OCR to gather receipts • Automates expense report submission and tracking Travel Booking & Expense Management • Personalized onboarding assistant for new hires • Uses LLMs grounded in HR data from SharePoint • Provide relevant training materials • Schedule orientations and set up software accounts • Monitor task completion and ensure efficient onboarding Employee Onboarding • Diagnoses issues by referencing history and product manuals • Provides tailored solutions or escalates through automated workflows • Creates tickets and schedules follow-ups • Updates CRM records, enhancing future support Personalized Customer Support • Analytics data from data lake and data warehouse • Responds to user requests in natural language • Generates insights, visualization, and sends via Teams or email • Automates data handling for real-time, effortless decision-making Data Analytics and Reporting 

Get started with the Azure AI Foundry: ai.azure.com Learn more about Azure AI Agent Service on Microsoft Learn: https://aka.ms/MicrosoftLearn_Age nts Get started with Azure AI Agent Service today Watch the sessions on-demand  Build 2025 Breakout Session  Build 2025: Bes Practices of Building Agent Applications  Build 2025: Multi-Agent Orchestration with Foundry Agent Service Read the GA announcement blog: aka.ms/Build25/AgentService_GA 

Thank you Try out the Azure AI Agent Service for free! 1 Join Discord 2 Join the channel #agentcon 3 Post a photo with #TryFoundryAgents 4 Follow the instructionsz in your DM aka.ms/agentcon/discord 

Thank You