Session

From Concept to Intelligent Agent: Build AI Agents with Copilot Studio and Azure AI Foundry

Struggling to keep pace with ever-growing tasks and business complexity? Looking for a smarter way to streamline cross-functional processes, automate decision-making, and personalize enterprise user experiences? This workshop takes a deep dive into designing, customizing, and integrating intelligent agents using Microsoft Copilot Studio, extended with the advanced capabilities of Azure AI Foundry.

We'll start by exploring real-life use cases - from automating employee or customer interactions to integrating with systems like Dynamics 365 and Microsoft Teams. You’ll learn how to configure intelligent agents in Copilot Studio using features like multi-turn dialogues, adaptive cards, actions, and external API calls.

The second half of the session focuses on Azure AI Foundry - where you’ll go beyond the basics and learn how to:
- Build, test, and optimize Prompt Flows to generate context-aware responses
- Configure evaluation metrics to assess response quality and performance
- Enable tracing and telemetry to monitor token usage, latency, and model behavior
- Leverage Prompt Flow chaining and retrieval techniques (RAG) to ground answers in enterprise data
- Deploy and manage components using Infrastructure as Code (IaC) approaches with Bicep scripts, enabling repeatable, scalable, and governed agent solutions across environments

By the end of this workshop, you’ll be equipped to:
- Identify impactful use cases for intelligent agents
- Build and extend agents in Copilot Studio using advanced features
- Use Azure AI Foundry to configure, evaluate, and trace Prompt Flows - ensuring your solutions are reliable, scalable, and measurable

Ideal for Functional Consultants looking to combine low-code AI development with deeper customization and quality control across the Microsoft cloud ecosystem.

Katerina Chernevskaya

Power Platform Architect at KPMG | BizApps MVP | MCT

Razlog, Bulgaria

Actions

Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.

Jump to top