Highlights
- Build and configure AI agents in Copilot Studio from the ground up
- Ground agents in enterprise data — SharePoint, Dataverse, files, and websites — for accurate, context-aware responses
- Connect agents to business systems via Power Automate, platform connectors, and REST APIs
- Design multi-turn conversations with branching logic, entity extraction, and error handling
- Apply generative orchestration and know when to use it over traditional topic flows
- Create autonomous, goal-driven agents capable of multi-step reasoning and task completion
- Evaluate agent performance using test datasets, automated testing, and conversation analytics
- Apply responsible AI principles and governance controls including Microsoft Agent 365 and Entra Agent ID
- Plan for licensing, capacity, and organisational readiness for successful agent adoption
Course Details
Session 1 — Getting Started with Copilot Studio
- Platform overview: the modern agent model and where Copilot Studio fits
- Copilot Studio interface walkthrough
- Creating your first agent — structure and workflow
- Core concepts: topics, triggers, entities, and variables
- Model selection: GPT-5, third-party models, and when to use each
- Authentication patterns: Azure AD, custom auth, and anonymous access
Session 2 — Generative AI & Grounding
- Generative answers and the Knowledge concept (modern capability)
- Grounding with enterprise data: SharePoint, files, websites, Dataverse
- Deep reasoning in declarative agents — applying it to organisation-specific data
Session 3 — Integration, Connectors
- Power Automate integration: triggering flows and passing data to/from agents
- Connectors: Dataverse, SharePoint, SQL, and REST APIs
- Reading and writing external data safely — permissions and data handling
Session 4 — Advanced Conversation Design
- Multi-turn conversation design principles
- Branching, conditions, and variable management
- Entity extraction and structured data capture
- Error handling and fallback strategies
- When to use topic flows vs. generative responses
Session 5 — Orchestration, Autonomous Agents & Computer Use
- Generative orchestration deep dive: how agents plan and select actions
- Topic flows vs. orchestration — choosing the right approach
- Autonomous agent behaviours and goal-driven execution
- Multi-step reasoning and long-horizon task completion
- Multi-agent orchestration: Connected Agents and delegation patterns
- Agentic workflows: the new Workflows experience in Copilot Studio
- Generative orchestration deep dive
- How copilots plan and choose actions
- When to use orchestration vs. topic flows
- Autonomous agent behaviours
Session 6 — Evaluation, Testing & Analytics
- Agent evaluation framework: what to measure and why
- Creating evaluation datasets from real conversation data
- Running automated tests and interpreting results
- Improving accuracy, reliability, and grounding quality
- Analytics dashboards and conversation transcript analysis
- Escalation tracking and continuous improvement cycles
Session 7 — Governance, Security & Responsible AI
- Responsible AI principles and guardrails for predictable behaviour
- Microsoft Agent 365: centralised control plane for managing agents across environments
- Microsoft Entra Agent ID: identity and access management for agents
- Admin controls: visibility, oversight, and environment-level policies
- Licensing and capacity planning for enterprise deployments
Who should attend
- Business analysts and process owners looking to automate workflows with intelligent agents
- Developers and technical users integrating agents with APIs, data sources, and enterprise systems
- Power Platform users wanting to extend Copilot and Power Automate capabilities
- Solution architects designing scalable, AI-driven business solutions
- Teams responsible for deploying, testing, and improving conversational or agent-based systems
Feedback
4.8 out of 5 average
"Our tailored course provided a well rounded introduction and also covered some intermediate level topics that we needed to know. Mariella gave us some best practice ideas and tips to take away. Brian Leek, Data Analyst, May 2024
“JBI did a great job of customizing their syllabus to suit our business needs and also bringing our team up to speed on the current best practices. Mariella was excellent & contents were very impressive” Brian F, Team Lead, RBS, Data Analysis , 20 April 2024