Microsoft Copilot Agents are quickly becoming a core part of modern enterprise applications, blending AI with workflow automation to accelerate digital transformation. With Microsoft Copilot Studio, developers and solution architects can design, extend, and integrate custom AI-powered assistants that operate securely within the Microsoft ecosystem. This session takes a deep dive into the technical capabilities of Copilot Studio and demonstrates how to build Copilot agents that go far beyond simple Q&A. We’ll cover end-to-end development patterns authoring conversational logic, integrating with Power Platform connectors, calling APIs and plugins, and leveraging Dataverse for secure data access. Attendees will also learn how to apply responsible AI principles, manage lifecycle deployment, and optimize performance in real-world scenarios. Technical Takeaways: By the end of this session, attendees will be able to: 1. Author and Customize Copilot Agents – Build a Copilot agent from scratch in Copilot Studio, design conversation flows, and implement prompt engineering patterns. 2. Integrate with Power Platform – Automate approvals, orchestrate workflows, and trigger Power Automate flows directly from Copilot interactions. 3. Connect to Data Sources – Use Dataverse, SharePoint, SQL, and external APIs to fetch, update, and process business-critical data securely. 4. Extend Functionality – Implement custom connectors, plugins, and API calls to extend Copilot beyond Microsoft 365 and tailor it for industry-specific use cases. 5. Enhance Productivity with AI – Embed capabilities like document summarization, knowledge mining, translation, and report generation into enterprise workflows. 6. Manage Governance and Deployment – Apply AI ethics, responsible usage, security, and monitoring practices to ensure compliance and scalable adoption. This session is designed for developers, solution architects, and IT professionals who want to move past demos and actually build enterprise-grade Copilot agents. Through real-world use cases and technical walkthroughs, attendees will leave with a blueprint for integrating Copilot Studio into modern business solutions.

A fireside chat on operationalizing responsible AI in high-stakes industries.

Keynote session featuring Scott Hanselman, Guido van Rossum, Jennifer Marsman, and Sarah Bird discussing AI’s impact on development, Python’s role, and the importance of ethical AI.

Careless speech is a new type of harm created by large language models (LLM) that poses cumulative, long-term risks to science, education, and the development of shared social truths in democratic societies. LLMs produce responses that are plausible, helpful, and confident but that contain factual inaccuracies, inaccurate summaries, misleading references, and biased information. These subtle mistruths are poised to cause a severe cumulative degradation and homogenisation of knowledge over time.

This talk examines the existence and feasibility of a legal duty for LLM providers to create models that “tell the truth.” LLM providers should be required to mitigate careless speech and better align their models with truth through open, democratic processes. Careless speech is defined and contrasted with the simplified concept of “ground truth” in LLMs and prior discussion of related truth-related risks in LLMs including hallucinations, misinformation, and disinformation. EU human rights law and liability frameworks contain some truth-related obligations for products and platforms, but they are relatively limited in scope and sectoral reach.

The talk concludes by proposing a pathway to create a legal truth duty applicable to providers of both narrow- and general-purpose LLMs, and discusses “zero-shot translation” as a prompting method to constrain LLMs and better align their outputs with verified, truthful information.

In this session, we will demonstrate how IBM’s Chief Privacy Office has innovated to expand its mature Privacy program into an Integrated Governance Program, adapting existing systems to address both ethical AI and privacy regulations, and move towards a continuous compliance approach.