Accessibility in Power BI is widely recognised as important, but it’s rarely approached in a consistent or scalable way. Most teams rely on manual checks and visual judgement, making it difficult to know whether a report is truly usable for everyone.

In this session, I’ll share how I built PBIX A11y, a free, browser-based accessibility checker for Power BI, using AI to turn a recurring frustration into a practical solution.

This is a behind-the-scenes look at the full journey, from identifying the gap and reframing the problem from a user perspective, to designing meaningful checks and creating a tool that is both usable and trustworthy. I’ll show how Copilot acted as a prompting companion throughout the process, helping to accelerate development, refine ideas, and expose the limits of AI that required stronger prompts and informed human judgement.

Along the way, I’ll explore the responsible use of AI in practice, including how transparency, validation, accountability, and privacy shaped key decisions. This includes clearly communicating where AI is used, how outputs are generated, and where limitations exist, as well as addressing real-world considerations such as validating AI-generated results, ensuring GDPR compliance, and balancing usability with trust.

Attendees will leave with a practical and honest perspective on what it takes to turn an idea into a purposeful AI solution, understanding not just how to build faster with AI, but how to build responsibly.