Session
Designing Accessible and Inclusive Copilot Agents
Session Summary
Learn how to design Copilot agents that support neurodiversity by replacing "digital noise" with calm, structured, and predictable interactions. We will move beyond accessibility checklists to explore practical patterns that reduce cognitive overload and decision fatigue for every brain.
Full Session Description
We spend plenty of time discussing what AI can do but far less time discussing how it feels to use.
As Copilots become part of our daily work, we face a significant, unspoken challenge: cognitive diversity. As someone with ADHD, I know how quickly digital tools can become barriers. Long forms, walls of unstructured text, and open-ended prompts often prevent me from engaging at all. This is not a failure in understanding the technology, this is a failure in user experience and inclusive design.
For some users, a poorly designed AI agent creates cognitive overload and decision paralysis. What should be a productivity boost simply becomes more digital noise.
This session moves beyond basic accessibility checklists and into the realm of cognitive inclusion. We will explore how to build Copilot Studio agents that are easy to understand, predictable in behaviour, and are not overwhelming to use.
We will walk through real examples of how to make your Copilots feel less overwhelming and more supportive. You will see how to swap long input forms for guided choices, avoid prompt paralysis with suggested actions, and build agents that ask/confirm before they act.
Whether you are a developer, architect, or strategist, you will leave with a framework to empower every brain in your organization. When we design for the edges, we create better experiences for everyone.
Will include demo of accessible and inclusive vs inaccessible and non-inclusive agents
Heather Perriam
Inclusive AI Leader | Biz Apps Practice Lead | Women in Tech Advocate
Brixham, United Kingdom
Links
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