Learning Lab | Building Purposeful AI Assistants for Practical Work in Higher Ed – July 2026

Part 1: July 7, 2026 | 12:00–1:30 p.m.ET
Part 2: July 9, 2026 | 12:00–1:30 p.m.ET
Part 3: July 14, 2026 | 12:00–1:30 p.m.ET
Part 4: July 16, 2026 | 12:00–1:30 p.m.ET

Overview

Many institutions are experimenting with generative AI. However, turning experimentation into useful practice remains a challenge. Where can AI assistants actually help? How can they be designed responsibly and integrated into everyday work? How can they be used in teaching and learning?

This Learning Lab helps higher education professionals design and prototype a custom AI assistant that supports a practical task in their institutional context. Participants will identify a meaningful use case, build an assistant using accessible no-code tools such as ChatGPT, Gemini, Claude, and similar platforms, and refine prompts, knowledge sources, and interaction patterns to improve reliability and usefulness.

Throughout the Lab, we will also explore responsible design considerations including guardrails, evaluation criteria, and integration within institutional environments.

Participants will start by learning the utility of custom chatbots within their own professional area(s) of work along with the particular configuration fields of the system (ChatGPT, Gemini, etc.) they are choosing to use. They will then learn frameworks and design strategies for their chosen use case. A peer-review of design choices will take place prior to participants creating the bot itself. Once the first iteration of their bot is ready, participants will learn a process for review and iteration. Participants should finish the Learning Lab at the very least with a functional prototype.

The participants have access to the instructors throughout to bounce ideas off of and to review design choices.

Learning Outcomes:

NOTE: You will be asked to complete assignments in between the Learning Lab segments that support the learning outcomes stated below. You will receive feedback and constructive critique from course facilitators.

• Identify meaningful use cases where AI assistants could support institutional workflows or services.
• Design, prototype, and iteratively refine a custom AI assistant using accessible generative AI tools, paying particular attention to any necessary guardrail-type instructions relevant to their use case.
• Evaluate and refine assistant performance to improve usefulness, reliability, and alignment with intended tasks.
• Assess key considerations for responsible implementation and future development.