Change display time — Currently: Eastern Daylight Time (EDT) (Event time)

Creating an AI Assessment Assistant with Gemini: A Framework for Feedback

,
W109B

Idea Lab
Save to My Favorites

Session description

This session demonstrates how teachers can create a custom AI assessment assistant with Google Gemini. Attendees will learn a step-by-step framework for building subject-specific “Gems,” see examples from Business Studies, and explore practical applications to reduce marking time, improve feedback quality, and extend classroom learning.

Outline

Outline (60 minutes total)

1. Introduction & Context (5 minutes)

Content: Introduce self, school context (small NZ secondary school), and session purpose.

Engagement: Quick audience poll via show of hands or digital tool (“How many use AI for assessment already?”).

2. The Challenge (5 minutes)

Content: Outline the problem of teacher workload and inconsistent feedback.

Engagement: Peer-to-peer 2-minute discussion — “What is your biggest challenge in giving feedback?” Volunteers share back.

3. Framework Overview (10 minutes)

Content: Present the 3-step framework (Prompting, Uploading Resources, Testing/Refining).

Engagement: Live demo of a sample prompt and AI output. Audience invited to suggest a variation, tested in real time.

4. Case Study: Business Studies Assessment (10 minutes)

Content: Show how Gemini was applied to an NCEA Business Studies standard. Share before/after examples of student feedback.

Engagement: Small-group discussion — “How would this transfer to your subject/assessment system?”

5. Hands-On Action Planning (15 minutes)

Content: Guide attendees in drafting their own custom AI assistant plan.

Engagement: Device-based activity — attendees outline a prompt + identify 1–2 curriculum resources they could upload. Peer sharing for feedback.

6. Expanding Uses Beyond Assessment (5 minutes)

Content: Showcase creative extensions (lesson starters, exam questions, interactives).

Engagement: Audience brainstorm in pairs — “What’s one classroom use you’d try next week?”

7. Reflection & Q&A (10 minutes)

Content: Revisit outcomes — consistent, time-saving, student-empowering feedback.

Engagement: Open Q&A plus final reflection poll — “What’s your first action step after this session?”

Process & Engagement Tactics:

Frequent audience interactions (every 5–10 minutes): polls, pair-shares, group discussions.

Device-based activity for hands-on creation of an action plan.

Real-time demo of Gemini showing authentic outputs.

Opportunities for peer-to-peer idea exchange and feedback.

More [+]

Outcomes

Attendees will leave with a replicable action plan for creating their own Gemini assessment assistant. This includes a step-by-step framework, a sample prompt template, and guidance for uploading curriculum resources. Participants will also identify specific opportunities in their context to implement AI for consistent, time-saving feedback.

More [+]

Supporting research

Supporting Research

Darling-Hammond, L., & Adamson, F. (2014). Beyond the Bubble Test: How Performance Assessments Support 21st Century Learning. Wiley.
→ Establishes the importance of high-quality, criterion-based feedback in improving learning outcomes.

Hattie, J., & Timperley, H. (2007). “The Power of Feedback.” Review of Educational Research, 77(1), 81–112.
→ Seminal work showing how effective feedback has one of the greatest impacts on student achievement.

Luckin, R. (2018). Machine Learning and Human Intelligence: The Future of Education for the 21st Century. UCL Institute of Education Press.
→ Explores the role of AI in supporting—not replacing—teacher expertise.

Holmes, W., Bialik, M., & Fadel, C. (2019). Artificial Intelligence in Education: Promises and Implications for Teaching and Learning. Center for Curriculum Redesign.
→ Practical guide to how AI can enhance assessment and personalization.

OECD (2023). Artificial Intelligence in Education: Guidance for Policy Makers. OECD Publishing.
→ Provides international perspective and policy framing for responsible AI adoption in schools.

Mollick, E., & Mollick, L. (2023). Using AI to Implement Effective Teaching Strategies in Classrooms: Five Strategies, Including Prompts. Wharton Interactive Working Paper.
→ Demonstrates how teachers can design prompts and AI activities to improve learning efficiency.

Kosmyna, N., et al. (2024). “Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task.” Proceedings of CHI 2024.
→ Cautions about overreliance, underlining the importance of reflection and responsible use.

ISTE & ASCD (2022). The ISTE Standards for Educators.
→ Provides the standards framework underpinning this session’s alignment.

Common Sense Media (2024). AI Literacy Principles for Schools.
→ Recognized framework for guiding safe, effective, and student-centered AI use.

Williamson, B., & Eynon, R. (2020). “Historical Threads, Missing Links, and Future Directions in AI in Education.” Learning, Media and Technology, 45(3), 223–235.
→ Academic analysis of the opportunities and risks of AI in education.

More [+]

Presenters

Photo
Teacher
Liger Leadership Academy

Session specifications

Topic:

Student Engagement and Agency

Grade level:

9-12

Audience:

Curriculum Designer/Director, Teacher, Technology Coach/Trainer

Attendee devices:

Devices useful

Attendee device specification:

Laptop: Chromebook, Mac, PC
Tablet: Android, iOS, Windows

Participant accounts, software and other materials:

Google Gemini

Subject area:

Interdisciplinary (STEM/STEAM)

ISTE Standards:

For Educators: Designer, Analyst
For Students: Empowered Learner

Transformational Learning Principles:

Elevate Reflection, Ignite Agency
Related exhibitors:
Google, Inc.