Sign in Subscribe

Inside eSpark’s AI Teacher Assistant: RAG, Evals, and Real Classroom Needs

Inside eSpark’s AI Teacher Assistant: RAG, Evals, and Real Classroom Needs

Listen to this episode on: Spotify | Apple Podcasts

How do you build an AI-powered assistant that teachers will actually use?

In this episode of Just Now Possible, Teresa Torres talks with Thom van der Doef (Principal Product Designer), Mary Gurley (Director of Learning Design & Product Manager), and Ray Lyons (VP of Product & Engineering) from eSpark. Together, they’ve spent more than a decade building adaptive learning tools for K–5 classrooms—and recently launched an AI-powered Teacher Assistant that helps educators align eSpark’s supplemental lessons with district-mandated core curricula.

We dig into the real story behind this feature:

  • How post-COVID shifts in education created new pressures for teachers and administrators
  • Why their first instinct—a chatbot interface—failed in testing, and what design finally worked
  • The technical challenges of building their first RAG system and learning to wrangle embeddings
  • How their background in education shaped a surprisingly rigorous eval process, long before “evals” became a buzzword
  • What they’ve learned from thousands of teachers using the product this school year

It’s a detailed look at the messy, iterative process of building AI-powered products in the real world—straight from the team doing the work.

Show Notes

  • Guests:
    • Thom van der Doef, Principal Product Designer at eSpark
    • Mary [last name], Director of Learning Design & Product Manager at eSpark
    • Ray Lyons, VP of Product & Engineering at eSpark
  • Topics covered:
    • The origin story of Teacher Assistant: connecting administrator mandates with teacher needs
    • Why the team abandoned a chatbot interface in favor of a more structured workflow
    • How retrieval augmented generation (RAG) and embeddings shaped the product architecture
    • Lessons learned from debugging semantic search vs. keyword search
    • Building evals with rubrics, Braintrust, and a human-in-the-loop approach
    • What’s next for Teacher Assistant: more contextual recommendations using student data
  • Links & References:

Chapters

02:05 Overview of Epar's Adaptive Learning Program

07:19 Challenges and Insights from COVID-19

17:06 Developing the Teacher Assistant Feature

24:55 User Experience and Interface Evolution

34:29 Chat GPT-5's New Features

35:16 Balancing Engagement and Efficiency

35:40 Seasonal Business and Real Traffic

36:29 Technical Decisions and RAG Implementation

38:28 Challenges with Embeddings and Metadata

41:24 Improving Recommendations and Data Enrichment

55:18 Evaluating the Teaching Assistant

01:05:51 Future Plans and User Feedback

01:07:57 Conclusion and Final Thoughts

Full Transcript

Podcast transcripts are only available to paid subscribers.

Read next