Super Data Science: ML & AI Podcast with Jon Krohn 983: AI in the Classroom: How a Top Elementary School Is Doing It Right, with Principal Traci Walker Griffith
69 snips
Apr 14, 2026 
Traci Walker Griffith, principal who turned the Elliott School from near-closure into Boston’s top K–8, describes how her team uses AI to speed writing feedback and boost multilingual and special-needs learners. She explains teacher-facing and student-facing workflows, prompt iteration, ethical and access decisions, and how AI fits into larger STEM and project-based learning.
AI Snips
Chapters
Books
Transcript
Episode notes
Iterate Prompts With Teacher Collaboration
- Do iterate prompts with teachers collaboratively and accept early failures as learning opportunities.
- Elliott's teachers called prompt engineering 'the good prompt whisper' and improved outputs through weekly collaborative refinement.
AI Multiplies Teacher Collaboration And Targeting
- Traci found AI amplified teacher collaboration by surfacing student-level feedback quickly, enabling targeted small-group instruction.
- Claude helped identify which students needed whole-class extension, small-group work, or individualized intervention based on feedback iterations.
Phase Student Access Based On Age And Policy
- Try student-facing AI only when age and district policy allow and start with teacher-facing AI for younger grades.
- Elliott uses Gemini student-facing from grades five to eight while K–4 teachers use gems behind the scenes without PII.
