Skip to main navigation Skip to search Skip to main content

CRAFT Prompt Generation Framework for Teachers

  • Deepti Joshi
  • , Robin Jocius
  • , Jennifer Albert
  • , Candace Joswick
  • , Melanie Blanton

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Generative artificial intelligence (GenAI) tools such as ChatGPT, Gemini, and Claude are transforming instructional design, yet most PK–12 educators lack effective strategies for engaging with them. To address this gap, we developed the CRAFT framework—a teacher-centered model for GenAI prompt design that emphasizes Context, Role, Audience, Format, and Tone. CRAFT translates principles from prompt engineering, instructional design, and Universal Design for Learning into a practical structure aligned with teachers’ professional planning language. We implemented the framework in a professional development program with 94 PK–6 teachers who used GenAI to create lessons integrating computational thinking. Their 688 prompts and AI-generated responses were coded across 30 analytical features representing critique, launch behaviors, refinements, and supplemental material generation. Findings suggest that CRAFT helped teachers produce standards-aligned, differentiated, and instructionally coherent lessons while increasing confidence, creativity, and reflective engagement with GenAI tools.

Original languageEnglish
Title of host publicationSIGCSE TS 2026 - Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2
Pages1383-1384
Number of pages2
ISBN (Electronic)9798400722554
DOIs
StatePublished - Feb 17 2026
Event57th SIGCSE Technical Symposium on Computer Science Education, SIGCSE TS 2026 - St. Louis, United States
Duration: Feb 18 2026Feb 21 2026

Publication series

NameSIGCSE TS 2026 - Proceedings of the 57th ACM Technical Symposium on Computer Science Education V.2

Conference

Conference57th SIGCSE Technical Symposium on Computer Science Education, SIGCSE TS 2026
Country/TerritoryUnited States
CitySt. Louis
Period2/18/262/21/26

Bibliographical note

Publisher Copyright:
© 2026 Copyright is held by the owner/author(s).

Funding

This material is based upon work supported by NSF under grant numbers 2300322 and 2300323.

FundersFunder number
National Science Foundation Arctic Social Science Program2300323, 2300322

    Keywords

    • Computational Thinking
    • CRAFT Framework
    • Generative AI
    • PK-12 Lesson Planning
    • Prompt Engineering

    ASJC Scopus subject areas

    • Computer Science (miscellaneous)
    • Education

    Fingerprint

    Dive into the research topics of 'CRAFT Prompt Generation Framework for Teachers'. Together they form a unique fingerprint.

    Cite this