45-minute prompt-based programming lesson with guided practice for end-user programmers¶

Design · All designs
Evidence · 2 claims (2 for) · 1 study (1 causal), q3 · 0 of 1 report an effect size · 2 claims rest on one study

Description¶

A lightweight lesson integrating selected CS1/CS2 concepts (function structure, data transformation, edge cases) with LLM prompting strategies, designed via backward design to fit a single class period. It consisted of "5 short sections (˜5 minutes each)", one per learning objective, each followed by active learning activities including live demonstrations and 3 Promptly problems with automated feedback. All instructional materials are publicly available, and the lesson requires no prior CS background.

Design Implications¶

Context¶

Requirements¶

Delivered as a single 45-minute class period with lecture, slides, and Promptly practice problems with automated feedback
No prior CS background required for learners

Constraints¶

Focused exclusively on prompting skills, with no instruction in Python syntax or code comprehension
Designed for end-user programmers such as first-year engineering students

Target Learners¶

end-user programmers
first-year engineering students without formal CS coursework

Learning Goals¶

specifying computational goals to LLMs
prompt construction and debugging

Claims¶

Examples¶

-

Key Sources¶

Keith Tran, Samiha Marwan, and Thomas Price. (2026). Teaching Prompt-Based Programming with LLMs: A 45-Minute Lesson with Guided Practice for End-User Programmers. https://arxiv.org/abs/2606.30547

Page metadata

Field	Value
`type`	`design`
`id`	`45-minute-prompt-based-programming-lesson`
`title`	`45-minute prompt-based programming lesson with guided practice for end-user programmers`
`description`	`A lightweight lesson integrating selected CS1/CS2 concepts (function structure, data transformation, edge cases) with LLM prompting strategies, designed via backward design to fit a single class period.`
`status`	`review`
`generated`	by `process:settle-candidates` on `2026-10-11`
`trust`	unverified — no one has confirmed this page's content
`sources`	1 — `keith-tran-2026`

Frontmatter is the page's machine-readable record — see the Schema & Guide.