Skip to content

Reusable structured prompt template built up across lesson sections

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

Description

The lesson taught students a reusable template for constructing prompts, built up throughout the lesson sections, to help them remember to address each learning objective. The template prompts learners to "Write me a Python function that takes as input [describe the input, including its type] and it should output [describe the output, including its type], that [explain how the function transforms the input into the output]" plus an example input and expected output. It operationalizes the Gulf of Envisioning dimensions of describing the problem, phrasing prompts, and assessing output.

Design Implications

Context

Requirements

  • Instruction across the five learning objectives so students can fill each template slot (input, output, transformation, example)

Constraints

  • Taught in the context of Promptly-style tasks requiring natural-language specification of computational intent rather than code writing

Target Learners

  • end-user programmers
  • novice LLM users

Learning Goals

  • articulating inputs, outputs, and transformations to an LLM
  • reducing vague or underspecified prompts

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 reusable-prompt-template-for-llm-code-generation
title Reusable structured prompt template built up across lesson sections
description The lesson taught students a reusable template for constructing prompts, built up throughout the lesson sections, to help them remember to address each learning objective.
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.