Skip to content

Madida: a fictional GAI learning companion supporting the backcasting exercise

Design · All designs
Evidence · no claims cited

Description

Madida is a fictional GAI character serving Use case 2 as a learning companion for the values-thinking backcasting exercise; "Its role includes helping the student prepare their backcasting presentation by engaging in a sparring session about their backcasting exercise." Madida's sparring approach "was prompt-engineered based on the backcasting questions formulated according to the I SEE project," and the character offers emotional support while helping students accomplish the task. Domain experts described Madida's interaction as natural and its nature as encouraging, supportive, and approachable.

Design Implications

Context

Requirements

  • Prompt engineering based on structured backcasting questions, iterated through multiple testing rounds

Constraints

  • The associated exercise includes a limited number of structured questions, which is why testing required fewer questions than Tero

Target Learners

  • higher education students in sustainability education

Learning Goals

  • values-thinking competency: creating visions guided by sustainability values via backcasting

Claims

  • Tero Gai Forest Owner Character

Examples

-

Key Sources

  • Ulla Hemminki-Reijonen, Noha M. A. M. Hassan, Minna Huotilainen, Jaana-Maija Koivisto & Benjamin Ultan Cowley. (2025). Design of generative AI-powered pedagogy for virtual reality environments in higher education. npj Science of Learning. https://doi.org/10.1038/s41539-025-00326-1
Page metadata
Field Value
type design
id madida-gai-learning-companion-character
title Madida: a fictional GAI learning companion supporting the backcasting exercise
description Madida is a fictional GAI character serving Use case 2 as a learning companion for the values-thinking backcasting exercise; "Its role includes helping the student prepare their backcasting presentation by engaging in...
status review
generated by process:settle-candidates on 2026-10-27
trust unverified — no one has confirmed this page's content
sources 1 — ulla-hemminki-reijonen-2025

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