Airships XR — Build an AI, Fly the R101
AI Literacy · Airships XR Workshop

Build an AI.
Fly the R101.

In this workshop you'll build a real AI agent, use it to investigate a historical crash, and then refly the airship with your fix. Here's how it works:

Stage 1 Build Your Agent You choose its name, personality, and the rules it follows — exactly how real AI assistants are configured
Stage 2 Investigate Scan your team's component, read the evidence, then chat with your AI agent to dig into what went wrong
Stage 3 Discuss as a Group Share your findings with your teammates, agree on a fix, and write your group's answer
Stage 4 Fly the R101 Apply your fix and refly the airship — the deeper you investigated, the better your chances of reaching Karachi
For facilitators & researchers
Framework Resnick's 4 P's of Creative Learning — Projects, Passion, Peers, Play. Each stage maps to one P. Students construct understanding of AI systems by designing one, not by being taught about one.
Research question Can constructionist design tasks — naming an AI, writing a system prompt, choosing a constraint — scaffold meaningful AI literacy in secondary learners?
Observable signals Inquiry depth (0–5 turns), system prompt choices, rule specificity, group answer quality, and flight outcome provide naturalistic behavioural data without explicit assessment.
Agent design Each personality maps to a distinct system prompt sent to the LLM. Students read their own prompt before it is used — making the hidden layer of AI systems visible and discussable.

Child-centered AI · Resnick's 4 P's · Airships XR Workshop, Bedford

October 4, 1930 — Cardington, England

Britain's R101 — the world's largest airship — departs tonight on its maiden voyage to India. 237 metres long. Built to connect an Empire.

54 people aboard. Hydrogen keeps it aloft. Tonight, you're at the controls.

100GAS
65ENGINE
50HULL
Lift
Descend
Hold to control thrust
CRASH CONFIRMED
R101 — INCIDENT BRIEF
Date05 October 1930
LocationBeauvais, France
Fatalities48 of 54 on board
CauseUNKNOWN
Investigation statusOPEN

Britain's largest airship crashed on its very first voyage. What went wrong — and could it have been prevented?

Your team will build an AI agent, scan a physical component to unlock evidence, then co-investigate the failure together. Your findings shape whether the R101 makes it to India this time.

Incident Report — October 1930

Your Mission

The R101 crashed on its maiden voyage. Three components are suspected. Your team investigates one, builds an AI agent, then reflys the airship with your fix.

Build your AI agent Name it, set its personality and rules
Scan your component Point the camera at the physical model to unlock your evidence
Chat with your agent Ask questions, push back, work out what went wrong
Write your group’s fix Compare findings and agree on a shared answer
Refly the R101 Your investigation depth determines if the airship makes it

Three suspected components — your facilitator will assign yours

Gas Bags Hydrogen bags that kept the ship airborne
Engine Cabin Five Beardmore diesel engines — speed and control
Dining Hall Full silver-service cabin — added weight nobody accounted for
Build Your AI Agent — Incident Report, October 1930
01 / 04

Stage 1 — Projects

Build Your AI Investigator

You’re writing the system prompt — the hidden instructions that control every response your AI gives. Name it, set its investigative style, then write a rule it must follow. This is exactly how real AI assistants are built.

Name→ Personality→ Rule
0/28

Give your agent a name before choosing an investigation.

Write a rule. It becomes part of your agent's system prompt.

0/60

Your rule changes how the AI replies — try it and see.

Personality — your system prompt

Pick one — the text shown is the actual instruction sent to the AI.

Tone —
Goal —
Constraint Never answers directly — always responds with a question.
Full assembled prompt 
Select a personality above to preview the full prompt that will be sent to the AI.
02 / 04

Stage 2 — Passion

Scan & Investigate

① Scan card ↓ ② Read evidence → ③ Answer questions ↓ ④ Chat
1 Scan your card
Gas Bags Engine Cabin Dining Hall
Hold card flat in the box
Scan your object

Hold your laminated card flat in the frame — the AI will identify it.

Hold your laminate card flat in the frame.

Identified

Identified — evidence unlocked below

Read the evidence below → then answer the two questions on the right.
Choose manually

Choose a component to unlock.

Evidence locked

Scan a card above to unlock

2 Evidence file

3 Brief your AI

Added

Added — launching investigation

AI brief assembled

4 Co-investigate
A
Agent Curious Engineer
Personality—
Constraint—
Your rule—
Investigation depth
0 / 5
What’s happening

Replies are shaped by your system prompt from Stage 1 — not free thinking. Tap Instructions above to see what the AI was told.

03 / 04

Stage 3 — Peers

Group Answer

Discuss→ Write→ Lock in

Talk first, then type. Compare what everyone found.

Group question

In one sentence - what is your strongest redesign idea?

Write your group's answer before launching.

Your group said

04 / 04

Stage 4 — Play

Fly the R101

You've investigated the failure. Now refly the R101 with your fix — does it make it to Karachi this time?

70LIFT
65SPEED
60SAFETY
Lift
Descend
Hold to control altitude
(keyboard: ↑ / W / Space)