Session 14 — Build with Generative AI

Duration: 75 min · Format: live online · Ages: 12–15

Session goal: by the end, students can write strong prompts using pro patterns, design a chatbot with a system prompt, and use generative AI honestly, safely, and with integrity.

Before class — prep (5 min)

• Have a chatbot / LLM open in a tab (one that supports custom instructions / a "custom GPT" / a Poe bot) on a school or grown-up account — you'll screen-share and demo the system prompt live.
• For the Python path: have a free Google AI Studio API key ready (aistudio.google.com) and a Colab notebook open, so Builders can run the code.
• Have the two diagrams below ready to share on screen (prompt recipe and chatbot flow).
• Ask students to have paper and a pencil ready to draft their system prompts.

Agenda

0:00 · Hook (5 min)

Ask the class and take a few answers (chat or unmute):

Read out both prompts and ask which will get the better result:

• "help me"
• "You are a patient tutor. Quiz me on Newton's laws, one question at a time, and explain my mistakes."

Let them vote, then reveal: same AI — wildly different results. The skill isn't in the AI; it's in the asking. Tell them that today they learn the patterns pros use, build their own chatbot, and — most importantly — use it honestly and safely.

0:05 · Teach — Prompt-engineering patterns (12 min)

Explain: a great prompt goes far beyond one line. Pros stack techniques. Share the diagram:

Walk through the patterns out loud, demoing one or two live in the chatbot:

• Role / persona: "You are a strict but kind physics tutor."
• Context: give it the background it needs.
• Examples (few-shot): "Format answers like this: …" — show it what you want.
• Step by step: "Think through it step by step" — better reasoning.
• Output format: "Answer in a 3-row table."

⚠ Watch for lazy prompting: students expect the AI to read their mind, then blame the AI for a bad answer. The fix is theirs — add role, context, and format. A vague prompt gets a vague answer.

Ask: "Take the prompt 'write about dogs' — add a role, a format, and an audience to it out loud." (Take 2–3 answers.)

0:17 · Teach — Design a chatbot (11 min)

Explain: a chatbot is a system prompt (its personality + rules) plus a back-and-forth conversation. Share the diagram:

• The system prompt sets who it is and what it must and mustn't do — it runs behind every reply.
• Want it to use your notes? Give it your text inside the prompt — a simple version of RAG ("retrieval-augmented generation": grounding the AI in real, trusted data instead of its memory).

⚠ Watch for privacy here: grounding a bot in "your data" must never mean pasting personal or sensitive information (real names, addresses, passwords, other people's data). Ground it in safe text only.

Ask: "What one rule would you put in a study-buddy bot's system prompt so it helps you learn instead of just handing you answers?" (Take 2–3 answers.)

0:28 · Teach — Use it responsibly (10 min)

Explain: this is the most important part of the whole module. Generative AI is powerful — which makes using it well a responsibility. Land all four points:

• Fact-check everything important. It can hallucinate (Session 13).
• Integrity: use AI to learn, draft, and get unstuck — never to submit its work as your own. If you used AI, say so (cite it). Competitions and schools expect honesty.
• Privacy: never paste personal or sensitive info — names, addresses, passwords, or other people's data.
• Bias: it learned society's biases, so question its outputs, especially about people.

⚠ Watch for the academic-integrity line: the boundary is using AI to learn vs passing off AI's work as your own. The first is smart; the second is cheating. When in doubt, disclose how you used it — that's what real teams and judges respect.

Ask: "You used AI to help write a project. What are the two things you must do before you hand it in?" (Answer: fact-check it, and disclose/cite that you used AI.)

0:38 · Activity — Build a study-buddy bot (22 min)

Demo Path A first on the shared screen, then have students build their own. Offer Path B to Builders who are ready for code.

Path A — No code (all students). In a chatbot that supports custom instructions / a "custom GPT" / a Poe bot, set a system prompt. Give them this starter to type in and then adapt:

"You are my Year-8 science study buddy. Quiz me one question at a time, wait for my answer, then explain gently. Never give the full answer first."

Have students use it for ~5 minutes, then tweak the system prompt until it behaves the way they want. Circulate and ask what change made the biggest difference.

Path B — Python (Builders). With a free API key from Google AI Studio (ask a grown-up), open Colab.

Type/run this together in Colab:

import google.generativeai as genai
genai.configure(api_key="YOUR_KEY")          # keep keys private!
model = genai.GenerativeModel("gemini-1.5-flash")

system = "You are a patient study buddy. Explain simply, then ask me one question back."
answer = model.generate_content(system + "\nStudent: How do vaccines work?")
print(answer.text)

Circulate and reinforce: the comment says it all — keep API keys private. A key is like a password; never paste it into chat, a shared doc, or a screenshot.

1:00 · Check for understanding (8 min)

Ask these aloud or drop them in the chat. Answer key (for you):

1. What does a system prompt do? → It sets the chatbot's persona and rules — who it is and how it behaves.
2. What is "few-shot" prompting? → Giving the AI examples of what you want, so it copies the format and style.
3. You used AI to help write a project. What must you do? → Fact-check it, and disclose/cite that you used AI — never pass it off as fully your own.
4. True or False: it's fine to paste a friend's home address into a chatbot to plan a visit. → False — never share personal or sensitive data with an AI.

1:08 · Wrap-up + homework (7 min)

• Ask one student to read out their system prompt and say the one change that improved it most.
• Homework — Portfolio chatbot: design and test a chatbot persona for a real need (revision coach, coding helper, idea generator). Write its system prompt, try it, note one improvement you made — and add a line stating how you used AI and how you checked it. Save it to your portfolio.
• Close by naming the journey: from training tiny classifiers to commanding generative AI — responsibly.

Teaching notes

• Correct this misconception: "a better AI gives better answers." Reframe — the prompt is what changes; the same model gives vague answers to vague asks and strong answers to well-structured ones (role, context, examples, format).
• Responsible-AI point (integrity): be explicit about the academic-integrity boundary — AI is a tool to learn and draft with, not a ghostwriter to submit. Disclosure/citation is the honest default; schools and competitions expect it.
• Responsible-AI point (hallucination + privacy): every important claim gets fact-checked; personal and sensitive data never goes into a prompt; API keys stay private.
• Bias: remind students the model can repeat society's biases, so its outputs about people deserve extra scrutiny.
• Fast finishers (extension): Ground it (mini-RAG) — paste a trusted source into the prompt and instruct "answer only from this text," then compare to the AI answering from memory (fewer hallucinations). Evaluate systematically — write 5 test questions with known answers and score the bot's replies, the way real AI teams measure quality. Ethics in your report — add a line to any competition project stating how AI was used and checked.
• Low-tech fallback: if student devices are limited, build and tune one class chatbot on the shared screen, taking system-prompt suggestions from the room and running the tests together.

Vocabulary

Resources

• Google AI Studio — free playground + API (with a grown-up).
• Learn Prompting — patterns, examples, best practices.
• Google — Be Internet Awesome / AI literacy — responsible AI use.

Next session

This is the final bonus session of the course. Students can now understand, build with, and responsibly use generative AI — a perfect edge for their competition project and portfolio.