SkillUp AI · Session 1 of 6
90 minutes · Interactive · Zero prerequisites
| 1 | The AI Hierarchy — Demystifying the buzzwords | 15 min |
| 2 | How GenAI Works — Tokens, prediction, temperature | 20 min |
| 3 | What AI Can Do — Real-world use cases | 15 min |
| 4 | AI on AWS — Services that matter | 10 min |
| 5 | Prompt Tips — A taste of prompting | 10 min |
| 6 | PartyRock Exercise — Build your first AI app | 15 min |
| 7 | Wrap-Up & Next Steps | 5 min |
"Which of these have you used?"
ChatGPT · Claude · Gemini · Kiro · None
"How confident are you explaining AI to a colleague?"
1 = No idea → 5 = Could teach it
🎯 Goal: By the end, you'll be able to explain AI to anyone.
Part 1
🔵 Artificial Intelligence — Machines that mimic human intelligence
🟣 Machine Learning — AI that learns from data (no hard-coded rules)
🟡 Deep Learning — ML using neural networks (inspired by the brain)
✨ Generative AI — DL that creates new content (text, images, code)
GenAI is what's new — it's the reason for today's AI wave
| Layer | Example |
|---|---|
| AI | Spam filters, voice assistants (Siri, Alexa) |
| ML | Grab's route optimization, fraud detection at banks |
| DL | Face recognition on your phone, medical image analysis |
| GenAI | ChatGPT writing emails, Claude answering questions, Midjourney images |
AI = All of cooking
ML = A specific technique (like stir-frying)
DL = A sophisticated version (mastering wok hei)
GenAI = A chef that invents entirely new recipes
Part 2
AI reads billions of pages — learns patterns in language
Text splits into "tokens" — chunks, not whole words
Predicts the most likely next token — one at a time
Repeat step 3 thousands of times → paragraphs appear
AI doesn't read words — it reads tokens
"Understanding" → Under + stand + ing = 3 tokens
"AI" → AI = 1 token
"สวัสดีครับ" → สวัสดีครับ = ~4 tokens
💰 Cost insight: AI pricing is per-token. Thai uses ~3x more tokens than English for the same meaning — multilingual content costs more!
The world's most sophisticated autocomplete
"The cat sat on the ___"
mat (45%) · floor (22%) · chair (15%) · table (8%) · ...
AI picks the most likely next token, adds it, then predicts again.
This is how it writes paragraphs, code, and poems.
⚠️ AI doesn't "understand" like humans. It predicts what sounds right based on patterns — not what IS right.
→ That's why AI sounds confident even when wrong
→ It's not lying — it's predicting tokens that pattern-match well
→ Always verify: numbers, dates, names, specific claims
Factual, predictable
Use for: compliance reports, data extraction, summaries
Balanced, reliable
Use for: emails, reports, general Q&A
Creative, unreliable
Use for: brainstorming only — verify everything
👔 Analogy: Low = your cautious compliance officer · Medium = reliable PM · High = creative strategist
Part 3
| Capability | Example | For |
|---|---|---|
| 📋 Summarize | 30-page report → key bullet points | All roles |
| ✍️ Draft | First-draft emails, proposals, SOPs | All roles |
| 🗂️ Classify | Sort: invoice / receipt / contract | Ops, Finance |
| 🔍 Extract | Pull names, amounts, dates from docs | Finance |
| 🌏 Translate | Content across ASEAN languages | Regional |
| 💻 Code | Generate scripts, automate tasks | Tech |
| 📊 Analyze | Identify patterns, anomalies, trends | Analytics |
🎯 Rule of thumb: Use AI for first drafts and pattern recognition. Use humans for final decisions and verification.
Part 4
Access to top AI models (Claude, Titan, Llama) via API
AI assistant that answers from your company's data
AI-powered development environment — specs, steering, agentic workflows
No-code AI app builder — free, no AWS account needed
You don't need to build these — just know they exist so you can ask the right questions.
Part 5
Most people talk to AI like a search engine
→ And get bad results
🔑 The fix: Talk to AI like you're briefing a smart colleague who's never worked at your company.
❌ "Write about Q3 results"
✅ "Write a 3-bullet executive summary of Q3 results for our board deck. Keep it under 100 words. Focus on revenue growth and market expansion in SEA."
❌ "Summarize this document"
✅ "I'm a finance manager preparing for a leadership review. Summarize this audit report into 5 key findings. Flag anything needing immediate action."
"Make it shorter" →
"Add bullet points" →
"Make the tone more formal" →
"Add a call-to-action at the end"
AI gets better in conversation. Don't start over — refine.
Part 6 — Hands-On
A free playground from AWS to explore AI by building apps.
partyrock.aws
1️⃣ Tell Whiskers what you need — describe your app in plain language
2️⃣ Watch it build — input fields, AI outputs, everything wired together
3️⃣ Try it & iterate — adjust through conversation with Whiskers
4️⃣ Share it — anyone with the link can use your app instantly
Build an AI-powered app for your job
Go to partyrock.aws → Click "Create an App"
Ideas to try:
Be specific — "Create a tool that generates 3 email reply options: formal, friendly, and brief"
Add constraints — "Keep outputs under 100 words" or "Use bullet points"
Give context — "This is for a finance team in Southeast Asia"
Iterate with Whiskers — "Add a dropdown for tone" or "Make the output include a subject line"
"What app did you build (or want to build)?"
We'll react to the most creative ones live!
Wrap-Up
✅ AI → ML → DL → GenAI — you now know the hierarchy
✅ Next-token prediction — AI is fluent but not always factual
✅ Temperature — low for facts, high for brainstorming
✅ AI can summarize, draft, classify, extract, translate, code, analyze
✅ PartyRock — you can build AI apps with zero code
✅ Prompt tips — be specific, give context, iterate
This week, try ONE AI task at work:
Summarize meeting notes · Draft an email · Ask AI to explain something · Build a PartyRock app
| Course | Duration | Type |
|---|---|---|
| AI Practitioner Learning Plan | 8 hours | Learning Plan |
| AI Practitioner Power Hour | 6 hours | Learning Plan |
| Fundamentals of Generative AI | 1.5 hours | Digital Course |
| Machine Learning Basics | 30 min | Digital Course |
| GenAI Fundamentals — Terminology | 10 min | Quick Start |
| Cloud Quest: GenAI Practitioner | 10 hours | Gamified |
All free on skillbuilder.aws · Requires active Skill Builder account
Live Prompt Engineering Workshop
Hands-on techniques · Chain-of-Thought · Personas · Structured Outputs · AI Judge Competition
Interactive explainer: session1-ai-for-everyone.html
PartyRock: partyrock.aws · Skill Builder: skillbuilder.aws