Blacksky Up
LLM 101: Language Models & You — Blacksky Up Course
What Is LLM 101?
LLM 101 is a two-week, hands-on introduction to the AI technology reshaping every industry. No coding. No prerequisites. Just clear thinking and curiosity. Students leave with a real understanding of how large language models work, why they sometimes fail, and how to build with them intentionally.
This is not a course about using AI — it's a course about understanding it.
Course At a Glance
| Detail | Info | |---|---| | Program | Blacksky Up | | Duration | 2 weeks, 4 sessions | | Format | Live, instructor-led | | Prerequisites | None — curiosity is the only requirement | | Tools Used | Claude Projects or NotebookLM (no accounts needed during class) | | Disciplines | Media · Technology · Business · Arts | | Capstone | No-code RAG chatbot + live demo presentation | | Cost | Free |
Week 1 — Understanding the Machine
Session 1: How LLMs Think (and How They Don't)
Core Concepts:
- What training actually means — in plain English
- Tokens and context windows — the basic unit of how LLMs read and respond
- Why models hallucinate — pattern completion vs. factual retrieval
- The pattern-completer mental model — smart, but not thinking
Hands-On Activity:
- Prompt experiments in the browser — observe how small wording changes shift outputs dramatically
- Group discussion: where did the model get it right? Where did it fail, and why?
Session 2: Prompting as Design
Core Concepts:
- Prompting is a design discipline — not a technical skill
- System prompts, personas, and constraints
- Few-shot examples and how to frame context
- Temperature and creativity as system levers
Hands-On Activity:
- Prompt redesign workshop — students receive a poorly written prompt and rewrite it
- Compare outputs before and after redesign; discuss what changed and why
Week 2 — Building with Structure
Session 3: What RAG Actually Is
Core Concepts:
- Why prompting alone isn't enough — the hallucination problem at scale
- What "grounding" means and why it matters
- Embeddings as a way of measuring meaning — no math, just the concept of similarity
- Vector stores as organized memory
- The full RAG pipeline as a system: ingest → retrieve → generate
Hands-On Activity:
- Visual mapping exercise — students diagram the RAG pipeline for a real-world use case
- Group Q&A: where does retrieval fail? What kinds of questions can't it answer?
Session 4: Demo Day — Present Your Chatbot
Format:
- Each student presents their RAG chatbot (10 minutes per student)
- Explain the document set chosen and why
- Show the chatbot answering questions well
- Intentionally break it — show a question it gets wrong and explain why
- Group feedback and discussion after each demo
Capstone Project — Your RAG Chatbot
The Challenge: Build a chatbot that can answer questions about the future of your field — using retrieval-augmented generation.
Project Requirements:
- Select 3–5 documents focused on the future of your chosen discipline (Media, Tech, Business, or Arts)
- Documents can be articles, reports, essays, or transcripts — PDFs and text preferred
- Build your chatbot using Claude Projects or NotebookLM (no coding required)
- Test thoroughly before Demo Day — find its limits
Demo Day Criteria:
- Explain your document set and the question you were trying to answer
- Demonstrate at least 3 strong responses from your chatbot
- Demonstrate at least 1 failure — and explain why it failed
- Share one insight about AI or your field that building this taught you
Learning Outcomes
By the end of LLM 101, students will be able to:
- Explain how large language models work at a conceptual level
- Write clear, effective prompts for a range of real-world tasks
- Understand the RAG architecture and why it matters for knowledge work
- Build and evaluate a no-code RAG chatbot over their own document set
- Identify where AI systems succeed and where they fail — and why
Common questions
Do I need to know how to code to take LLM 101? No. Zero coding required. The tools used — Claude Projects and NotebookLM — are no-code. If you can type and think, you can take this course.
What will I walk away with? A real working RAG chatbot you built yourself, the ability to explain how LLMs work to anyone, and practical prompt-writing skills you can use immediately.
What disciplines is this course for? All four — Media, Technology, Business, and Arts. The capstone lets students focus on the future of their own field.
How long is LLM 101? 2 weeks, 4 sessions. Live and instructor-led.
Is LLM 101 free? Yes. Free education. Real knowledge. No exceptions.
What's the difference between LLM 101 and NLM 101? LLM 101 covers how AI thinks with language — how models are trained, how prompting works, and how RAG systems are built. NLM 101 is the counterpart: how intelligence emerges without language — through swarms, sensors, and emergent behavior. They complement each other and can be taken in either order.
What is RAG? RAG stands for Retrieval-Augmented Generation. It's the system architecture that makes AI useful for real-world knowledge work — instead of the model just guessing from training data, it retrieves relevant documents and uses them to generate grounded, accurate answers. LLM 101 teaches this from concept to hands-on build.