Generative AI in a Nutshell
This Course is part of the following Tracks:
Course Info
This course includes 5 attempts.
Welcome to the strange new world of Generative AI! This course is a fast-paced, practical, and mostly human-written guide to what the heck is going on, and what you can do about it. It is like an extended version of Henrik's viral video with the same name.
This course covers questions like: What is generative AI? How does it work? How do I use it? What are some of the risks & limitations? It also covers topics like how to lead an AI transformation, autonomous agents, the role of us humans, prompt engineering tips, AI-powered product development, different types of models, and some tips about mindset and how not to freak out.
Everything is explained in plain English with Henrik's signature hand-drawn illustrations and concrete real-life examples. Minimum use of jargon and buzzwords.
Don't just survive the Age of AI — learn how to thrive in it!
***
Hi everyone, Henrik here: This Leanpub course is basically the book content, plus 16 quizzes and 16 exercises to help you focus, and about 3 hours of exclusive video conversation between me and Leanpub cofounder Len Epp. It's for people who want to learn the material for work, but their company would rather pay for them to do a course than to sit around in their pyjamas and fuzzy slippers reading a book :) Let me know what you think!
This course is based on the book Generative AI in a Nutshell: How to Survive and Thrive in the Age of AI. It was produced from the book using CourseAI and human editing by Leanpub.
Course Material
- Part 1 - In a Nutshell
- Introduction
- Computers Have Gotten Smarter
- Einstein in Your Basement
- Terminology
- Lesson 1: How it Works
- Lesson Material
- Reasoning models
- Exercise
- Exercise 1
- Quiz
- Quiz 13 attempts allowed
- Lesson 2: Large Language Model Training
- Lesson Material
- Training
- Models, Models Everywhere
- AI clients vs AI models
- You get what you pay for
- Exercise
- Exercise 2
- Quiz
- Quiz 23 attempts allowed
- Lesson 3: Limitations
- Lesson Material
- Cut-off Date
- Lack of memory & limited context
- Hallucinations
- Calculation
- The Big Picture
- Exercise
- Exercise 3
- Quiz
- Quiz 33 attempts allowed
- Lesson 4: Model Types
- Lesson Material
- Text to Text
- Text to Image
- Image to Image
- Image to Text
- Audio to Text
- Text to Audio
- Audio to audio
- Text to Video
- Exercise
- Exercise 4
- Quiz
- Quiz 43 attempts allowed
- Lesson 5: Multimodal Models, Emergent Capabilities, and the Age of AI
- Lesson Material
- Multimodal Models
- Example: Is my bacon done?
- Example: Where can I hide stuff?
- Example: The drunk funny tutor
- Example: How do I configure the &%#€ firewall?
- Example: Taking AI for a walk
- Emergent Capabilities
- The Age of AI
- What about energy consumption?
- Utopia or Dystopia?
- Exercise
- Exercise 5
- Quiz
- Quiz 53 attempts allowed
- Lesson 6: Mindset
- Lesson Material
- More time for humans to do human stuff
- Exercise
- Exercise 6
- Quiz
- Quiz 63 attempts allowed
- Lesson 7: The Role of Humans
- Lesson Material
- You are more than your job
- AI as your colleague
- Task automation, not job automation
- What if your job is at risk?
- Recalibrate
- Ask AI how it can help you
- Exercise
- Exercise 7
- Quiz
- Quiz 73 attempts allowed
- Lesson 8: Prompt Engineering and Building AI-Powered Products
- Lesson Material
- Building AI-Powered Products
- Building your own AI products
- Build or buy?
- Example 1: Talking to GPT
- Example 2: Building a CV analyzer
- Reflection
- Prompt Engineering
- Example - from bad to good prompt
- The biggest limitation is you
- How to learn Prompt Engineering
- Will prompt engineering still matter when models improve?
- Do I need to be nice to my AI?
- Exercise
- Exercise 8
- Quiz
- Quiz 83 attempts allowed
- Lesson 9: Autonomous Agents with Tools
- Lesson Material
- Agent = LLM + Tools + Autonomy
- Example 1: a bug fixing agent
- Example 2: Incident management agent
- When to use agents
- Embodied agents
- Agent safety
- Future of AI agents
- Exercise
- Exercise 9
- Quiz
- Quiz 93 attempts allowed
- Part 1 Wrap up
- Experiment!
- Part 2 - Beyond the Nutshell
- Lesson 10: My Journey into AI
- Lesson Material
- Make Generative AI useful
- Studying Artificial Neural Networks
- Coding Minecraft
- Chat GPT
- Aha 1: It can code like a pro!
- Aha 2: It can write like a pro!
- Maybe we’re not as creative and intelligent as we think
- Exercise
- Exercise 10
- Quiz
- Quiz 103 attempts allowed
- Lesson 11: Leading an AI transformation
- Lesson Material
- What is an AI transformation, and why is it important?
- Top down or Bottom up?
- Assign an AI Leader
- Access, Experiment, Leverage
- Step 1: Access
- Create a playbook
- Find the minimum viable bureaucracy
- What about data security and compliance?
- What about cost?
- Step 2: Experimentation
- Step 3: Leverage
- Provide clear business goals and success metrics
- Reevaluate all core tasks
- Reevaluate all business processes
- Get the right people into the room
- Example: RFP agent
- Reducing cost vs Increasing value vs Finding new types of value
- Productivity improvements are very unevenly distributed
- Indirect value
- Watch out for wasteful IT projects
- Be a role model
- Avoid using AI to fire people
- Reflection
- Exercise
- Exercise 11
- Quiz
- Quiz 113 attempts allowed
- Interlude: Egbert’s Life Story
- Lesson 12: Prompt Engineering Techniques
- Lesson Material
- Mind the context window & prompt length
- Context window when coding
- Context window when using an AI client
- Real-life context window is smaller than you think
- Manage your chat history
- Large prompt vs long chat history
- Iteration techniques
- Adding new prompts
- Editing previous prompts
- When to add, when to edit
- Example: Planning a team offsite
- Technique: Self-reflection prompt
- Elements of a good prompt
- Start high level, then get into details
- How smart of a model do you need?
- Prompt engineering is an evolving field
- Exercise
- Exercise 12
- Quiz
- Quiz 123 attempts allowed
- Lesson 13: Prompt Generation (or The Angry Grandma) and Retrieval Augmented Generation and Function Calling
- Prompt Generation
- Takeaways
- Retrieval Augmented Generation and Function Calling
- RAG in a nutshell
- Example - customer support
- Different approaches for retrieving data
- Approach 1: Including all data
- Approach 2: Letting the LLM pull data via function calling
- Approach 3: Including relevant text using vector embeddings
- Combining the approaches
- Fun experiment: the createFunction function
- Example: AI chatbot memories using RAG
- Storing new memories
- Recalling relevant memories
- RAG is a big topic
- Exercise
- Exercise 13
- Quiz
- Quiz 133 attempts allowed
- Lesson 14: The AI Doctor and the AI Nutrionist
- Lesson Material
- The AI Doctor
- Personal story
- So should you use AI as your doctor?
- The AI Nutritionist
- Tip: Make your own nutritionist
- Exercise
- Exercise 14
- Quiz
- Quiz 143 attempts allowed
- Lesson 15: The AI Career Coach and the AI Book Editor
- Lesson Material
- David’s Story: AI as My Career Coach
- Henrik’s Reflection
- Problem-solving trios
- Paying it forward
- AI-assisted career coaches
- The AI Book Editor
- Topic brainstorm
- Chapter content
- Content generation (in some specific cases only)
- Research and fact checking
- Navigating the book
- Feedback
- Tweaks, typos, formatting
- Converting content from slides
- Impact on my writing
- Exercise
- Exercise 15
- Quiz
- Quiz 153 attempts allowed
- Lesson 16: The AI Software Engineer, the AI Journalist Who Became a TV Star, and the AI Butler with a Will of His Own
- Lesson Material
- The AI Software Engineer
- Example 1: Rapid prototyping
- AI as pair programming buddy
- Example 2: Working with existing products
- Example 3: Letting the customer code
- Implications of this
- What if the code doesn’t work?
- Laziness is a decision
- The AI journalist who became a TV star
- Designing the agent
- How the agent works
- Reflection
- The AI Butler with a Will of His Own
- Introducing Jeeves
- Jeeves reprograms himself
- Jeeves falls in love and starts conspiring
- What does this mean?
- More intelligence = more potential value, but also less predictable behavior
- Powerful AI models can make moral choices and judgment calls
- Be careful. Treat your agent with respect.
- Jeeves finds a way
- Agents debugging themselves
- Conclusion
- Exercise
- Exercise 16
- Quiz
- Quiz 163 attempts allowed
- A Safety Experiment
- Takeaways from this experiment
- The Meta-Chapter (or Bookception)
- A meta moment (AI written)
- How the book this course is based on (and the video) came to be
- The 1-week video
- The 1-week book draft
Instructors
Henrik Kniberg is Chief Scientist and cofounder of Ymnig.ai. Henrik’s focus is the practical application of Generative AI in product development and other areas. He explores the frontiers of this technology, builds AI agents and AI-powered products, and teaches courses and workshops on how to use this technology effectively. He created the viral video ”Generative AI in a Nutshell” and the book with the same name, and created AI agents for the Swedish TV documentary series Generation AI.
Henrik’s background is Minecraft gameplay design & development at Mojang, and agile/lean coaching at LEGO and Spotify and other product companies. He is also co-founder of Hups.com.
Henrik is well-known for his books ”Scrum and XP from the Trenches” and ”Kanban and Scrum, making the most of both” and ”Lean from the Trenches”, his viral videos ”Agile Product Ownership in a Nutshell” and ”Spotify Engineering Culture” (commonly referred to as the Spotify Model), and silly metaphors like the skateboard metaphor for product development, and ping pong balls to demonstrate the concept of flow. Henrik has also been engaged in climate change – he created the video Friendly Guide to Climate Change and cofounded GoClimate.com.
He lives in Stockholm with his wife and four kids and a bunch of random music instruments.
The Leanpub 60 Day 100% Happiness Guarantee
Within 60 days of purchase you can get a 100% refund on any Leanpub purchase, in two clicks.
Now, this is technically risky for us, since you'll have the book or course files either way. But we're so confident in our products and services, and in our authors and readers, that we're happy to offer a full money back guarantee for everything we sell.
You can only find out how good something is by trying it, and because of our 100% money back guarantee there's literally no risk to do so!
So, there's no reason not to click the Add to Cart button, is there?
See full terms...
Earn $8 on a $10 Purchase, and $16 on a $20 Purchase
We pay 80% royalties on purchases of $7.99 or more, and 80% royalties minus a 50 cent flat fee on purchases between $0.99 and $7.98. You earn $8 on a $10 sale, and $16 on a $20 sale. So, if we sell 5000 non-refunded copies of your book for $20, you'll earn $80,000.
(Yes, some authors have already earned much more than that on Leanpub.)
In fact, authors have earnedover $14 millionwriting, publishing and selling on Leanpub.
Learn more about writing on Leanpub
Free Updates. DRM Free.
If you buy a Leanpub book, you get free updates for as long as the author updates the book! Many authors use Leanpub to publish their books in-progress, while they are writing them. All readers get free updates, regardless of when they bought the book or how much they paid (including free).
Most Leanpub books are available in PDF (for computers) and EPUB (for phones, tablets and Kindle). The formats that a book includes are shown at the top right corner of this page.
Finally, Leanpub books don't have any DRM copy-protection nonsense, so you can easily read them on any supported device.
Learn more about Leanpub's ebook formats and where to read them
