AI 101

A deep dive introduction to model capabilities, context design and engineering and experience evaluation.

What we will discuss:

  • What is context design?
  • Let's try an eval.
  • What is context engineering?

Understanding models

  • Models are stochastic.
  • Models are stateless.
  • How should I think about model capabilities?
  • Why do models have different personalities?

Who is this for?

  • Anyone trying to better understand LLMs.
  • Non-engineers who want to learn the basic activities that build great AI experiences.
  • Team leaders that are looking for some grounding in the underlying technology.

Start your free trial

Start a 15-day free trial to unlock every episode. Cancel any time.

1. Introduction

2. Getting our hands dirty

Episode 2.1 · 5:55
Context Design Exercise

Let's do some context design. The model's context window is the key to creating useful and helpful output.

Free
Watch →
Episode 2.2 · 6:35
Context Engineering Exercise

So we did some context design - now how does that become context engineering?

Members only
Episode 2.3 · 5:35
Evals Exercise

And the final missing piece: evals! But wait, do we even need them here?

Members only

3. Model basics

Episode 3.1 · 4:17
Models are Stateless

What does it mean for models to be stateless? Let's build some intuition around that.

Free
Watch →
Episode 3.2 · 4:26
Models are Stochastic

And what does it mean for models to be Stocastic? Why do they hallucinate? Can we ever get beyond that?

Members only
Episode 3.3 · 2:35
A model warning

Some common misunderstandings about AI and Large Language Models can easily lead us astray.

Members only

4. Model Capabilities

Episode 4.1 · 6:05
Introduction to Model Capabilities

What can LLMs do? How do we know what the capabilities of these models are? How are they trained? And how does that influence our product design decisions?

Members only
Episode 4.2 · 9:47
Model Post Training and RLHF

How are capabilities trained into models? How can we build intuition around these capabilities and best use them?

Members only
Episode 4.3 · 3:55
Why do models have different personalities?

What is model character, how is it trained, and how can we learn to understand and use this beyond "Claude feels friendlier"?

Members only

What participants say

“This is opening up all sorts of new neural pathways for me to see under the hood more of how the sausage is made! 🙏”
Maya Lindgren · Senior UX Designer
“Very timely at my enterprise software company as evaluation of AI features scales.”
Daniel Reyes · Principal Product Designer
“Everything I know about evals is from Peter's talk, which is why I'm back to find out more!”
Anneke Visser · UX Researcher

Ready to get started?

15-day free trial. Cancel any time.