Masterclass · Intermediate

A Deeper Understanding of LLMs

Stop guessing. Start steering the model.

Most developers use LLMs by trial and error. This masterclass unpacks what's actually happening inside the box — tokens, context windows, sampling, tool use, caching — so you can write prompts and build systems that work reliably.

Join the Waitlist See Other Masterclasses

Duration

1 day · 2-3 hours

Level

Intermediate

Format

Slides + live demo on Zoom / Google Meet

What you'll walk away with

By the end of the session.

✓

A concrete mental model of how LLMs process your input

✓

Techniques to debug why a prompt isn't working

✓

Patterns for structured output, tool use, and caching

Syllabus

What we'll cover.

1Tokens, context windows, and why they matter
2Sampling: temperature, top-p, and when each matters
3Structured output: JSON mode, tool use, schema design
4Prompt caching and cost optimization
5Debugging: what to do when the model 'just won't listen'

Prerequisites

What you need before you join.

●You've used an LLM API at least once
●Comfortable reading code in any language

Tools we'll use

Bring these, or install during setup.

Anthropic / OpenAI APIA notebook environment

Reserve your spot

Join the waitlist for A Deeper Understanding of LLMs.

We'll email you when the next cohort opens. Early signups get launch pricing.