LLM Foundations
Understand how language models work and call them reliably from code.
01
This program is for developers who want a clear, working understanding of large language models before building on them. It skips the hype and focuses on the concepts that directly affect the code you write: tokens, context limits, sampling, and API behavior.
You will write Python that calls a hosted model API or a local open-weight model, handles streaming and errors properly, and returns structured data validated with Pydantic. You will also learn to structure prompts so they are easier to test and maintain.
The final exercise is a small command-line tool or API endpoint that extracts structured information from unstructured text, with a handful of tests that check its output.
if over budget → trim history first, then lowest-ranked chunks
02
03
A working mental model of what happens between your prompt and the model's response.
Call models from Python in a way that holds up outside a notebook.
Write prompts that are clear, testable, and easy to change.
Get data, not prose, from a model — and verify it.
04
Related project briefs
Outcomes describe skills and artifacts you will practice. No certification, employment or career outcome is guaranteed.
05
LLM Application Engineering
Alex focuses on the unglamorous parts of LLM products: input validation, structured outputs and graceful failure. Their sessions are about turning a promising prototype into code a team can maintain.
Sample profile06
Using a chat interface and building with model APIs are different skills. If you are already comfortable with tokens, streaming, and structured outputs in code, you can move directly to an intermediate program.
07
Register your interest and tell us about your experience. We’ll suggest where to start.