Week 1 (Friday): Foundations - the reliable reasoning component

8 lessons · Back to full syllabus

What you keep

How to turn a model call into a dependable, observable piece of software.

You ship

A working `/ask` endpoint that answers reliably - the reasoning core of your capstone.

Watch through (async)

Think Like an AI Engineer (free 10-part series)

Watch this YouTube playlist before or alongside Week 1. Plain-English foundations - how LLMs work, prompting, models, context, agents, workflows, and evals - so the live FastAPI and reliability work clicks faster.

  1. 1How LLM Actually Works (in Plain English)Watch
  2. 2How to Prompt AI Like a Pro: The 5-Part FormulaWatch
  3. 3How to Pick the Right AI Model for the JobWatch
  4. 4Using AI With Your Files, Images and DataWatch
  5. 5Context Is Everything: The #1 Skill for Using AIWatch
  6. 6Vibe Coding for Non-Engineers (and Engineers)Watch
  7. 7What AI Agents Actually Are (Hype vs Reality)Watch
  8. 8Build AI Workflows With No Code (n8n, Zapier, Make)Watch
  9. 9AI Evals: How to Know If Your AI Actually WorksWatch
  10. 10The Fastest Way to Stay Current in AIWatch

Live session resources

Lessons

Live

From model call to reliable component

Production means the right shape, at a known cost, with a plan for when it fails - every time.

Read lesson
Live

The OpenAI API and the Playground

Experiment in the Playground first: system vs user messages, temperature, max tokens, and the token counter.

Read lesson
Live

FastAPI and the /ask endpoint

Wrap the model in typed software: POST /ask returns the answer plus tokens used.

Read lesson
Live

Prompting with rigor

Structured outputs, few-shot, and decomposition - tested live against your own endpoint.

Read lesson
Live

Output guardrails and validation

Validate the response matches your schema; reject or retry on malformed output.

Read lesson
Live

Token economics

Treat the context window as a budget - few-shot, system prompts, and verbose outputs all cost on every call.

Read lesson
Live

Model selection

Match capability, cost, and latency - swap models on the same endpoint and watch tradeoffs move.

Read lesson
Assignment

Ship your reliable reasoning endpoint

Schema-validated answer, token usage, guardrail on malformed output, and a justified model choice.

Read lesson