ZENITHLABGet access
Zenith Lab
Build AI Agents & LLM AppsSelf-paced course

AI Engineering

The real stack behind production AI products: prompting, retrieval, agents, tool use, structured outputs, and evaluation, applied to a real shipped product, not a toy chatbot.

8
modules
11
in-app pages
6.5h
of module content
Full curriculum

9 modules, in order

  1. 0Orientation
    What this field actually is, what people in it actually build, where you might fit, and exactly what the next 8 modules will (and won't) teach you.
Stage 0 · Prompting foundations
  1. 1Prompting & Structured Outputs45m
    A language model produces text. Your program needs data. This module closes that gap reliably, not with a nicer-sounding prompt, but with validation and repair logic that doesn't trust the model to behave.
  2. 2Context Windows & Token Economics40m
    Every prompt has a budget, measured in tokens, not characters or "how much text feels reasonable." The actual arithmetic for what fits, what it costs, and what to do when your content doesn't fit.
Stage 1 · Retrieval and tools
  1. 3Retrieval-Augmented Generation45m
    A model only knows what's in its prompt. Retrieval decides, out of everything you could put there, which pieces actually get in, by searching, not by hoping the right chunk made the cut.
  2. 4Tool Use & Function Calling45m
    A model can only produce text. Everything it does beyond that, looking something up, sending an email, charging a card, happens because a tool call it generated got executed by your code. That execution step is where correctness and safety actually live.
Stage 2 · Agents in production
  1. 5Agent Architectures & Control Flow45m
    An agent is what happens when a model chains steps together, reasoning about each result before deciding the next action, in a loop it controls. That loop needs boundaries, or it doesn't stop on its own.
  2. 6Reliability for LLM Systems40m
    Model APIs fail: rate limits, timeouts, transient server errors. Some failures are worth retrying, some never will succeed no matter how many times you try, and treating them the same wastes time, money, and your users' patience.
  3. 7Evaluation, Testing & Observability40m
    "I tried a few prompts and it looked good" isn't evaluation, it's a vibe check on a handful of lucky examples. A systematic way to measure whether a system is actually working, and whether a change made it better or worse.
Stage 3 · Capstone
  1. 8Capstone: A Production AI Agent90m
    A client brief: a support bot that must answer from a knowledge base, act on tools safely, run inside a bounded loop, and survive a flaky model API, graded against a rubric, not vibes.
Inside the course

4 sections, 11 real pages

Learn5 pagesCourse structure, reference material, and where you left off
  • DashboardYour home base: progress, streaks, and what's next
  • SyllabusThe full course outline, module by module
  • Learning RoadmapThe whole journey mapped on one page
  • Cheat SheetsPrintable quick-reference for every tool
  • Python FoundationsPython fundamentals, taught for this course specifically
Practice2 pagesExtra reps, quizzes, and skill tracking
  • Quiz CenterEvery module's quiz, plus a cumulative final
  • ChallengesCross-module challenges that gate the capstone
Build1 pageThe real projects and labs you'll actually ship
  • ProjectsThe real portfolio projects you'll build
Evidence3 pagesPortfolio, career path, and proof you can show
  • Final AssessmentA cumulative assessment across every module
  • My PortfolioEvery completed project, auto-summarized
  • Career PathCareer Path Edition: readiness and job-landing playbook
What you'll actually do
  • Write prompts that produce reliable, structured output
  • Ground a model on your own data with retrieval
  • Build agents that use tools and take real actions
  • Evaluate outputs instead of eyeballing them
  • Control cost and latency as usage scales
  • Ship a real product with real evals behind it
Tools and topics covered
PromptingRetrievalAgentsTool UseStructured OutputsEvaluationCost & Latency
Why it matters

Retrieval can ground an LLM on information outside its training data.

Tool use lets an AI system interact with external systems, not just generate text.

Evaluation is necessary because a response that sounds right can still be wrong.

Prompting is only one part of a production AI system.

Cost and latency become real engineering constraints once an AI application scales.

Career Path Edition

A shipped AI product with evals you can point to in an interview, whether you're moving into AI engineering freelance or hired.

Ready to start? Self-paced, start whenever you are.

Get access