AI can write the code. Can it judge the code? This track builds the one thing AI can't hand you — the judgment to test, orchestrate and command AI systems: LLM foundations, prompt craft, agents, RAG, evaluations and the tooling companies actually run.
In an AI-coding world, an entry-level engineer's primary value is testing, orchestration and judgment — not syntax recall. So we build it deliberately, and make you prove it on real AI-agent work.
AI writes the code now. The skill that lasts is the judgment to test, orchestrate and command it — so we build that deliberately, across a full track of LLMs, agents, RAG and evals.
Every concept is exercised on real work: the Prompt Lab runs and scores your prompts, and you operate your own agent — Xook — propose-and-approve, its audit log becoming your portfolio.
Hallucination, prompt injection, data leakage, runaway cost — you learn the failure modes and the guardrails, tied to real incidents.
A build-first path from how models work to orchestrating governed AI tools your company can rely on — judgment at every step.
How large language models actually work: tokens, context windows, temperature, cost and latency trade-offs, and where models fail — so you can judge their output instead of trusting it blind.
COSTAR and canonical technique — role framing, few-shot, structured output, delimiters, chain-of-thought and anti-hallucination — practised live in the Prompt Lab, where every rewrite is scored.
Retrieval-augmented generation end to end: chunking, embeddings, vector stores, hybrid search, re-ranking, grounding and citations — and the judgment to tell a grounded answer from a confident hallucination.
Planning, tool/function calling, memory, multi-step loops and guardrails. Orchestrate agents that do real work safely — and hold the judgment to know when an agent is the wrong tool.
You can't command what you can't measure: build eval sets, judge outputs, catch regressions, trace tokens and cost, and keep quality from drifting in production.
Build the internal tools companies run: retrieval over private docs, gateways and key management, MCP tool servers, and putting a human — with judgment — safely in the loop.
Every module ends in something that runs, and every decision lands in your auditable record — not a quiz.
Write a prompt, watch it run against a real model, and get scored on COSTAR with an optimized rewrite and rationale.
Chunk and embed a corpus, retrieve, ground the answer with citations, then judge whether it actually improved.
Give Xook tools and a goal, set the guardrails and memory, and command it — propose-and-approve — as it plans and executes, every decision logged.
Build an eval set, judge outputs at scale, and catch the regression before your users do.