◎TRACK 01
LLM Evaluations
Define what good looks like. Catch unsupported claims, design rubrics, and question the judge.
50 questions · Foundations
Don’t just learn AI.
Put it to work.
Build the judgment behind reliable AI. Practice LLM evaluations, RAG, and agents with focused questions and clear explanations.
150 questions · 15 free samples · Sign in to save progress
YOUR NEXT REP● LLM EVALUATIONS
SPOT THE FAILUREA confident answer.
A confident answer.
But is it grounded?
A support assistant cites a refund policy that isn’t in the source. What should your evaluation catch?
Response length
Unsupported claims ✓
Response speed
One scenario. A sharper instinct.●●●
Built around real AI decisions◎ Practice with realistic scenarios↳ Get explanations, not just scores▥ Build one skill at a time
CHOOSE YOUR TRAINING GROUND
Three tracks. Practical skills.
▤TRACK 02
RAG Systems
Find the right evidence. Diagnose retrieval misses, handle policy versions, and ground your answers.
50 questions · Foundations
⌘TRACK 03
AI Agents
Give agents useful boundaries. Choose tools, handle missing information, and design approval steps.
50 questions · Foundations
NEW TRACK
Case Studies
CASE 01 · FREE BETA
The refund chatbot investigation
A chatbot gives incorrect refund advice. Inspect the trace, find the cause, choose a fix, and decide whether to release it.
15–20 minutes · 5 decisions · Saved progressStart case study ↗
CASE 02 · FREE
The invoice that tried to send an email
Close the gap between “ignore malicious instructions” and code that actually blocks unauthorized actions.
5–8 minutes · 5 steps · Optional interview responseStart case study ↗
CASE 03 · FREE
Your chatbot scores 95%—why are users complaining?
Audit a misleading evaluation, build a targeted test, and defend a release decision using new evidence.
7–10 minutes · 5 steps · Optional interview responseStart case study ↗
25 GUIDED CASES · MEMBERS
Engineering case library
Work through RAG, agents, evaluation, performance, and security scenarios with five guided steps.
Case Studies or Complete membershipExplore case library ↗
PRICING
Choose your practice.
Monthly subscriptions · USD
Questions
$9.99 /month
150 questions across LLM Evals, RAG, and Agents.
- Concept explanations after every answer
- Saved progress and mistake review
QUESTIONS + CASE STUDIES
Complete practice
$19.99 /month
150 questions and 25 guided case studies.
- All question-pack features
- Guided technical decisions and interview practice
Case studies
$12 /month
25 guided case studies without the question pack.
- Step-by-step scenarios with feedback
- Optional interview responses