Labs · 8 projects

Build it once, and you will believe you can.

Reading gives you ideas. A lab gives you proof. Each lab is a guided project for one AI-native role. You get a scenario, starter files, clear steps and a checklist that tells you when it is really done. At the end you have something real to show in an interview.

Agentic engineerSome code4 to 6 hours
Build a support agent with two tools and a safety limit

A small agent that looks up orders and opens tickets, with checks, limits and a test set.

Start this lab →

Agentic orchestratorNo code3 to 5 hours
Run a three-agent report pipeline and break it on purpose

A researcher, a writer and a reviewer pass work to each other. You add limits and test the failures.

Start this lab →

Forward deployed engineerNo code5 to 7 hours
Run a mock customer project from first call to handover

Play the forward deployed engineer for a fictional clinic: discover, scope, prototype, test and hand over.

Start this lab →

AI transformation strategistNo code4 to 6 hours
Build an AI strategy pack for a fictional company

Score ideas, build a business case, list the risks and plan a pilot for Riverside Logistics.

Start this lab →

AI evaluation engineerNo code4 to 6 hours
Evaluate a help-center assistant and gate a release

Write a rubric, build a test set, score an assistant, study the failures and decide if it can ship.

Start this lab →

AI security engineerNo code3 to 5 hours
Attack and harden a practice assistant

Try ten attacks on a sandbox assistant, write the findings, add defenses and test again.

Start this lab →

AI governance and risk leadNo code4 to 5 hours
Review an AI resume screener and write the decision memo

Register it, tier it, ask the vendor questions, check fairness and write a go, conditions or stop decision.

Start this lab →

AI product managerNo code5 to 7 hours
Spec an AI essay-feedback feature and plan its launch

Frame the problem, test feasibility, write the PRD with an evaluation plan, and plan metrics and launch.

Start this lab →