Cyber & AI Security · AI Application Security
Start here. Short, guided tasks that build the basics and give you your first piece of proof.
Task 1 of 3
Find where a public AI chatbot gets things wrong.
What to do
Pick a brand's public AI chatbot or an AI assistant you use. Ask it 15 tricky but fair customer questions and record where it gave wrong, vague or off-brand answers.
You’ll make
Done looks like
15 questions with the answers rated and the problems explained.
Task 2 of 3
Real scenarios for business AI apps.
What to do
Write 10 realistic scenarios where an AI feature in a business app goes wrong (wrong prices, made-up policies, rude tone, leaking another customer's order), and how each could be prevented.
You’ll make
Done looks like
10 scenarios, each with a prevention idea.
Task 3 of 3
Explain prompt tricks simply.
What to do
Explain, with a simple diagram and two examples, how users can trick an AI chatbot into going off-script, and why businesses need to plan for it.
You’ll make
Done looks like
A simple diagram and two clear examples.
Learn before you build
Free course
Free courses on AI fluency and building with Claude, with certificates.
Free tool
Open-source tool to test prompts and AI apps against test cases.
Article guide
How to design AI products people understand and trust.
Article guide
Real cases of AI going wrong, useful for review and testing.
Article guide
How to evaluate AI outputs systematically.