How do you check whether an answer from an AI assistant is correct?
AI basics for everyone · Beginner 1
Short answer
Treat it as a draft, not a fact. Check claims that matter against a trusted source, such as an official website, the original document or a person who knows. Ask the assistant for its sources and open them. Be extra careful with numbers, dates, names, quotes, laws and anything medical or financial.
Deeper answer
AI assistants can produce confident, fluent answers that are wrong, a problem called hallucination. Fact-checkers use lateral reading: leave the answer and see what other reliable sources say about the same claim.
Useful habits: ask the same question a different way and see if the answer changes; ask the assistant what it is unsure about; and for work, keep a human responsible for anything that goes out under your name.
What a strong answer covers
- Treats the answer as a draft, not fact
- Checks against trusted or original sources
- Opens the sources the AI gives
- Extra care with numbers, names, laws, health or money
Answer it out loud in the mock interview about 1 min
Follow-ups to expect
- What kinds of answers would you never use without checking?
- What is lateral reading?
Common mistakes
- Trusting an answer because it sounds confident
- Asking the same AI to confirm its own answer and stopping there
Learn it
- How would you use AI to help write a difficult email to an upset customer?
- How would you use AI to research a topic you know little about?
- What can today's AI not do well?
- What is the difference between AI, machine learning and generative AI?
- Your manager forwards a report a colleague wrote with AI, and one key figure looks wrong. What do you do?
- Your team asks you to suggest one place to start using AI. What would you pick, and why?
- If you had three months to get comfortable using AI in your job, what would your plan be?
- Will AI take your job? How are you preparing?
- What makes a good prompt? Give an example.