AI Red Teaming Terms Every Intern Should Know
By K. Boopathikumar, CEO & Founder · 16 November 2026 · 4 min read
In your first AI Red Teaming internship meetings you will hear words that everyone else seems to know. Here they are in plain English. If you hear a term that is not on this list, write it down and ask; nobody minds an intern asking what a word means.
The terms
- Red teaming: authorised testing to find how a system can fail.
- Scope: what you are allowed to test.
- Harm category: a type of risk, such as privacy or bias.
- Over-refusal: refusing safe, legitimate requests.
- Finding: a documented issue with evidence.
- Severity: how serious a finding is.
- Mitigation: a change that reduces the risk.
- Responsible disclosure: reporting privately so issues can be fixed first.
Next steps
- Study the free AI Red Teaming learning path and take its module quizzes for a free certificate.
- Follow the AI Red Teaming skill track from basic to advanced.
- Do real, reviewed work in a AI Red Teaming internship and keep every project in your own GitHub.