AI engineering glossary · AI ethics law product
What is fallback behavior?
Fallback behavior (also called fallback behaviour, graceful degradation): What an AI product does when it cannot answer confidently or when a component fails, such as asking a clarifying question, offering a simpler option, showing a safe default or handing over to a human. Designing it well prevents dead ends and harmful guesses.
Fallback behavior: an example
When a shopping assistant is unsure what the user wants, it lists three product categories to choose from instead of guessing.
Related terms
- Escalation rate
- Confidence indicator
- Human oversight
- Guardrail
More AI ethics law product terms
- Federated learning
- Four-fifths rule
- GDPR
- General-purpose AI model
- Global explanation
- High-risk AI system
- Historical bias
- Homomorphic encryption
Where you learn it
Fallback behavior is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.