Evaluate an AI assistant with verifiable test cases
Build cases, criteria and evidence to compare AI assistant versions before assigning work.
Read the practical method →NIST · AI Risk Management Framework
NIST voluntary framework for structuring risk management for artificial-intelligence systems.
Resource identity and purpose checked against the source on . This check does not verify all service conditions or individual data records.
Use this resource for a specific task.
Data and artificial intelligence · International
Open the original resourceWhen it helps
Structure discussion of risks, responsibilities and controls for an AI use.
How to start
Connect the risk-management framework to a specific AI use case. Record allowed behaviour, costly failures and affected people; keep evaluation results alongside the deployment decision.
Limits to keep in mind
NIST presents the framework for voluntary use. Using it does not establish certification or automatic legal compliance.
Check before using
Three points to record with the decision.
- 01
Selected document version.
- 02
Risks specific to the system and its use.
- 03
Human decision and test evidence.
A method and complementary resources.
Source and verification
NIST · AI Risk Management Framework — primary source. Link checked . The checklist is editorial guidance; link availability does not guarantee completeness or suitability.
Read the editorial method · Report a correction with its source