TR-011MediumProviderPreventive
Interpretability and Explainability Measures
Providers must implement measures that enable deployers and, where feasible, affected persons to understand the basis for AI system outputs to the extent technically possible, supporting informed human oversight decisions.
Articles:Article 13(1)Article 14(4)
Evidence Examples
- Explainability method description
- Feature importance output samples
- Explanation interface documentation
Standards
ISO 42001:2023 §8.3ISO/IEC 24028
Related controls
- TR-001User Instructions for UseArticle 13(1) requires providers to supply high-risk AI systems with instructions for use containing the information necessary for deployers to understand…
- TR-002Intended Purpose DisclosureProviders must clearly communicate the intended purpose of the AI system, the specific context and use cases for which it was designed, and the categories…
- TR-003Performance Metrics Disclosure to DeployersThe instructions for use must include the performance metrics for which the system has been designed and the level of accuracy that the provider committed…
- TR-004Known Limitations Notice in IFUProviders must include in the instructions for use any known or foreseeable circumstances in which the AI system may fail to perform as intended,…
- TR-005Human Oversight Guidance for DeployersInstructions for use must provide deployers with information about human oversight measures required, including the competencies needed to interpret…
- TR-006Input Data SpecificationsThe instructions for use must describe the form and type of data required as inputs to the AI system, the formats expected, and any constraints on input…
Related EU AI Act terms
- Instructions for UseInformation provided by the provider of a high-risk AI system to inform deployers about the system's intended purpose, performance characteristics, limitations, maintenance requirements, human oversight mechanisms, and the technical measures needed to ensure the system can be effectively overseen by natural persons.
- Human OversightMeasures built into high-risk AI systems enabling natural persons to understand, monitor, and — where necessary — override or shut down the system. Must be proportionate to the risks and must ensure that deployers can intervene in the system's output before it takes effect.
- Transparency RequirementsObligations under Article 13 requiring that high-risk AI systems are designed to ensure that their operation is sufficiently transparent to enable deployers to interpret the system's output and use it appropriately, and under Article 50 for specific systems (chatbots, synthetic content) to notify persons they are interacting with AI.
Upgrade when it needs to be
The free questionnaire returns preliminary signals. The Full Assessment turns real system material into a governed decision record - extraction, component separation, evidence, national overlays, and a review-ready dossier.
Start free risk preview