Towards an Interface Description Template for AI-enabled Systems

TL;DR

This paper proposes an interface description template for AI-enabled systems to improve component reuse and assess compatibility across different systems and contexts, addressing a gap in current documentation practices.

Contribution

It extends Google's Model Card concept to system-level AI components, creating a template for interface descriptions to facilitate reuse and compatibility assessment.

Findings

Developed an initial interface description template for AI components.

Inspired by Model Cards, tailored for system-level AI capabilities.

Aims to improve AI component reuse and system integration.

Abstract

Reuse is a common system architecture approach that seeks to instantiate a system architecture with existing components. However, reusing components with AI capabilities might introduce new risks as there is currently no framework that guides the selection of necessary information to assess their portability to operate in a system different than the one for which the component was originally purposed. We know from SW-intensive systems that AI algorithms are generally fragile and behave unexpectedly to changes in context and boundary conditions. The question we address in this paper is, what type of information should be captured in the Interface Control Document (ICD) of an AI-enabled system or component to assess its compatibility with a system for which it was not designed originally. We present ongoing work on establishing an interface description template that captures the main information of an AI-enabled component to facilitate its adequate reuse across different systems and operational contexts. Our work is inspired by Google's Model Card concept, which was developed with the same goal but focused on the reusability of AI algorithms. We extend that concept to address system-level autonomy capabilities of AI-enabled cyber-physical systems.