🤖 AI Summary
This work addresses the lack of forward-looking, structured design and governance methodologies in current agentic AI systems, where existing documentation is often retrospective, non-machine-readable, and lacking interoperability. To bridge this gap, the paper proposes the Agentic Automation Canvas (AAC)—a structured framework encompassing six dimensions: scope definition, user expectations, development feasibility, governance stages, data sensitivity, and outcomes. Integrating semantic web technologies—including controlled vocabularies, Schema.org, and the DCAT ontology—and aligned with FAIR principles, AAC enables the generation of machine-readable, versioned, and privacy-aware project charters. Implemented as an open-source web tool, it supports export to RO-Crate format. Empirical validation across research, clinical, and institutional settings demonstrates that AAC significantly enhances design transparency and cross-role collaboration in autonomous AI systems.
📝 Abstract
Agentic AI prototypes are being deployed across domains with increasing speed, yet no methodology for their structured design, governance, and prospective evaluation has been established. Existing AI documentation practices and guidelines - Model Cards, Datasheets, or NIST AI RMF - are either retrospective or lack machine-readability and interoperability. We present the Agentic Automation Canvas (AAC), a structured framework for the prospective design of agentic systems and a tool to facilitate communication between their users and developers. The AAC captures six dimensions of an automation project: definition and scope; user expectations with quantified benefit metrics; developer feasibility assessments; governance staging; data access and sensitivity; and outcomes. The framework is implemented as a semantic web-compatible metadata schema with controlled vocabulary and mappings to established ontologies such as Schema.org and W3C DCAT. It is made accessible through a privacy-preserving, fully client-side web application with real-time validation. Completed canvases export as FAIR-compliant RO-Crates, yielding versioned, shareable, and machine-interoperable project contracts between users and developers. We describe the schema design, benefit quantification model, and prospective application to diverse use cases from research, clinical, and institutional settings. The AAC and its web application are available as open-source code and interactive web form at https://aac.slolab.ai