Organizations increasingly seek to integrate generative AI into their workflows, yet deciding which tasks to augment, and to what degree, remains a poorly structured challenge. Current design toolkits such as Microsoft’s HAX and Google’s PAIR offer valuable guidance for building human-AI interfaces but assume the decision to deploy AI has already been made. This paper addresses the upstream question: is a given task ready for AI augmentation? We present a five-dimensional framework that evaluates tasks along Cognitive Load, Temporal Engagement, Expertise Requirement, Social-Relational Demands, and Agency & Responsibility. The first three dimensions capture readiness—malleable conditions where AI can reduce burden and extend human capability—while the latter two capture suitability—structural and normative constraints that may limit AI involvement regardless of technical feasibility. Each dimension is operationalized through four concrete factors, grounded in a systematic mapping of 41 HAX and PAIR guidelines. We validate the framework’s content through an expert survey (n = 10), which confirmed strong relevance and clarity across all dimensions and factors, and a focus group with practicing AI consultants (n = 5). The framework aims to serve as a structured precursor to design-level toolkits.

Concept maps are visual tools for organizing knowledge, commonly used in education and design. The process often involves reading and developing conceptual models, where feedback is crucial. Learners (e.g., students, designers) often refer to reading materials, and receive feedback from instructors (e.g., teachers, stakeholders) based on the maps they create. However, annotations made by learners, like highlights, are usually not visible to instructors, limiting tailored feedback. We propose incorporating annotation practices into concept mapping. Learners could highlight text and link these highlights to existing or newly created concepts in their concept map. This way, instructors can access both the concept map and the relevant readings for better feedback. This vision is realized through Concept&Go , a plug-in for the editor CmapCloud . This extension aims at the interplay between mapping, reading, and feedback during concept mapping. The effectiveness of this approach is demonstrated through a focus group (n=5) and a UTAUT evaluation (n=12). Concept&Go is publicly available.