Intervenability as a Design Requirement for Autonomy and Oversight within Human-Centered AI
2.80T1 sourcearXiv cs.HC
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2607.10322.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryA research paper proposing 'intervenability' as a design requirement for AI systems, extending beyond emergency shutdowns or workarounds. It provides a taxonomy of human intervention activities differentiated by mental effort, and discusses how intervention supports both human capability development and AI reconfiguration within human-centered AI.
Why it mattersGives designers of agentic systems a concrete vocabulary for the spectrum of human interventions beyond binary on/off controls, with a mental-effort axis worth referencing.
Cited by
No citations on record.