Maai & AI
← Stream
weblinks

Improving Conversational AI Models | Interactional AI

Interactional AI is a research programme that applies Conversation Analysis to improve conversational AI models and user interfaces. The core argument is that interactive interfaces are not naturally intuitive unless they are grounded in the foundations of human social interaction, requiring design teams to ground conversational UIs in conversation analytic research methods and social science approaches.

interactionalai.com ↗
Published Tended 16 June 2026 Maturity 🪴 Plant AI 100% Maai Fully written by me.
Mycelium tags, relations, arguments & questions

Relations

  • Conversational user interfaces requires Conversation Analysis
  • Interactional design structured-as CADENCE design method
  • Natural conversational experience caused-by Social interaction
  • Conversational user interfaces inaccessible-via Interactive design alone
  • CADENCE design method demonstrates Conversation Analysis

What this post argues beta

  • Conversational user interfaces must be built on naturally occurring human social interaction patterns to achieve true intuitiveness.
  • Conversation Analysis, as a social science discipline, provides the theoretical foundation and practical tools needed to design better conversational AI systems.
  • The gap between 'interactive' and 'interactional' reflects a fundamental design challenge: systems can be responsive without being naturally conversational.

Share