Designing Explainable Conversational Agentic Systems for Guaranà Speakers
This work addresses the exclusion of indigenous and oral language communities from AI systems, offering a culturally grounded framework, though it is a position paper with incremental technical proposals.
The paper tackles the problem of AI and HCI systems underserving oral languages like Guaraní by proposing an oral-first multi-agent architecture that respects indigenous data sovereignty and diglossia, moving beyond text-centric approaches to focus on conversational elements like turn-taking and shared context.
Although artificial intelligence (AI) and Human-Computer Interaction (HCI) systems are often presented as universal solutions, their design remains predominantly text-first, underserving primarily oral languages and indigenous communities. This position paper uses GuaranÃ, an official and widely spoken language of Paraguay, as a case study to argue that language support in AI remains insufficient unless it aligns with lived oral practices. We propose an alternative to the standard "text-to-speech" pipeline, proposing instead an oral-first multi-agent architecture. By decoupling Guaranà natural language understanding from dedicated agents for conversation state and community-led governance, we demonstrate a technical framework that respects indigenous data sovereignty and diglossia. Our work moves beyond mere recognition to focus on turn-taking, repair, and shared context as the primary locus of interaction. We conclude that for AI to be truly culturally grounded, it must shift from adapting oral languages to text-centric systems to treating spoken conversation as a first-class design requirement, ensuring digital ecosystems empower rather than overlook diverse linguistic practices.