Designing Explainable Conversational Agentic Systems for Guaran\'i Speakers

TL;DR

This paper advocates for an oral-first AI architecture tailored for Guaraní speakers, emphasizing cultural grounding, community governance, and conversational dynamics over traditional text-based systems.

Contribution

It introduces a novel multi-agent framework that prioritizes spoken language and indigenous data sovereignty, moving beyond recognition to interaction-focused design.

Findings

Decoupling language understanding from conversation agents enhances cultural relevance.

An oral-first architecture better supports Guaraní's linguistic practices.

Community-led governance ensures indigenous data sovereignty.

Abstract

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 Guaran\'i, 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 Guaran\'i 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.