Latin American hyperlocal social marketplace and community platform came to Armakuni for openAI-to-AWS Bedrock migration, voice-first AI interfaces for low-literacy users, conversational onboarding, AI content moderation, and AI commerce companion.
The challenge
Armakuni won the engagement by demonstrating a clear roadmap that addressed Vecinos' cost structure and prepared the platform for 1-2 million users. The assessment SOW validated the architecture before implementation began, and the migration SOW executed the three-phase build. Armakuni now owns the AI architecture that runs the entire platform.
Scale: 143,000+ active users across Argentina and Costa Rica; targeting 1-2 million users across Latin American markets.
What we built
Armakuni delivered openAI-to-AWS Bedrock migration, voice-first AI interfaces for low-literacy users, conversational onboarding, AI content moderation, and AI commerce companion. The engagement ran as two fixed-scope SOWs: Assessment Phase SOW (August 2025) and AWS SaaS Migration & Enhancement SOW (November 2025). The work was AWS funded.
The outcomes
6 measurable outcomes shipped across the engagement. The ones that moved the business the most:
Full AI capability migration from OpenAI/LLaMA to AWS Bedrock completed, with every conversational, moderation, and onboarding workflow running on AWS infrastructure.. The cost structure of AI operations is now under Vecinos' control and optimized by model selection based on task complexity rather than a fixed per-API-call rate.
Voice-first interface live and validated with lower-literacy Latin American users. meaning the platform now reaches a structurally important audience segment that form-based interfaces excluded entirely. Vecinos can launch in markets where voice is not an accessibility feature but the primary interaction mode.
Conversational onboarding replacing forms, with users completing registration through natural language dialogue rather than data entry.. Drop-off at registration , a critical acquisition metric for a community platform , is addressed at the architectural level rather than through UI iteration.
AI content moderation with positive rephrasing running at scale, maintaining community quality without human review as volume grows.. The feedback loop means moderation accuracy improves with every interaction rather than requiring manual rule updates.
Platform architecture validated for 1-2 million users before the Mexico City launch, with auto-scaling policies in place and AWS cost modeled against real usage assumptions.. The business enters its most significant market launch with infrastructure confidence rather than uncertainty.
AI companion live with memory and preference learning, building user models that become more useful with every session and positioning Vecinos to. activate autonomous commerce features without a foundational rebuild when the product is ready.
Built on AWS
The production environment runs on 9 first-party AWS services. Delivered under our AWS Generative AI Services Competency, SaaS Consulting Competency competencies.
What's next
Autonomous commerce activation , enabling the AI companion to facilitate purchases and transactions directly through conversational interfaces, building on the foundation laid in Phase 3