Enterprise transactional data wasn't built for token-hungry AI agents.
Fabiane Nardon explains how to build an agentic data architecture combining Data Mesh, Semantic Web ontologies, and MCP tools - improving precision while cutting token costs by up to 60%
🔗 Watch now: https://www.infoq.com/presentations/enterprise-data-architecture-ai-agents/
Fabiane Nardon shares how TOTVS prepares enterprise data for token-hungry AI agents. She discusses balancing deterministic logic and non-deterministic LLMs across precision, security, and cost. Nardon details using data mesh, low-latency database architectures, semantic ontologies, and dynamic MCP tool selection to optimize context windows and reduce token overhead in transactional systems.
www.infoq.com
Comments (0)
Sign in to comment or create an account