Presentation: Architecting the Data Layer for AI Agents: From Transactional Systems to MCP and Semantic Models
Must ReadInfoQ · 2026-08-29 11:00 UTC AI
AI Summary
Fabiane Nardon explains how TOTVS prepares enterprise data for token-hungry AI agents, balancing deterministic logic and non-deterministic LLMs across precision, security, and cost. She 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. The presentation focuses on architecting the data layer for AI agents.
AI analysis by Groq
Why should I care?
Because it shows how to reduce token costs and improve LLM performance, directly benefiting AI agent development.
Content
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. By Fabiane Nardon