Urgent.News

What's breaking now, across thousands of outlets.

AI

Presentation: Architecting the Data Layer for AI Agents: From Transactional Systems to MCP and Semantic Models

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…

We haven't written up this one. InfoQ has the full story — the link below goes straight to it.

Read the original at infoq.com →

More in AI

The First Hour: An On-Call SOP for AI-Generated Code

Most teams plan for smooth AI handoffs. Almost none plan for the broken one. This article defines a sixty-minute playbook for AI changes that fail in production. Every step fits on one page.

  • First five minutes focus on containment by rolling back or disabling the feature
  • Capture prompt, git range, and test output in incident bundle using script
  • Reproduction phase runs failing input against plain model to identify minimal case

The Best Model Pair in My Field Test Was Also the Least Trustworthy

v0.2.1 RELEASED — Aug 28, 2026. Release notes · Field test report v0.2.1 Key Finding: The Mistral effect is confirmed. DeepSeek+GPT (two different labs, no Mistral) converged at 0.246 — same as the…

  • DeepSeek + Mistral had highest average convergence score at 97%
  • Model pair exhibited capitulation cascade pattern in debates
  • Trustworthiness compromised despite best performance metrics

I Gave the Same Governance Audit to One AI and an AI Swarm. They Missed the Same Bug.

I Gave the Same Governance Audit to One AI and an AI Swarm. They Missed the Same Bug. I started the experiment wondering whether rapidly improving AI was making my deterministic governance…

  • Single AI missed most defects in 341 document corpus
  • Swarm of AI agents achieved higher comprehensive analysis
  • Synthesis agent identified cross-domain defects missed by single AI

More from Saturday 29 August →