Topic

AI Evaluation

AI Evaluation

2 entries · Topic

Latest

Agentic BI Fails 79% of Real Workflows, Survey Finds

A 68-study survey under review at IEEE IT Professional finds top agents complete 14–21% of realistic workflows, with trust failures to match. Vendors sell them regardless.

  1. Netflix Details AI Discover: LLM Planning With Code Guardrails

    Netflix engineers detail the agent harness behind AI Discover: plan-then-execute agents, async TV serving, code-enforced safety a…