AI Engineer · July 23, 2026

Why We Killed Our Multi-Agent Pipeline — Subbiah Sethuraman and Abhilash Asokan, ZS Associates

Why We Killed Our Multi-Agent Pipeline — Subbiah Sethuraman and Abhilash Asokan, ZS Associates video thumbnail
Why it matters

Their first pharma analytics system mimicked a human analyst: one agent to detect a signal, one to localize it, one to find the cause, one to synthesize, all wired to an orchestrator.

My takeaway: Why We Killed Our Multi-Agent Pipeline — Subbiah Sethuraman and Abhilash Asokan, ZS Associates is an agent-security signal. The practical read is that autonomy, memory, tool permissions, and third-party integrations are the control surface that needs threat modeling and monitoring.