Building Reliable Agentic AI Systems
Sarang Kulkarni writes up PRINCE, the agentic research platform Thoughtworks built with Bayer for preclinical drug discovery — in production with real users since early 2024, which makes it a rarer artefact than the usual demo-ware. The reliability story is context engineering plus harness engineering: route different information types to different agents instead of stuffing one prompt, keep orchestration in LangGraph with state in PostgreSQL, fall back across LLM providers, and close the loop with three reflection passes (workflow trajectory, evidence sufficiency, draft completeness) plus citations back to source documents. The HN discussion pushes back hard on the 3.1/5.0 user-satisfaction score and asks whether the multi-agent decomposition earns its complexity — one builder's verdict: the real work is 99% data management, 1% agent tuning.
Was this useful?