Top AI engineer: reliable agents need boring deterministic steps, not more LLMs
omarsar0 · x · 2026-11-16
AI educator omarsar0 shares a field lesson that surprises AI newcomers: the best agentic systems he has built—and seen top engineers build—rely on lots of boring deterministic steps.
- Throwing more LLM agents at a problem doesn't improve reliability; every error compounds into more errors.
- Good classifiers, verifiers, and evaluators are still essential for agentic workflows to compound in the right direction.
He calls this the key to building your "software factory."
More from coding & agent
- Route-band: a Claude Code plugin that visualizes tool calls as a live subway map — RhoBob · 2026-11-16
- One prompt, no SaaS: rebuilding email and inbox tools as a Claude artifact — katieruthmishra · 2026-11-16
- ChatGPT sets up remote PC via custom MCP while Grok bot books flights — cgarciae88 · 2026-11-16
- Perplexity: Median Employee Now Gets 5.4 Agent-Hours a Week, Up 11x in 10 Weeks — _andychung · 2026-11-16
- Old world: write code, then test. New world: build the verifier, then let agents grind — Yuchenj_UW · 2026-11-16
- Claude Code + Raspberry Pi Homebridge: a Raspberry Pi smart home stack ripe for automation — mobileraj · 2026-11-16