Working with agents: people own decisions, rules belong in code not prompts
gerardsans · x · 2026-11-05
The author lays out an "AI as infrastructure" principle for agent workflows: agents are powerful tools, not colleagues or decision makers—people own the strategy, the budget, and the sign-off.
- From terminal to Mission Control: A CLI works for one careful person but fails for teams, shift handovers, and audits. Approvals should reach you via screen, phone, or voice, with a button as fallback.
- Rules belong in code: If a rule can be written in code, enforce it in code. Let prompts explain rules, never enforce them.
This follows his earlier prediction on what comes after harness engineering: the 2027 "factory engineering" path (more is more) piles up debt, burnout, and never-ending costs, while 2028 should bring "slow engineering"—low-load ambient agents that stay out of the way within human-set constraints.
More from coding & agent
- Auto-unsubscribe agent built on Jev: browser-aware email triage cleans inbox in a week — threepointone · 2026-11-05
- Olki ditches LLM-based agent monitoring for strict type systems and effects algebra — bigdata · 2026-11-05
- Why Coda's formula language beats Notion for deterministic agent memory — bfrench · 2026-11-05
- Dev quits 11-year career, vibe-codes AAA-looking sci-fi FPS with AI in 24h, lands Gamescom booth — Aiden_Tech_Ai · 2026-11-05
- JetBrains argues IDEs still matter in the agentic coding era: 'a cockpit, not a typing tool' — Sam_Witteveen · 2026-11-05
- tiny-llm: Open Course Builds a Mini vLLM Inference Engine on Apple Silicon — alexcovo_eth · 2026-11-05