Beyond harness engineering: from 2027 factory engineering to 2028 slow engineering
gerardsans · x · 2026-11-05
The author lays out where agent engineering goes next: 2027 'factory engineering'—more is more, AI as coworkers, piling up debt, burnout and unbounded costs—versus his proposed 2028 'slow engineering'—less is more, sustainable and frugal, with low-load ambient agents working within constraints you set, AI as infrastructure, and no silent decisions by design. He'll open the GoTech World Developers Stage on 11 Nov with 'Mission Control: From Whiteboard to PR,' showing a bounded control plane using Gemini, Antigravity Computer Use, ADK, MCP, A2A and Gemini Live to replace fragile chat and CLI workflows. The thread's ten principles include: agents are infrastructure, not colleagues or decision makers; rules enforceable in code should be enforced in code, with prompts only explaining them; and approvals should reach you on screen, phone or voice.
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