Rob LeClerc: harness means two things — labs supply the pilot, companies must build the plane
robleclerc · x · 2026-10-28
Rob LeClerc argues the term "harness" conflates two distinct layers: the model-side harness (the loop turning a model into an agent — tools, memory, autonomy) that labs like Claude Code and Codex ship generically with the model, and the enterprise-side harness (systems, data, rules, workflows, objectives, skills and tools you build for the agent in your business). His prediction: as agents become more autonomous and interchangeable, companies will treat them like airline pilots — labs train and supply the pilot, but every company builds and refines its own plane and cockpit, swapping in newer pilots as they're released.
Related event: Rob LeClerc: Agent Harness Splits Into Model Side and Company Side(2 posts)→
More from coding & agent
- Superwhisper taps Grok Bot, showing how businesses can ship products as conversational templates — XFreeze · 2026-10-28
- Sentient OS (YC F26) launches: on-device AI that learns your life overnight with a local LLM — testingcatalog · 2026-10-28
- Supermemory reverse-engineers how Claude Code's memory actually works — julianweisser · 2026-10-28
- GitHub's Spec Kit pushes spec-driven development: 5 commands to plan before coding agents build — Arindam_1729 · 2026-10-28
- How LangChain built its design agent: taste comes from context, not the model — LangChain · 2026-10-28
- Dev predicts in 5 years we'll laugh at today's juggling of terminal and agent harness tabs — DavidWells · 2026-10-28