Greg Isenberg: Agent Harnesses Are the New GPT Wrappers, Targeting a $5T Market
gethackteam · x · 2026-09-14
Greg Isenberg argues that agent harnesses are the new GPT wrappers, breaking down what a harness does:
- Runs the model in a loop so it keeps working step after step instead of answering once
- Gives it hands to read files, call tools, and run code
- Manages memory so hour three of a job still knows what happened in hour one
- Enforces rules on what the agent can touch and when it must ask a human
He frames the opportunity as huge: wrappers sell software ($800B market) while harnesses sell the work itself ($5T+). Crucially, harnesses aren't tied to one model — the job knowledge lives in the harness, so you can run GPT today, Claude next month, and open models like Gemma, Qwen, or DeepSeek locally later, all without rebuilding.
Related event: Agent Harness Seen as the New GPT Wrapper(2 posts)→
More from coding & agent
- Element Forge: open-source editable AI VFX for real footage in ComfyUI — zitroffell · 2026-10-30
- Gym-Anything Adds Audit Agents That Try to Break Simulations With Legal Robot Actions — wellecks · 2026-10-30
- CMU's Gym-Anything Auto-Builds 200+ Agent Environments from Any Software, Selected by GDP — wellecks · 2026-10-30
- durable-object-migrator: zero-downtime exports for Cloudflare Durable Objects — samgoodwin89 · 2026-10-30
- This 5-question interview prompt makes Grok design your first two custom bots in minutes — nateliason · 2026-10-30
- Cursor and Harvey swap general models for task-specific brains, but most niches can't afford to — MartinGTobias · 2026-10-30