When Should a Startup Build Its Own Agent Harness?

Jon Noronha says a startup should build its own agent harness when the job looks very different from plain coding. For Gamma the work is subjective: two people disagree about what good looks like, a human stays in the loop, and the person using the tool cares about the specifics. He treats those traits as the test.

A personal video game is one opening he is bullish on. Coding agents already make games, and they are weaker at taking in what the player wants, the way non-coders shape Roblox or Minecraft. He can imagine a harness that runs inside a 3D world. The practical rule is to build something that looks nothing like what everyone else is shipping, then keep moving, because copies trail by a few months. The edge can be a distinct view of where things are going, data other people do not have, or a real-life business rather than more crowded software. He would look at a human exchange, such as a meal or a massage, that has not been reinvented with AI, and he says he does not know that world. Legal and accounting look crowded, so he would probably not start a legal-tech harness today. Greg Isenberg offered HVAC companies as a niche, and he agreed. The design question is which tools the founder can build that are not already out there, and what their life and relationships make them suited to do.