I ve been spending more time vibe coding recently, and I ve started to question something I initially took for granted. Most of the conversation around vibe coding is about speed. Like how quickly you can go from idea to prototype, or how fast you can iterate. And to be fair, that part is real. The barrier to building has clearly dropped.
But the more I use these tools, the more it feels like speed isn t the limiting factor anymore.
The real constraint seems to be taste.
what do you choose to build?
what do you keep vs discard?
what actually feels right vs just working ?
what is genuinely useful vs just impressive in a demo?
I ve been thinking a lot about how AI agents are being monetized, and I m not convinced we ve landed on the right model yet. Most of them are still packaged like traditional SaaS: monthly subscriptions, seat-based plans, or usage tiers.
But agents don t really fit neatly into the software tool category.
Built Hyta s mini internal RL environment host this weekend. It s only a TUI for now. It can register and spin up environments, run and monitor rollouts, stream logs and telemetry, and manage a small model registry. Still early and scrappy, but super fun to build and test custom RL environments.
Watchman AICapturing invisible B2B buyers with AI agents
