Mubit launches a service that trains your own small model using agent API calls
Mubit reads the API calls that agents have already sent to OpenAI or Anthropic, identifies repetitive tasks, and trains a user's own small model so that this portion of the work costs less and has shorter wait times, while the remaining tasks are still handled by frontier models. Integration only requires replacing the base URL and keeping the existing client code; it can also connect directly to traces that have already been collected. The company says the model refreshes every few minutes. The author believes the idea is to write experience into weights rather than prompts, so agents from different companies will train different small models.
Why read this
AI score 58
The original article explains how Mubit turns repeated agent calls into a proprietary small model, so readers can judge how a division of labor between proprietary models and frontier models would work in practice.
Topics
View original postWe started Mubit in Aberdeen. No network, no lab, nobody knew us. We just wanted AI systems that actually work. Today we work with some of the best companies and engineers in the world. And the thing we kept seeing: you and your competitor run the same AI. It should be yours. 🧵 Comment "SAPLING" in the next 48 hours for $100 free credits. Enterprises get the first month free.
View original
We started Mubit in Aberdeen. No network, no lab, nobody knew us. We just wanted AI systems that actually work. Today we work with some of the best companies and engineers in the world. And the thing we kept seeing: you and your competitor run the same AI. It should be yours. 🧵 Comment "SAPLING" in the next 48 hours for $100 free credits. Enterprises get the first month free.
Body
Your API calls are now training data you own, a great launch for owning your intelligence stack.
Mubit reads the calls your agents already send to OpenAI or Anthropic, finds the tasks that repeat, and trains small models that you own.
so you pay less and wait less while the big model handles the rest.
> The company says they refresh every few minutes. > The integration is one line. You swap the base URL and keep the same client code. If you’d rather not touch that, you can connect the traces you already collect. > I like is the split. Narrow, repeated work moves to a model trained on your own traffic. Anything outside those tasks still goes to the frontier model.
All these means, two companies on Mubit end up with different small models, because each is shaped by its own agents’ work.
Remembering feedback in the prompt is unpredictable. So what Mubit is doing that instead of putting lessons into the prompt, it trains small models on the tasks your agents repeat, so the improvement lives in the weights.