Quante Carlo is an optimization company. The name is the method: a Monte Carlo accelerator, built in 2013 for a search problem in astronomy, that turned out to be a general way of finding good points in expensive spaces. Hyperparameters first. Then prompts. Then whole agents.
Every problem we have worked on has the same shape: a function that is expensive to evaluate, no gradient to follow, and a budget. The answer is always to spend each evaluation where it teaches you the most — a surrogate model of what you have already measured, an acquisition rule for what to try next, and enough sampling to know a lucky result from a real one. That is Bayesian optimization, and the accelerator is what makes it fast enough to use.
The original engine: sampling that converges in a fraction of the draws, first used in planetary-discovery research where each evaluation was a simulation.
The same engine pointed at model training. In our benchmarks it reached the optimum thousands of times faster than the next-best method and cut training time by about 80%.
The current work. Prompts are discrete, the objective has no gradient, evaluations are noisy and cost money: the problem the accelerator was built for. Why it's hard →
Three things, one optimizer underneath.
Bayesian Prompt Tree Optimization: the library. Tree search over prompt rewrites with GEPA-style reflective proposals and Bayesian selection as peers, whole-program execution, budgets, caches and logged experiments.
The point-and-click front end: draw a program of prompt steps, attach labelled data, validate, run a pilot for the cost, optimize, and read the new prompts off each step.
The business case for the objective most teams meet first: the same answers from fewer tokens, measured on your data — with a worked example in the studio.
Twelve deployed use cases across several industries, and twenty-four hackathon wins along the way. The numbers in this section are company results, not bpto experiments; the experiments are on the findings page with their logs.
How the optimizer works, in four steps.
The findings: every number, with the experiment it came from.
Impromptune: run it on your own prompts.
Contact us about a system you want measured.