RL environments · evals · post-training
Experts watch frontier models do real work on a real computer and correct them as they go, or do the work themselves while it's recorded. Every correction becomes deterministic grading, on the answer and on how the work was done.
states “Net leverage” = 4.0x ±1%new check · provenopens the credit agreement before emailingnew check · provenNo answer keys to write, no rubrics to draft. Experts do what they already do at work: review someone's work, or do it themselves. We turn that into grading that can't be gamed.
A frontier model does the job on a live desktop, saying what it's about to do and why. The expert flags the step where it goes wrong, in their own words. The AI retries with the coaching.
The expert does the work the way they normally would. We record what they open, save and send, and they can go back through their own steps and correct themselves. That becomes the reference workflow.
Two frontier models answer side by side; the expert says right, partly right or wrong and what's missing. Answers are pre-filled from what they accept, and new cases are proposed for them to check.
Every point an expert makes is compiled into a deterministic check, then kept only if it agrees with their verdicts on real attempts. The proof ships with the environment.
Checks on the numbers and the call (one call, no hedging), and on how the work was done: which sources were read, in what order, who was told. The same check grades a model's tool calls and an expert's recorded clicks.
Frontier models from every major lab do the finished tasks and the real grading scores them: a pass-rate table per environment, held-out exam cases the model never trains on, and a before/after score once you've trained.
Stateful finance tasks on a real desktop (spreadsheets, documents, email, a market-data terminal and colleagues to ask), graded by checks experts proved on real attempts. Built for RL post-training and for evaluating frontier agents.
Your experts show us how the work is done: they correct an AI or record themselves. We build the environment from it, test today's models on held-out cases, and train a model on your work: on your provider, your GPUs, or run by us.
Works with: Tinker, Baseten, Together AI, Fireworks AI, OpenAI, Azure AI Foundry, Amazon Bedrock, Google Vertex AI, Prime Intellect, NVIDIA NeMo RL, or your own GPUs (veRL, TRL, Unsloth). Model tests run on any OpenRouter model or any OpenAI-compatible service, including your own.
One page that always says what you do next. A first environment can be ready in a day; your expert spends about an hour.
Everyone signs in with the personal link from their invite email: no passwords.
Open your workspace from your invite link. Try the one-click sample to see every step in a few minutes, then build your own.
Use the link you were sent: a review link, a "teach a workflow" link, or your Percio expert page. Each opens only the work waiting for you.
Tell us what you'd like to train or evaluate. We reply within a few days with a plan, usually starting with one workflow and one expert.
No. Your own people can teach and review through a link, or we assign a vetted Percio expert. Either way an expert only sees the work waiting for them.
None to start: describe the work in words, or let your expert show it. Past cases and answers make it faster; you preview everything before it's saved.
Your projects live in your own workspace; other customers can't see them. Keys for your own model tests are used once and never stored.
No language model scores anything. Every check is code, proven on correct, wrong, blank and hedged answers and on the expert's own verdicts, so a policy can't talk its way to a reward.