Expert-led or self-service
The same platform and the same tools either way. Expert-led always ends with your team running it.
Self-service
Your engineers run the factory on the platform from day one.
- Sign up in the web app or from the CLI
- Bring a task description and 20 or more examples
- Train, evaluate and compare against your current model

Expert-led
Our forward deployed engineers embed in your team and run it with you.
- Scope one use case with success criteria agreed up front
- We train the first models on your data and read out the results
- Your engineers are onboarded and take over on the platform
Which path fits your team
| Expert-led | Self-service | |
|---|---|---|
| Best for | Teams that want results first | Teams that want to own the loop from day one |
| Who builds | Our engineers, inside your team | Your engineers |
| We provide | Platform and agent, plus scoping, evals, data work and training | Platform, agent, onboarding and support |
| PoC pricing | Priced per use case | Pay as you go, starting with $200 of credit |
| Model rights in the PoC | Agreed in the scope | Non-commercial, hosted with us |
| Where it ends | Handover to your team, in 2 to 3 weeks | You keep building |
Get started with existing inputs

Required
Your harness
- An endpoint to your conversational agent
- Your system prompt, tools and knowledge base
- We build mock APIs and test users around it

Helpful
Traces
- Up to 10k real conversations, no labels needed
- Requests from a full day to size your deployment
- Or route n% of traffic through our endpoint

Helpful
Evals
- The rubric or LLM judge you already trust
- Hand-labeled scenarios you came across
- None yet? We agree acceptance criteria together

Choose your way in
Start on the platform today, or talk to us about your use case.