We build agents for teams that cannot afford a bad write
Rubatt is an engineering studio building autonomous systems for operations, sales, research and support teams at small and medium businesses and startups across the US and UK. We are small, we work directly with the people who run the process, and we say no to work that should not be automated.
What we believe, and why it shapes the code
The write path is the whole problem
Reading is not where agent projects fail. Writing is. Almost every design decision we make follows from taking that seriously, which is why our systems are boring in exactly the places that matter.
Scoping honestly beats building fast
Most failed agent projects failed before any code was written, in a specification that described the process as somebody imagined it rather than as it runs. We would rather spend two weeks finding that out than three months discovering it.
You should own what you paid for
Source, prompts, evals and infrastructure config, in your accounts, from the first commit. We do not operate a runtime you rent, and nothing we build for you becomes a component of somebody else’s system.
An agent that admits uncertainty is worth more
Calibrated uncertainty is more useful than confident coverage. We tune for the system saying it does not know, because that is the behaviour that makes the rest of its output trustworthy.
Engagement models
Three ways to start. The last row is the one most people are really asking about.
| Attribute | Discovery sprintScope one workflow, prove it can be agentic. | Build engagementShip the system into production. | Managed agentsWe run and improve it while you use it. |
|---|---|---|---|
| Best for | Teams with a workflow in mind and no certainty it is automatable | A validated workflow that needs to exist in production | A shipped system that needs to keep working as your tools change |
| Duration | 2 weeks | 6 to 12 weeks, scoped per workflow | Monthly, cancel with 30 days notice |
| What you get | A working prototype in demo mode, an integration map, and a build estimate | The production system, connectors, approval gates, and a runbook your team owns | Monitoring, model and prompt tuning, connector maintenance, and new capabilities as you need them |
| Approval gates | On every write path | On every write path | On every write path |
| Runs without live API keys | Yes, that is the whole point | Yes, demo mode ships alongside production | Yes, retained for staging and demos |
| What you own at the end | The prototype, the code, and the integration map. Yours whether or not you continue. | Everything. Source, prompts, evals, infrastructure config, in your repositories and your accounts. | Everything, continuously. Stopping the retainer stops our work, not your system. |
If you would rather see the mechanism than read about it, the approval gates page explains the part that makes everything else safe.
Tell us what you are trying to automate
Including the part you think will not work. That is usually the interesting bit.