Skip to content
Rubatt

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.

0
production agent platforms shipped
0%
of write actions behind an approval gate
0
API keys needed to evaluate a build
0 weeks
typical discovery sprint to working prototype

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.

Comparison of Rubatt engagement models.
AttributeDiscovery 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 forTeams with a workflow in mind and no certainty it is automatableA validated workflow that needs to exist in productionA shipped system that needs to keep working as your tools change
Duration2 weeks6 to 12 weeks, scoped per workflowMonthly, cancel with 30 days notice
What you getA working prototype in demo mode, an integration map, and a build estimateThe production system, connectors, approval gates, and a runbook your team ownsMonitoring, model and prompt tuning, connector maintenance, and new capabilities as you need them
Approval gatesOn every write pathOn every write pathOn every write path
Runs without live API keysYes, that is the whole pointYes, demo mode ships alongside productionYes, retained for staging and demos
What you own at the endThe 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.