A small team, a large fleet of agents, and one engine behind every product we ship.
The engine
We built every part to run our own companies first. They are not a stack you buy in order: they are the parts of one engine, and each one stands on its own.
Agent harness
The interface. Proactive agents that live where you do: Slack, iMessage, email, and on the phone.
Agent orchestration
The orchestration. Every agent we run, ours or a customer’s, lives here: runners, credentials, guardrails, dashboards.
Agent fleet management
The plan. A list of features becomes a sequenced roadmap, and one person runs a fleet of dozens of agents against it.
Agent testing
The proving ground. Synthetic calls, emails and meetings that test an agent before a customer ever meets one.
Bare-metal deployments
The infrastructure. Local models and local inference, orchestrating work on bare metal we rent.
Live product Runs our own fleet Alpha
How we work
The team is deliberately small. Most of the work is done by agents. They hold the context, do the drafting and the calling, and carry the parts of a company that used to need a department.
The engine is one codebase. When one product learns something, every product gets it in the same release, so the work compounds instead of being rebuilt three times.
That makes each new product a question of distribution rather than a new company. A different audience, a different name, the same engine underneath.
Working here
The team stays small on purpose. Each person here runs a large part of the company, with a fleet of agents doing the work. So the bar is people who are used to owning an outcome end to end, and comfortable handing most of the doing to agents. If that is already how you work, write to us and say what you have run.
cedric@marblinghq.comGo deeper
Where the engine goes next, in numbers. Leave your email; the deck opens.
deck.marblinghq.comA walkthrough of how we think about agents. Behind a password; ask us for it.
agents.marblinghq.com