Saphan StudioDocs

Saphan Studio documentation

Saphan Studio is a control plane for governed fleets of AI coding agents: install it, connect your agents, and run work that a human decides and the record can prove.

Saphan Studio is a control plane for governed fleets of AI coding agents. Agents do the work on machines you own; every change waits for a human decision, and what happened is written into a record you can read afterwards.

This is the operator's documentation: how to install it, connect it, run it, secure it, and answer for it.

Start

TaskGo here
Install it and reach the first working screenAn install, end to end — one command, what it verifies before it writes anything, and the address it leaves you at
Set up the first machineFirst run at /setup — six screens in a browser, including the key ceremony that does not repeat
Run the first governed streamInstall, found the fleet, run the first stream — from an order to a human gate to a recorded result
See which agents and systems are supportedThe agents it drives — the backends, and what has been exercised on which platform

Operate

TaskGo here
Read the fleet from a screenThe console — the owner's view of the record, and the small number of acts it offers
Decide a gate, land a changeWorking with git — orders, returns, verdicts and merges
Control what it spendsCost management — the quote, the cap, and what stops a run
Understand a refusalTroubleshooting — the product refuses in words; this says what each set of words means
Look up a commandCommand reference — every verb and flag, generated from the binary

Deploy and connect

TaskGo here
Choose a deployment shapeDeployment — which programs each machine gets, and which run centrally
Decide the settings with no defaultConfiguration — the values you must choose, separated from the ones you can leave alone
Establish who actsIdentity — how a person or a machine is identified, and what that identification is worth
Connect it to your systemsIntegrations · Notifications · MCP server

Govern and prove

TaskGo here
Review the boundarySecurity — what the product defends, and what it leaves to you
Answer an auditorAudit and compliance — what the record proves, and where that proof stops
See what a run is allowed to reachEgress control — what happens to a connection leaving a run

Choose by your job

You areStart here
The person who owns the decision to run this productFor the owner
The person who installs it and is paged when it stopsFor devops
The person accountable for what it spendsFor the finance controller
The person who must establish what happened and whether the record holdsFor the auditor
The person who signs off on the boundaryFor the security officer

Understand it first

If you would rather read before you install: Concepts is the vocabulary the product uses and what each word is doing in it, and Actors and roles is who — and what — is allowed to act.

Where a chapter stops short, it says so on its own page. Some capabilities are built and not yet exercised on every platform, and some are not built at all; those pages state which, rather than leaving a reader to infer it.

On this page