Docs
How Sanaf works, written for whoever has to make it work. Hiring and briefing it, connecting your apps, what it may do without asking, running work on a schedule, and reaching it from your own software over HTTP or MCP.
Start here
Hiring it, briefing it, and the first week.
Getting started
Sanaf is the AI employee every workspace starts with. It runs a team of agents, one per job, and brings you one answer. You give it a job in plain words, connect the apps that job needs, and decide what it may do without asking. Everything below takes about twenty minutes and nothing here needs a card.
ReadConnecting your tools
Sanaf works inside the apps you already run. You connect an app by signing in to it from the console, you decide per tool what it may do without asking, and you can disconnect it on its own at any time. Nothing is connected by default.
ReadTrusting it
What it may do without asking, and what runs while nobody is watching.
Approvals and permissions
Sanaf asks before anything it cannot undo, unless someone at your business has told it otherwise. Rules are set per kind of action, and per tool where you want finer control, so sending an email and updating a record are governed separately.
ReadScheduled and recurring work
A job can run on a schedule rather than waiting to be asked. You set one up by asking Sanaf or from the console. A schedule carries its own timezone, posts where it was set up, and a new one Sanaf proposes always needs your approval, with what it will cost a month on the card.
ReadSkills: teaching it how you do something
A skill is a folder with a SKILL.md at its root: written instructions for how your business does one particular thing. Sanaf reads the description to decide whether a skill applies to the request in front of it, and follows the instructions when it does. You add skills by uploading a folder or pointing at a public repository.
ReadBuild with it
Reaching your AI employee from your own software.
The HTTP API
Give a hire a task over plain HTTP, for callers that do not speak MCP: a cron job, a webhook from another system, a shell script. Authenticate with a workspace API key. The response is 202 rather than 200, because a turn is durable and may wait days for an approval.
ReadThe MCP server
Point any MCP client at the Sanaf endpoint with a workspace API key and your AI employee becomes a set of tools in that client: list the employees, give one a task, read the reply, and read the work log.
Read