Start with $120 of free credit. No card.
Hire Sanaf, put it in your Slack or Teams, and see the work before you pay anything. When the free credit runs out, buy credits from $20 as you need them. They never expire, and you pay for the work, not per seat.
Last updated 2026-09-08.
An illustration of how the conversation reads, not a transcript from a client account.
Sanaf starts free. You get $120 of credit when you sign up, no card needed, and it never expires. When it runs out, buy credits as you need them: $20, $50, $100, $200, $500, or any amount you type, and none of that expires either. You pay for the work Sanaf does, not per seat and not per job, so giving it more jobs costs nothing extra. If you would rather we set the whole thing up and run it, we do that too, priced to the role and quoted in writing.
Start free, buy credits, or hand it to us
Free
See it work before you pay
$0
Sign up, give Sanaf its first job, put it in your Slack or Teams and give it real work. Your free credit never expires.
- $120 of free credit, on the house
- Sanaf, working in your Slack or Teams on the everyday models
- Every approval rule and the full work log
- No card, and the credit does not expire
- Hundreds of real tasks before you decide anything
Credits
Buy it when you need it
From $20
When the free credit runs out, buy a credit pack and keep going. Buying any pack opens up every job and the whole model catalogue. You pay for the work Sanaf does, not for how many jobs it holds, and nothing charges on its own.
- Credits from $20, in any amount you choose
- All thirty five jobs, any you write yourself, and the whole model catalogue
- No seat fee and no per-job fee
- Credits never expire, not one of them
- No recurring charge and no contract
Fully managed
We set it up and run it
Quoted to the role, in writing
The way you would bring on a person: we learn the role, connect the apps, set the approval rules with you, run a shadow week, then put it to work with us watching.
- Role interview and a written job description for the job
- App connections and approval rules set up by us
- A shadow week before it sends anything
- Phone, text, and chat where the role needs them
- A weekly report, and a person to call when something is off
- Invoiced directly, with no credit meter to watch
| Pack | Fits |
|---|---|
| $20start here | Try it on one job |
| $50 | A few jobs, most days |
| $100 | Several jobs, every day |
| $200 | A team, most days |
| $500 | A busy team |
Start free, buy credits when you need them, stop whenever you like. If an AI employee is not the right fit for the work, we will tell you before you spend anything.
What Sanaf comes with
Most AI employee products are one shared assistant your whole team talks to. Sanaf is a hire: a job description for every job, logins scoped to each, rules you set per action, a trial period, and a memory you can question. These are the mechanics, not promises.
A hire with a job description, not a chat box
Sanaf holds a written job description for every job you hand it: what it owns day to day, what it hands to a person, which apps it works in. Thirty five are written before you start, and the thirty sixth is yours to write. It is a colleague with a role, not an assistant waiting for a prompt.
Elsewhere: One assistant shared by the whole workspace, wearing every hat at once with no job to be measured against.
Logins scoped to the job
Every app connection is granted for a job and scoped to the narrowest permission that lets that work happen. Revoke a single connection without touching anything else, and see at a glance which job each one serves.
Elsewhere: Integrations connected once and shared across everything the assistant might ever do.
Approval rules per action, not one switch
For every kind of action, you choose: do it, ask me first, or never. Add conditions like an amount, after hours, or a new contact. Unattended work runs one notch stricter than work you asked for in the moment, and every decision carries a one-line reason. A safety check proves the rules hold before it goes near a customer.
Elsewhere: A single "ask before anything irreversible" setting, or an always-approve button per tool.
Starts in shadow mode and earns trust
Sanaf watches first and drafts what it would have done without sending anything. You review the drafts, then promote it a level at a time, with a report that says how often you agreed. Every promotion is your explicit call and is written down.
Elsewhere: Live on day one, learning by making mistakes in front of your customers.
Learns by proposing, never by rewriting itself
Overnight it reviews the day and proposes changes to its own instructions, each one citing the moments that prompted it. You accept or reject. Accepting creates a new version; rejecting is remembered so it stops asking. It cannot change itself without you.
Elsewhere: Notes the assistant writes to itself that nobody reviews.
Memory with receipts
Ask "why do you think that?" and it answers with when it learned the fact, where, and what it replaced. Correct a fact inline and the old one keeps its history. Nothing it acts on is untraceable.
Elsewhere: A memory you can reset but cannot inspect.
Everything it does is written down
Every turn is a replayable log: what it read, what it called, what it asked, what it sent. Your manager view shows it live while it works and keeps the timeline afterward, so "what did Sanaf do on Tuesday?" has an exact answer.
Elsewhere: A chat transcript and a credits total.
One bill, for the work
There is no seat fee and no per-job fee. You pay for the work Sanaf actually does, and the work log shows you what each piece of it used, so handing it another job costs nothing until that job produces something.
Elsewhere: A seat fee on top of credits whose price is never explained.
Working before the call you did not have to book
Sign up, give Sanaf its first job, and add it to your Slack. There is no demo gate, no waitlist and no onboarding queue between you and a colleague doing real work, and the $120 of credits you start with is enough to find out on your own jobs.
Elsewhere: A demo call, a trial that starts when sales says it does, and a setup checklist you complete yourself anyway.
How the models differ
Side-by-side comparisons against the AI employee platforms people ask us about. Each one says plainly when the other option is the better pick.
Frequently asked
What is a credit?
How far does $120 of credits actually go?
Do I pay per job?
What happens when I run out?
Do credits expire?
Can you just run it for me?
Is there a contract?
Not ready to hire yet?
Follow along instead. Field notes on what an AI employee can take off a team, what it costs to run, and where it still needs a person.