AI agents can already shop, book, and research on their own but the moment one needs to pay, every existing system assumes a human clicks approve. Nobody built for agents. Orite fixes that. Set spending limits once Orite enforces them on every transaction, automatically. Stay within budget, it just happens. Go over, it's blocked or held for a quick yes/no. Every payment logged, always explainable. Works wherever you build your agent. This is day one of AI having its own money.
Hey everyone π
I started building this after noticing something that kept bugging me: AI agents are getting genuinely good at *doing* things searching, comparing, booking, researching. But the second one of them needs to actually pay for something, it just stops. Someone has to step in and click approve.
That felt backwards. If an agent is trusted enough to do the task, why can't it be trusted to spend $2 on an API call it needs to finish that task?
So I started digging into how payments actually work β bank transfers, cards, UPI, all of it β and realized every single one of these systems was built with one hidden assumption: a human is always the one hitting confirm. Nothing was built for a world where that's not true anymore.
Orite is my attempt at fixing that. Not by replacing how payments move, but by building the missing layer in front of it the thing that decides *whether* a payment should happen at all, based on limits you actually set, before any money moves.
The approach changed a lot while building this. I originally thought this was just "give the agent a payment API key." It's not. It's closer to giving an employee a company card limits, categories, an audit trail, a way to say no. That reframing changed almost everything about how I built it.
This is still early a first version, built solo, and I'm sure there are rough edges. Would genuinely love to hear what you think, what's missing, and whether this is a problem you've run into building your own agents.
Thanks for checking it out π
Report
You asked what is missing. The spend that sits inside the limit and is still wrong. Right amount, confident agent, wrong thing. A budget does nothing there. Can autonomy options be set till the time trust gets built with user?
Also can I reverse after the fact or raise dispute (worst case scenario)? And does the log/trace tell me which decision led to the charge, or only what the charge was? That second one is what lets me go fix the agent right, which is gonna be criitcal.
Right a budget only checks how much was spent, not if it was the right thing to buy. That part's not on Orite, that's the AI's own thinking, we just handle the payment side.
For the initial version after a purchase happens, you just tell it "this was good" or "this was wrong." Do that enough times and the agent builds a track record. Good record, it gets more freedom. Bad record, we hold more stuff back for you to approve first. So yeah, training wheels at first, less hand-holding as it earns trust.
Refunds work exactly like normal you return the wrong item, the store decides if they refund it, same as always. We just make sure that if the money comes back, it actually lands back in the right agent's account properly.
And the log isn't just gonna say "spent βΉ1,499." It'll actually show why it was allowed to spend it which rule let it through. That's the part that lets you go fix your agent instead of just staring at a receipt.
Orite
You asked what is missing. The spend that sits inside the limit and is still wrong. Right amount, confident agent, wrong thing. A budget does nothing there. Can autonomy options be set till the time trust gets built with user?
Also can I reverse after the fact or raise dispute (worst case scenario)? And does the log/trace tell me which decision led to the charge, or only what the charge was? That second one is what lets me go fix the agent right, which is gonna be criitcal.
Orite
Right a budget only checks how much was spent, not if it was the right thing to buy. That part's not on Orite, that's the AI's own thinking, we just handle the payment side.
For the initial version after a purchase happens, you just tell it "this was good" or "this was wrong." Do that enough times and the agent builds a track record. Good record, it gets more freedom. Bad record, we hold more stuff back for you to approve first. So yeah, training wheels at first, less hand-holding as it earns trust.
Refunds work exactly like normal you return the wrong item, the store decides if they refund it, same as always. We just make sure that if the money comes back, it actually lands back in the right agent's account properly.
And the log isn't just gonna say "spent βΉ1,499." It'll actually show why it was allowed to spend it which rule let it through. That's the part that lets you go fix your agent instead of just staring at a receipt.
@pratik_pandey4Β sounds good! will give this a spin !