AllowIt lets your AI agents spend and invest,
within a policy you set.
What it may buy, how much it may spend, and until when.
Inside the policy, the agent goes ahead.
Outside it, the request is denied.
Give an agent a scope, a budget and an expiry. AllowIt checks every action against those terms. Outside the terms, nothing moves.
Follow the story ↓A cheque is an instruction to someone else: pay this person, this sum, from my account. The oldest surviving English one was written in 1659.
Pay unto Mr Delboe
the sum of four hundred pounds
The agentic economy grows only as fast as this gap closes.
It acts on its own inside the policy, asks you when a call is unclear, and stops at the edge.
Some of what an agent needs is not on the open web: proprietary data, specialised models, verified contacts. x402 lets it buy exactly that, one request at a time. Here is one job, with and without AllowIt.
It sets what the agent may buy, how much, and for how long. Your keys stay with you.
Each agent gets a share of its parent’s allowance: the email checker $1 of the contact finder’s $7, the renderer $2.50 of the pitch designer’s $5. Every share comes out of your $15.
Splits the work and hands each part a narrower allowance.
Finds the best roofs
$3 ceiling · solar data60 warehouses from open map data · free
Who decides on energy
$7 ceiling · people data$1 ceiling · Hunter only
One page per prospect
$5 ceiling · images$2.50 ceiling · image model only
Tried a premium image model at $0.50 an image. Denied: your limit is $0.25 an image.
The results return to your prospecting agent.
$8.41 spent · $6.59 left · 1 request deniedThe log shows what was bought, by which agent and for how much, including the request that was denied.
22 warehouses with strong rooftop solar potential, the person who decides at each and a verified work email, plus a one-page pitch for the top ten with panels drawn on their own roof. I spent $8.41.
Unit prices from the x402 catalogs of StableEnrich (data) and StudioMCPHub (image generation), October 2026.
Stablecoins, tokenised funds, on-chain positions. An agent can rebalance, buy and redeem around the clock, inside a policy you approve: which assets, how much per trade, what must stay liquid, and when it comes back to you.
1,000 USDC
Policy created from this prompt: “Manage 1,000 USDC of approved assets. Keep 20% liquid, nothing above 25% in one asset, and ask me about unusual currency risk.”
Allowed.
Every rule passes. The agent goes ahead on its own.A wallet key is all or nothing: whoever holds it can move all of your money. Any web page or email the agent reads can instruct it to send that money elsewhere.
Run my research desk with up to 1,000 USDC. Keep at least 20% in USDC and no more than 25% in any one asset. You may buy and sell approved tokenised funds, and buy the data you need for the analysis. Ask me before anything with unusual currency risk. Stop at the end of the year.
use allowit::v1::prelude::*;
pub async fn exec(ctx: &Context) -> PolicyResult {
set_cap(ctx, "1000", "USDC")?;
cap_per_transaction(ctx, "250", "USDC")?;
allow_actions(ctx, &["buy_asset", "sell_asset", "buy_data"])?;
check_preference(ctx, "Does this keep at least 20%
in USDC, no asset above 25%, and avoid
unusual currency risk?", None, 0.85).await?;
Ok(())
}--- name: allowit-policy description: Check and submit every paid or trading action for the AllowIt policy "Research desk". Use before any payment, trade or transfer in this task. ---
Every action that moves money goes through this policy. The policy is enforced by AllowIt, outside the agent. The agent cannot change or bypass it.
Try it in the demo: write a policy in plain words, hand it to an agent, and watch every action get checked.
In the header, set the network to Local dev. No wallet, no funds.
Pick an example or describe your own, in plain words. Generate the policy.
Approve the budget to create the agent skill. Copy it to your agent.
Follow each request and decision live. Answer the ones that come back to you.
The rules an agent must follow when it touches your money: what it may do, with which assets or services, how much, until when, when it must ask you, and what it may hand on to other agents. AllowIt writes it from your words. You approve it before it takes effect.
Ackrate is our policy engine. It checks each proposed action against your policy before execution, outside the agent, and records the decision.
No. Your agent receives a skill and an access token scoped to one policy. Access expires, and cancelling the policy revokes it. AllowIt enforces the policy outside the agent; the agent’s tools cannot change or bypass it.
It is denied, with the reason. A hard limit, such as a per-trade cap, cannot be overridden. Actions that pass the limits but leave the judgement unclear wait for your answer.
Any agent that can read a skill and use a tool: hand it the skill AllowIt creates for your policy. Or let the hosted agent in AllowIt run the job for you.
In Local dev, actions are simulated. No wallet connects and no funds move.