Beersy

4 standards

Agents and automation

Software acting on its own, with a budget and a boundary rather than a wallet of its own. Standards here cover the allowance it spends against, the policy the wallet enforces, and the audit trail it leaves behind.

Also searched as AI, AI agent, autonomous, inference, automation, bot.

Filed under

4 standards, spread across 3 of the 12 topics.

Start with

BRC-181

Wallet-Enforced Autonomous-Agent Spend Policy

An AI agent or automated script that holds a wallet's keys can be tricked or malfunction into sending money to the wrong place, and the usual safeguard, a human approving every transaction, defeats the whole point of letting software act on its own. Before this, a wallet could only grant a monthly spending ceiling to an app, which limits how much but says nothing about to whom, how fast, or under what conditions, so a single bad request could still drain the budget to an attacker.

Filed under Wallet

Standards about this

Agents and automation is the main subject of these 3.

  • 172

    Giving an AI Agent Control of a Delivery Vehicle Without Giving It a Wallet

    Letting a computer program spend Bitcoin on its own usually means handing it a private key, and a key can sign for anything, not just the one task it was meant for. Even a lightly funded key is a full custodian, which is risky when the program is something like an AI agent reading untrusted instructions. This describes a way to let a program trigger on-chain steps and pay their fees automatically, without ever holding a key that could send money elsewhere.

    sun-dive2026State machines
  • 181

    Wallet-Enforced Autonomous-Agent Spend Policy

    An AI agent or automated script that holds a wallet's keys can be tricked or malfunction into sending money to the wrong place, and the usual safeguard, a human approving every transaction, defeats the whole point of letting software act on its own. Before this, a wallet could only grant a monthly spending ceiling to an app, which limits how much but says nothing about to whom, how fast, or under what conditions, so a single bad request could still drain the budget to an attacker.

    RexStarBSV2026Wallet
  • 204

    Agent Allowances

    When an AI agent spends money on your behalf, it usually does so with a password-like credential that can drain whatever account sits behind it, and if something goes wrong you have to notice, log in, and revoke that credential while the agent keeps spending in the meantime. There was no way to hand an autonomous agent a fixed amount of money it could use on its own, anywhere, while guaranteeing the owner could never lose more than that amount and could always take the rest back in a single action.

    Ruth Heasman2026Wallet

Standards that touch it

These are about something else, and deal with agents and automation on the way.

Usually read alongside

Concepts that keep appearing on the same standards as this one.

Was this helpful?

Search Beersy

Search standards by number, title, author or topic