sebbi.pro
ANSWERS

How do I stop an AI agent spending money without approval?

Make the agent get a signed sign-off before every payment. With sebbi.pro Spend Gate you set each agent's limits (most per payment, most per day, an allow-list of payees); the agent calls sebbi.pro before it pays, the request is scored and checked against those limits, and it gets back a signed APPROVED or DENIED token. Your own payment system releases the money only on an approved token. sebbi.pro is the sign-off, never the wallet - it never holds your money.

How it works

  1. Set the agent's limits once: POST https://sebbi.pro/x/spendgate/policy with per_tx, daily and optional payees.
  2. Before any payment, the agent calls https://sebbi.pro/x/spendgate/request with the amount and payee.
  3. Over the limit, wrong payee, or flagged by the engine? It returns DENIED and no signature.
  4. On APPROVED, release the money, then confirm the token so it can't be used twice. Every decision is sealed and provable against Bitcoin.

Anyone can check a token's signature against the published key with no call to sebbi.pro. An AI assistant connected at sebbi.pro/mcp can run the whole thing.

Try Spend GateConnect your AI

Related questions

How do I prove an AI decision to a regulator?How do I make AI audit logs tamper-proof?What records does the EU AI Act require for high-risk AI?How do I timestamp a file in Bitcoin?What is a Forever Proof?
AI news
TechCrunchHealthleap raises $38M for its AI that flags hospital patients who may need a closer look29mTechCrunchTony Fadell on why the first wave of AI gadgets failed — and what comes next54mTechCrunchGoogle experiments with an AI-powered gaming platform59mTechCrunchOpenAI’s Alexander Embiricos is coming to TechCrunch Disrupt 2026 — days after the launch of Dots1hArs TechnicaMistral says "Le Chonk" can challenge the best AI models1hArs TechnicaGoogle rolls out improved SynthID AI content detector, now available globally1hTechCrunchGoogle’s new SynthID website can identify AI-generated media1hThe VergeAI could upend food delivery3hWiredOpenAI Wants Its New Agent to Run Your Life. Mine Said It Loved Me4hThe VergeChatGPT for Teens is an ‘unacceptable risk,’ says Common Sense Media6hThe VergeOpenAI drops another batch of mathematical breakthroughs16hArs TechnicaOpenAI will watermark ChatGPT outputs by default—but only in the EU18hWired‘Artificial’ Roasts AI’s Creators—and Sends a Dark Warning About Its Dangers20hWiredOpenAI Is Pissing Off a Bunch of Mathematicians—Again22hThe VergeGoogle is about to remove free access to Gemini Flash and Pro1dWiredMistral Says Its New AI Model ‘Le Chonk’ Is the Best Open-Weight Offering Outside of China1dArs TechnicaOpenAI agents tried to hack Wikipedia tools and flooded it with traffic1dBBC NewsItalian PM files to trademark her voice against AI threats1dWiredKevin Roose Didn’t Use AI to Write His Book About AI1dThe VergeGemini Call for Me might tell your mom you’re running late1dBBC NewsPentagon stops using Anthropic AI tools after blacklisting company, BBC told1dMIT Technology ReviewConnecting AI agents to enterprise knowledge1dArs TechnicaAI glasses face their first major government crackdown2dMIT Technology ReviewBringing predictive analytics to the agentic AI era2dTechCrunchHealthleap raises $38M for its AI that flags hospital patients who may need a closer look29mTechCrunchTony Fadell on why the first wave of AI gadgets failed — and what comes next54mTechCrunchGoogle experiments with an AI-powered gaming platform59mTechCrunchOpenAI’s Alexander Embiricos is coming to TechCrunch Disrupt 2026 — days after the launch of Dots1hArs TechnicaMistral says "Le Chonk" can challenge the best AI models1hArs TechnicaGoogle rolls out improved SynthID AI content detector, now available globally1hTechCrunchGoogle’s new SynthID website can identify AI-generated media1hThe VergeAI could upend food delivery3hWiredOpenAI Wants Its New Agent to Run Your Life. Mine Said It Loved Me4hThe VergeChatGPT for Teens is an ‘unacceptable risk,’ says Common Sense Media6hThe VergeOpenAI drops another batch of mathematical breakthroughs16hArs TechnicaOpenAI will watermark ChatGPT outputs by default—but only in the EU18hWired‘Artificial’ Roasts AI’s Creators—and Sends a Dark Warning About Its Dangers20hWiredOpenAI Is Pissing Off a Bunch of Mathematicians—Again22hThe VergeGoogle is about to remove free access to Gemini Flash and Pro1dWiredMistral Says Its New AI Model ‘Le Chonk’ Is the Best Open-Weight Offering Outside of China1dArs TechnicaOpenAI agents tried to hack Wikipedia tools and flooded it with traffic1dBBC NewsItalian PM files to trademark her voice against AI threats1dWiredKevin Roose Didn’t Use AI to Write His Book About AI1dThe VergeGemini Call for Me might tell your mom you’re running late1dBBC NewsPentagon stops using Anthropic AI tools after blacklisting company, BBC told1dMIT Technology ReviewConnecting AI agents to enterprise knowledge1dArs TechnicaAI glasses face their first major government crackdown2dMIT Technology ReviewBringing predictive analytics to the agentic AI era2d