sebbi.pro
SPEND GATE · NEW

Your AI can't spend
without a sign-off.

Give an AI agent money to spend and you're trusting it not to go wrong. Spend Gate takes that on trust away. The agent asks sebbi.pro before every payment, it's checked against the limits you set and scored by the engine, and you get back a signed yes or no. Over the limit, wrong payee, acting out of line? No signature. No spend.

sebbi.pro is the sign-off, never your wallet. It never holds your money or the keys to it. It signs the decision; your own payment system releases the money only if the signature says yes.

Try it

A live agent with a £100-per-payment limit and a £250 daily cap. Paste your sebbi.pro key, or just watch the decisions — every one is sealed and provable.

How your code uses it

One call before the agent pays. Release the money only on an approved, spendable token.

POST https://sebbi.pro/x/spendgate/request
{ "api_key": "YOUR_KEY", "agent": "billing-bot",
  "amount": 49.99, "payee": "AWS", "reason": "monthly compute" }

-> { "decision": "APPROVED", "token": "sbg1.…", "expires_utc": "…" }
   release the payment, then POST /x/spendgate/confirm { token }

-> { "decision": "DENIED", "reasons": ["over the per-transaction limit"] }
   do not pay

Anyone can check a token's signature against the published key, with no call to us: /x/continuity/pubkey. Or let an AI assistant run it all — connect https://sebbi.pro/mcp and ask it to gate a payment.

Why it holds

YOU SET THE RULES

Per-payment limit, daily cap, an allow-list of who can ever be paid. Per agent.

IT ASKS FIRST

Every payment is scored by the live engine and checked against your rules before a penny moves.

SIGNED YES OR NO

A short Ed25519-signed token, valid once, for a few minutes. Anyone can verify it.

SEALED FOREVER

Every approval and refusal is in the chain and provable against Bitcoin.

AI news
TechCrunchTony Fadell on why the first wave of AI gadgets failed — and what comes next19mTechCrunchGoogle experiments with an AI-powered gaming platform25mTechCrunchOpenAI’s Alexander Embiricos is coming to TechCrunch Disrupt 2026 — days after the launch of Dots31mArs TechnicaMistral says "Le Chonk" can challenge the best AI models48mArs 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 breakthroughs15hArs TechnicaOpenAI will watermark ChatGPT outputs by default—but only in the EU18hTechCrunchHow AI decision models could change content moderation18hWired‘Artificial’ Roasts AI’s Creators—and Sends a Dark Warning About Its Dangers20hWiredOpenAI Is Pissing Off a Bunch of Mathematicians—Again21hThe 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 era2dTechCrunchTony Fadell on why the first wave of AI gadgets failed — and what comes next19mTechCrunchGoogle experiments with an AI-powered gaming platform25mTechCrunchOpenAI’s Alexander Embiricos is coming to TechCrunch Disrupt 2026 — days after the launch of Dots31mArs TechnicaMistral says "Le Chonk" can challenge the best AI models48mArs 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 breakthroughs15hArs TechnicaOpenAI will watermark ChatGPT outputs by default—but only in the EU18hTechCrunchHow AI decision models could change content moderation18hWired‘Artificial’ Roasts AI’s Creators—and Sends a Dark Warning About Its Dangers20hWiredOpenAI Is Pissing Off a Bunch of Mathematicians—Again21hThe 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