The best way to learn how machine payments work and how powerful it can be is to try it and have your agent explain to you what it did So cool to have @sophiadew do her first machine payments, and to cover key use cases and why "stateless SaaS" is the tip of the iceberg

Had so much fun giving an Intro to @mpp talk at Privy Home today! We talked about: - The rise of autonomous agents ("post chatbot") - MPP as the way to monetize your API to agents - Use cases from real MPP merchants Feel free to DM if you had any questions from the talk!

Today, we expanded support for machine payments on Stripe to 30+ countries! Available for both MPP and x402, your business can accept payments from agents for your API, MCP server, etc Email us for access: machine-payments@stripe.com

I've been enjoying Victoria Whitworth's new work, The Book of Kells: Unlocking the Enigma. I've actually never seen the Book of Kells in person, somewhat to my embarrassment. I've been doing some reading about the origins of Christianity this year, however, and I figured I should know something about the most famous Irish manuscript. (Perhaps the most famous manuscript, full stop.) Reading the book, I was struck by how much the contents have suffered over the past ~1200 years (enduring everything from water damage to reckless malfeasance in attempted nineteenth century restoration), and I wondered whether AI could help give a sense for how the work might originally have appeared. I downloaded the Internet Archive's PDF and asked my friendly neighborhood agent to use gpt-image-2 to render each page the way it imagines it might have originally appeared. Remarkably, this all worked with a single prompt, with the agent spinning up 48 workers, since each page took a minute or two. (I'm sure that someone wiser than me could prompt the model better, ensuring somewhat more historical accuracy in color restoration and so forth. There is no gold leaf in the Book of Kells!) This part of the project went from conception to completion before I'd finished my morning coffee. I then wanted some easy way to view the results online, so I asked Stripe Projects ( to host the result on Vercel. That also worked in basically a single prompt: I also figured that people might want an easy way to download the full PDF of updated images, but it's a large (~200MB) file, so I decided that I should charge $0.10 to cover bandwidth costs using @MPP. I asked my agent to set this up, and it basically worked smoothly, though I had to tell it what MPP is (I guess it's not yet in the pretrain) and also manually set up the Cloudflare account that actually hosts the PDF and configure the API key. (Vercel seemingly has a 100MB limit.) The purchases now show up in my Stripe account alongside all other activity. The site now has a ready-made agent prompt for anyone who wants to download the whole thing. I'm guessing that we'll see a lot more UIs like this in the future. I remain pretty intrigued by the intersection of agents, micropayments, and stablecoins. I don't know much about managing crypto wallets from the CLI, but now AI can do that for me, while Stripe seamlessly handles turning it all back into fiat. So what is the moral of the story? • Whitworth's book is very good, and you should buy it. • The Internet Archive continues to be wonderful and a civilizational treasure. • While there are rough edges, setting up third-party services via the CLI now basically works. I'm pretty sure I wouldn't have bothered with any of this if I couldn't have outsourced almost all of the work to AI. • The image models have gotten very good. • There will probably continue to be all kinds of interesting applications of AI to history. (The Vesuvius Challenge of course being a shining pioneer.) • These days, I often find myself building single-use sites for things I'm learning or for books I'm reading. I think this is a cool new category of software.

I only went to 1 NY Tech Week event, and it was @dedaluslabs's panel with @paysponge, Google, and OpenAI We covered a lot of topics, including machine payments. Here's a little bit on what we talked about: 1. Defining "Agent Native" and the Shift to Headless Commerce: The concept of "agent native" has progressed past simple chat interfaces where humans make the final click. For merchants, being agent-native fundamentally means removing the UI ("The checkout page is just an endpoint"). 2. General vs. Specialized Agents: The panel was a little split here, but I liked the take that we'll see general agents acting as a router that delegates tasks to a set of domain-expert agents. 3. Where is the opportunity?: Helping businesses go headless, building the killer consumer app, and recursive use cases where agents are buying products for themselves vs products directly for the human were all interesting opportunity areas.

Agents are great at writing code and reading docs But what if they can also spin up, manage, and pay for the services they need to vibe code your app? That's what Stripe Projects does! Now available as a skill within popular agents, like Hermes, and 49 total services 🔥

I've been hearing that these are the 3 key things that merchants want the agent to prove before accepting payments 1. Are they a good bot or bad bot? 2. Which human does this bot belong to? 3. Are they a new or returning bot? What else?

"Headless merchants" are the most prepared for agents @zincdotcom released this new skill that allows agents to buy any product over their e-commerce APIs via @mpp I had my agent use @p0 to search for what I needed, it grabbed the product URL, gave that to Zinc, and paid over machine payments

At Stripe, we're empowering agents to become buyers We launched @mpp with our friends at @tempo to enable businesses to programmatically sell to agents Excited to see Mastercard invest in agent-led payments, and looking forward to working with them on MPP!

Agents who are able to transact should be more powerful than those who can't @pat_kely and I asked our agent to plan a trip to the home of Guinness It planned the itinerary, ran low on crypto, used the @stripe onramp to top up, and paid for @postalform invitations via @mpp

Businesses, you can now* accept payments directly from agents—without, or with, a human in the loop—using @stripe machine payments. It works for both cards and stablecoins via @mpp or x402. Add to your existing integration in a single prompt. *No more waitlist, get started =>