AI That Works: Teaching agents to pay with Apify
HTTP 402 "Payment Required" has been in the HTTP spec since 1997 and almost nobody has used it, because the clients that needed it didn't exist yet. They do now.
AI That Works is a monthly meetup for anyone building with AI in Austin: developers, founders, operators, go-to-market teams, and the AI-curious. Every session: live demos from people shipping for real use cases, a hands-on build, and honest conversation about what's actually producing results.
We don't care if you're writing code or mostly prompting. If you're putting AI to work on something real, you belong here.
This month
Your agent can call any free endpoint you point it at. The moment that endpoint costs money, it stops. It can't enter a card, approve a subscription, or agree to a rate, so the workaround is always the same: you, in the loop, pasting in an API key.
This month we take you out of that loop. You'll watch an agent hit a paid endpoint, get a 402 back with the price attached, pay it, and retry - no human, no subscription, no key. Then you'll run the same flow yourself against a real paid Actor on the Apify platform.
This is the session Apify brought to the RenderATL AI Summit in Atlanta earlier this month, the only talk there on agentic payments, rebuilt so you leave having actually done it rather than having watched it.
If you're building agents that need data they don't own, you'll see what the payment layer looks like when it isn't a human with a credit card. If you publish tools, you'll see the other side of it: what it takes to charge an agent directly, per run, with no account and no signup.
How the evening works
We start with why this gap exists. Agents are expected to go out and get things - data, compute, services - but every paid door on the web is built for a human with a browser and a card. HTTP 402 was reserved for exactly this case decades ago and then sat unused, so we walk through what the status code actually specifies and what had to be built around it before anyone could use it.
Then the protocol itself. You'll see a request fail with a 402, read the payment terms that come back in the response, and follow the negotiation step by step: what the agent is being quoted, what it sends back, and how the service verifies it before serving the content. Nothing hand-waved - the whole round trip, in the open.
Then you run it. You'll point an MCP client at the Apify MCP server with x402 support, call a paid Actor, and let the agent settle the charge on its own. Same run you'd normally pay for with a plan and a token, except this time your agent handles it and you watch the payment land.
We close on where this fits and where it doesn't. Per-call payments make sense for some workloads and are the wrong shape for others, and it's worth being honest about which is which before you build on it.
Bring your laptop.
Agenda
5:30 pm - doors open and networking
5:45 pm - kickoff and presentation
6:15 pm - hands-on
7:15 pm - wrap-up and chatting
7:30 pm - end
What you'll need for the hands-on portion
A laptop (macOS, Windows, or Linux)
Node.js installed
An Apify account (free tier works, sign up at apify.com)
An MCP client you're comfortable in: Claude Code, Cursor, or similar
A Base wallet, if you have one. It'll get you set up faster, but it isn't required - if you turn up without one you can still follow along, and we may be able to top up your agent's wallet with a small amount of USDC during the workshop.
Don't have all of this? No worries. You can follow along with someone at the event who does. The concepts apply regardless of your stack.
About the host
Apify is the largest marketplace of tools for AI. Thousands of ready-to-run tools called Actors to get live web data, automate jobs, and plug into your apps and AI agents. Tonight your agent pays for one by itself. But this meetup isn't a product pitch, it's a community. See what others are building, learn something new, and meet the people doing the work.
👾 Join the conversation on Discord.
Explore Apify at apify.com.
We will use your information to contact you about the event. For more information, see our Privacy Policy.