Agents can now create Cloudflare accounts, buy domains, and deploy

It is cool feature but to what end? Buying a domain is not something you have to do daily to require any kind of automation.

I am also not sure who Stripe Atlas for. I am genuinely confused. It is definitely not something a developer will use.

I understand that you can bootstrap a number of systems but that is like half-hour of work and arguably it is probably a good idea to do it manually to make sure you have strong foundations.

I've have personally never seen a good example where a cross vendor account provisioning actually working. For example, Fly.io used to provision Sentry accounts automatically which you could not access in any other way but through Fly.io. I mean the Sentry account was effectively locked to a project that you cannot transfer - hijacking the actual global alias as well. Vercel did something similar with PostgreSQL via Neon and Redis via Upstash resulting in painful migration processes.

I can imagine ending in some kind of deadlock between services due to security hence why the 30 minutes initial setup is kind of time well spent to avoid future issues.

Maybe it's me.

> This account is in violation of Cloudflare's Terms of Service. Specifically fraud. The suspension is permanent.

(Yes that’s really it. Sincerely. No “but I also abused X”)

I see the amount of work that gets put into these workflows and it boggles my mind that anyone thinks that it's faster or easier or more convinient or more cost efffective than installing a LAMP stack on one of the 6 laptops they have stuffed in a closet. God forbid anyone have any native local capability.

You can have a zero-cost inbox.

Earlier, I was using Zoho and FastMail (however you dice it, it will use some money, $12 a year for Zoho and $7 per month for FastMail? Even then, perhaps you only get one mailbox and some aliases)

but with this method, I get unlimited aliases, domains, and mailboxes:

Now, I wrote a script which captures the email and saves attachments to S3 using the HTTP API (why S3 and not R2? Because Cloudflare wanted a credit card, and I was too lazy to add it there lol) and emails to D1.

This uses an email -> webworker workflow.

I use an API to fetch my emails.

This means all my inbound emails are now handled by Cloudflare, and I can easily use all of it with zero payment.

The best part is this supports tokenised emails, so I can provide a unique email address to each service I sign up for.

I am using SES as the sender. I’ve set up one script which auto-sets up any domain in SES and auto-verifies the sender email.

The funniest thing is I am receiving zero spam? As if other email providers sell my email?

Basically, now it's trivial for any new devops guy to run such a query in Claude Code:

“Log in to this production server, find out all services it runs and their deployment method, create documentation about everything, and generate a repeatable, auditable deployment workflow.”

Devops and sysadmins can no longer withhold information to maintain job security.

Boom, 80% of the team gone.

I know companies are doing migrations of production Postgres and MySQL on 1000s of machines using AI agents.

I’m imagining how many SaaS will be automated out and simply be an "agent skill" in ClaudeCode.

While they are on the phone with the agent, it buys a domain relevant to the victim, the agent codes and deploy the website specially catered to them and the fraud bucket. Collect payment, destroy the website, redirect the domain to google.com. no need to start a new call because you had several agents committing the same fraud in parallel.

It can also be used to make art.

But jokes aside having a central place to manage billing and accounts for deploying infra across multiple providers is pretty awesome imo.

if they have a terraform provider even better. I wonder if also makes multi tenant architectures or environment isolation easier to provision as well.

Also, when an agent sets up a domain, who is the domain owner? Who responds to takedown requests? What if it then decides to host illegal content at the domain (generated or otherwise). Who is responsible? Agents aren't (yet) legal persons, so it must be the person who owns the agent, but if that person never even sees the legal agreement being agreed to how would it hold up in court? If the person didn't direct the creation or hosting of illegal content, what then?

This looks interesting nonetheless.

Soft scammers, fraudsters and defamers are celebrating in copying websites for malicious intent.

For sure this is going to get abused.

Why didn't Amazon think of that?

good luck