🧙🏼 Easily set up a Claude Agent

Howdy, wizards.

Quick reminder: Nexla is hosting an awesome free webinar today about data leaders overcoming challenges to build and accelerate AI initiatives. Check out ‘Driving AI Innovations on Data Foundations’ at 2 pm ET/11 am PT.

And now – what’s brewing in AI today.

DARIO’S PICKS

1. How to easily set up and run a Claude Agent in 20 minutes

Allie K. Miller just posted the tutorial on how to easily setup a Claude Agent on your coffee break, so you can start testing the Computer Use feature!

This means you’ll be one of the first people in the world to try AI agents.

Everything is super simply explained – no technical skills needed. In brief, the steps are:

• Installing Docker

• Getting an API key from the Claude Console

• Installing the Computer Use demo through the Terminal

• Prompting Claude with Computer Use on a virtual desktop

At the end of the article, there’s a tip on how to add in custom system prompts (similar to custom instructions in ChatGPT) as well as links to 9 cool use cases people have found for Computer Use.

‎ Why it matters‎ ‎ Allie has a knack for explaining things simply, which is very helpful.

For my first test, I asked it to go online and subscribe to What’s brewing in AI (yes, this newsletter) using the email [email protected]. First it tried going to the URL whatsbrewinginai dot com (which isn’t my website), before doing a Google search, finding the right page and successfully subscribed. Took a couple of minutes and costed exactly $0.13.

Have to admit this experience caught me off guard a bit; I’ve read so much about this feature, but testing it in real-life—seeing the steps it takes, the process and that it actually works—it’s truly impressive. Of course it’s still a bit clumsy, but it’s an early look on what’s coming.

TOGETHER WITH HUBSPOT

Use AI as Your Personal Assistant

Ready to save precious time and let AI do the heavy lifting?

Save time and simplify your unique workflow with HubSpot’s highly anticipated AI Playbook—your guide to smarter processes and effortless productivity.

Download the free guide today.

DARIO’S PICKS

2. Stripe makes it easy to build AI apps that can buy things for you

Stripe just unveiled an Agent Toolkit, allowing developers to integrate Stripe’s payment services into agentic workflows – making it possible to do things like charge users based on metered usage, handle refunds and manage billing.

For example, if you’ve built an agent that can search flights according to the user’s requirements, you could use this toolkit to make it possible to purchase the tickets. It’s compatible with common frameworks including AI SDK, LangChain, and CrewAI which make it easier to build the agents.

‎ Why it matters‎ ‎ Stripe’s toolkit help bridge the gap between LLMs and programmatic actions, in this case executing financial transactions as part of their tasks. It’ll make it easier to build functionality like the one I wrote about yesterday: Perplexity enabling shopping directly within its platform.

Expect more AI apps that can buy stuff on your behalf very soon.

THAT’S ALL FOLKS!

Affiliate disclosure: To cover the cost of my email software and the time I spend writing this newsletter, I sometimes link to products and other newsletters. Please assume these are affiliate links. If you choose to subscribe to a newsletter or buy a product through any of my links then THANK YOU – it will make it possible for me to continue to do this.