-
MCP Takeaways: Structures, Workflows, and Death of the Form
Last week, Anthropic released Model Context Protocol (MCP), an open source standard proposal for enabling communication between LLM-powered apps and services that can take actions and provide context. After a week of exploring the protocol, writing a server, and most importantly, using Claude with a variety of MCP tools, I’m very excited.
-
Stripe's New Agent SDK
Yesterday Stripe announced their new Agent SDK, designed specifically for LLMs to interact with their payment infrastructure. This is the first time I’ve seen a major platform release an SDK explicitly designed for use by AI agents.
-
The Standard Model of an App
Building a single integration is pretty straight forward: read the docs, download the SDK, try the quick start and tweak to your needs. Building hundreds of integrations requires defining standards that work across many integrations. If you take that standardizing process to its most simplest/general extreme, you end up with a sort of App Standard Model. -
How It's Built: Open Interpreter
Open Interpreter (OI) is an open source project allowing Large Language Models to execute code on your laptop. It’s generated some buzz with its impressive demos.
-
How Does GPT "Know"?
Everyone I read these days is in the middle of a series of posts exploring the capabilities of Large Language Models (LLMs). It’s fascinating to see the global community trying to build a collective understanding of how they work and their potential impacts, and I’m along for the ride. Expect this to be the first of a series of posts as a I rubber duck all this out for myself.
-
The Most Important Thing Dropbox Did to Scale Product Management
One of the most valuable experiences was seeing Dropbox rapidly scale (both in customers and employee size), and witnessing all the issues that arise as those numbers increase. Today, I want to talk through the framework we developed for keeping the growing company on the same page through the product development process.