I tweeted a twelve-point spec for what an agent-native cloud actually needs to look like. Vercel volunteered. Cloudflare's engineers got to work. Here's the test.
The AWS "solution" to this would be to get a few Solutions Architects to wire up 12 different Lambda functions, four CloudFormation stacks, a marketplace vendor, and wrap it up into a blog post and awslabs GitHub repository.
That said, AWS might still make out here. How many of the solutions are using AWS infrastructure to power what their customers don't see?
I mean, Vercel is a front-runner and they ride on top of AWS. Vercel is also a reportedly $10B business; the only reason AWS couldn't have built something equivalent is a lack of organizational will to do it.
The AWS "solution" to this would be to get a few Solutions Architects to wire up 12 different Lambda functions, four CloudFormation stacks, a marketplace vendor, and wrap it up into a blog post and awslabs GitHub repository.
That said, AWS might still make out here. How many of the solutions are using AWS infrastructure to power what their customers don't see?
I mean, Vercel is a front-runner and they ride on top of AWS. Vercel is also a reportedly $10B business; the only reason AWS couldn't have built something equivalent is a lack of organizational will to do it.
How does AWS AgentCore not meet the definition of the right set of primitives for Agentic Engineering?