Amazon Bedrock AgentCore payments - Solving the microtransaction problem
We have covered Agent to Merchant payments for e-commerce, but what happens if your agent wants to call out to a pay-per-request API or a pay-per-use model? A while ago, we discussed the x402 protocol. There is a new breed of business popping up selling API requests and model invocations for fractions of a penny per request. This is great if you are actually going to make thousands of requests, but what if your agent just needs to make 10 requests for a deep research project you are working...
1 day ago • 1 min readAWS Meeting Simulator (No, this is not a joke)
It’s official: AWS has way too many services. Did you ever wish you were in more meetings? How about meetings just to practice being in a meeting? Well, now you can with AWS Meeting Simulator. No, this is not an April Fool’s joke, though I wish it was. AWS has released a virtual service so you can “increase your soft skills” by meeting with AI bots in a simulated meeting. Call me old-fashioned, but if you want better people skills, you should probably interact with real people. I am all for...
4 days ago • 1 min readLooking for a way to emulate AWS services locally?
If so, then you should check out MiniStack. They have an impressive amount of services that they state they can mimic, even including some of the advanced Event Driven Architecture and Data Lake services I love, like Athena, Kinesis, and Glue. They don’t do Bedrock or Sagemaker quite yet, but that makes sense as a lot of people’s local envs would struggle to emulate the beefy hardware required to run those models. You can even provision it with Terraform, which I love. You might point out...
5 days ago • 1 min readBad Actors are scamming tokens off of AI compute providers
Stripe is seeing a pattern emerge for businesses that charge by the token. In a recent post Stripe made, they outlined a new form of fraud. Well... kind of new. According to the post, “one in six attempted sign-ups is made by a bad actor, and free trial abuse has more than doubled in the past six months.” That is wild to think about. One in six? You also have to wonder about how many they missed as well. Using their tool, Stripe Radar, they claimed to have “blocked more than 3.3 million risky...
6 days ago • 1 min readStripe, one of the world's largest payment processors, has gone all in on Agentic AI
At Stripe’s annual customer conference, they announced a lot of big things, and they are doubling down on Agentic AI. What does that mean? Almost a year ago, I did a presentation predicting the rise of AI Agents that will purchase things on your behalf. I’m not going to pat myself on the back too much, as the whole internet was already screaming about exactly that. Since then, several protocols have emerged, like AP2 and ACP. Then, a few weeks ago, Stripe announced a product(not protocol); a...
8 days ago • 1 min readUpdate on Matt’s Vibe Coding journey
Are you sick of hearing how good AI Agents are at programming? I know I am, but it's my job to evaluate and document my various experiments with cutting-edge technology. Recently, I tried using Hermes Agent. I ran Claud Opus 4.6, which was the latest model that was available on AWS Bedrock. As I look now, it looks like 4.7 is out. The task I gave it was simple: just update the dependencies for Schematical.com. The result…. The local version of Schematical I gave it access to is pretty much...
11 days ago • 2 min readAmazon Workspaces now has AI Agents
Have you ever needed to give AI Agents full access to a desktop without setting it free on your computer? Amazon Workspaces has been around for a while, offering cloud-hosted virtual desktop environments. Now, Amazon has added AI Agents to its Workspaces. Just like everything else on the planet. I say that jokingly, but this actually could be useful for certain use cases. If you had some software that only had a desktop interface and no API that you wanted to automate tasks, this could be a...
12 days ago • 1 min readValkey GLIDE
Want to save 95% on your inter AZ costs while decreasing latency by 49%? Previously, I had written about how replacing your Redis ElastiCache clusters with ValKey can save you 33% on your AWS bill. But are you still using a Redis first client to connect to Valkey? Then you might be missing out on some native valley functionality. You may want to check out Valkey GLIDE (General Language Independent Driver for the Enterprise). Under the hood, it's written with RUST, but it has wrappers for...
13 days ago • 1 min readCTO Coffee Hour: Off-Market Data
On today's episode of CTO Coffee Hour, Matt & Dom touch on Off-market Data and where is the next big business opportunity. Check it out now!
14 days ago • 1 min read