Morgan Willis

I gave an AI agent the vended bash tool from Strands and asked it to read my AWS credentials file. At...

Context engineering matters for two reasons: reliability and cost. If your agent's context window is...

How to defend AI endpoints against inference theft and denial-of-wallet attacks: bot detection, guardrails, cost-aware routing, and budget controls.

To have an AI agent, you need to build a harness first. But what exactly is an agent harness? The...

Customer support agents are hallucinating policies. Coding agents are deleting production resources....

So you want to add AI to your application. Maybe you want to build a smart assistant, add a feature...

Building an AI agent in Python can be as easy as giving a model some tools and letting it figure out...

We've always designed APIs for humans. A well built API means obsessing over naming conventions,...

Most AI agents don’t reliably follow directions, and that’s one of the biggest reasons they never...

"Software engineering is solved." This is all I see lately when scrolling LinkedIn, X, or...

What if you could write a Python function where the docstring is the implementation? You define the...

Most AI agent tutorials show the same problematic pattern: a front-end client directly invoking an...

Most agents that are useful need access to private data. They need to query internal databases, call...

AI agents are getting easier to build and host. With agentic frameworks and cloud-based hosting...