Recent Posts

While a single generalist AI coding agent can be useful, sometimes it helps to have teams of specialist agents working in coordination.

Ardalis, Barret, Michelle, and Sadukie presented this year, and we were all in attendance. In this post, we're sharing some of our adventures from Stir Trek 2026.

In this recap we walk through the key take‑aways from the Domain Events webinar, highlighting patterns, best practices and real‑world use cases.

With agent-driven workflows, you are able to describe an outcome and have the agent figure out the steps to reach that outcome.

There are things that an AI coding agent simply isn't capable of doing out of the box. This is where MCP servers come in.

Teach your agents how to do specific things - knowledge for repeatable tasks. This is the domain of skills files.

Learn how you can extend your testing plane by using property-based testing, contract testing, and test doubles.

You launch an AI, give it a prompt, and the result generally isn't great. AI agent instruction files help guide your agent to better results.

Code reviews are among the highest value, yet most time consuming aspects of the modern development process. While it cannot, and should not, replace human developers in the code review chain, AI can prove a valuable resource to handle much of the mechanical work of the flow – styles, naming, bugs, null checks, and so forth – so that human reviewers can focus on architecture, intent, correctness, and nuance. When applied prudently, AI can be a critical augmentation to humans in the process.

Unit testing has been around for a long time. We know how to do it. It's a well established pattern and it just works. But unit testing an LLM is nothing like testing a sorting algorithm.