I shipped five products with my own AI agent. Then I built what it was missing.
Instructions in a prompt are requests. How I moved my rules out of the prompt and into tests, analyzers and decisions.
Thoughts and ideas about architecture and programming
Instructions in a prompt are requests. How I moved my rules out of the prompt and into tests, analyzers and decisions.
Documentation tells an agent how a library works. A skill tells it what it will get wrong from habit. Keeping the two apart is what makes either one useful.
I got the question above in my ADO.NET done right article. I hope that my answer can help others and therefore it got this dedicated post.
Do you use anemic models? i.e. having business classes like “User” without any methods but just properties instead? Do you want to do better but do not know…
There is some discussion about whether loggers should get injected into your classes (dependency injection) or if you should use the logger facade (like…
(This article has been rewritten since it didn’t seem like I managed to communicate my thoughts properly)
I just answered a question on SO about lazy loading which involved the double check pattern. It’s a really useful pattern for lazy loading since it hurts…
I’ve just written a new article on CodeProject. It’s an introduction to Inversion Of Control containers and Dependency Injection. It can be found here.
The following article aims to explain the five SOLID principles with real world examples. The SOLID principles are five programming principles which are…
I was creating an integration between my own users table (or document since I use RavenDB) with the MembershipProvider in ASP.NET. I’m using the default SQL…