November 6 2025 by
B-Drive in
AI |
Here’s a good use case as to why developers are needed to monitor code generated by AI. Using Amazon Q, I set up a project that is a 100% unit test project to be 100% AI generated, for another barely tested project. (More about this later; was not a smooth creation.) This is grails — […]
Generating out descriptive schema for your existing applications that AI can well. Working on a Grails API application, I am using with BurpSuite DAST to do some security testing on a regular basis for it. I’ve needed an API list of endpoints for their API security scan feature for quite some time, that’s easy to […]
October 20 2025 by
B-Drive in
AI |
AI often misfires the more I work with it. I think the big issue is, you cannot forget that you continually need to keep AI guided and boxed into your task, or you will get hallucinations and errors. Here’s an example of an agent example using Gemini. It asks for a complex math question, and […]
October 10 2025 by
B-Drive in
AI |
Here’ an issue I’ve run into repeatedly: AI having old versions of APIs for services, in this case JIRA, who recently updated theirs and didn’t leave any backwards compatibility (and also hosed my dev data lake). I have a python script I AI’d out of Claude to extract JIRA data for a BERT model training. […]
October 7 2025 by
B-Drive in
AI |
Let’s talk about using AI in this current age of 2025. Here’s a stock photo to help out: As obvious as it sounds, writing prompts for an AI chat session is a lot like golf. Basically, honing down until you get a good answer OR run out of chat memory and have to move to […]
September 26 2025 by
B-Drive in
AI |
This is just an open thought/notes post — using agents specifications files in an AI development environment. These kind of files are written in Markdown, and can do some of these kind of things: There’s an emerging standard, open source, called AGENTS.md. Here’s their first page sample: # AGENTS.md ## Setup commands – Install deps: […]
September 15 2025 by
B-Drive in
AI |
Was running Jira integrations with Clade AI — and the total count of issues was coming back incorrectly. I’d get twenty-four issues back for what would be a few hundred (163 in this case) results I could see in a JQL console in Jira. A JQL query like this: project = “<project>” AND “Fix Version” […]