<div dir="auto">I have my agents really dialed in on classic software and data science practices. They run in a very old school, gated design, dev, test, release cycle. I've found it works very well compared to other in the org who are more vibe focused. It's funny that being away so long was an advantage when I came back. My stuff works, is documented, and maintainable and observable. The same can't be said for lots of the other Ai or AI assisted projects in the enterprise. <div dir="auto"><br></div><div dir="auto">I've mainly been building heuristic services that then feed the AI analytics so it's good, verifiably correct data going in.</div><div dir="auto"><br></div><div dir="auto">What I really like is having my ai dev team but also an AI engineer managing my servers. It's funny when they complain about each other. </div><div dir="auto"><br></div><div dir="auto">James</div></div><br><div class="gmail_quote gmail_quote_container"><div dir="ltr" class="gmail_attr">On Wed, Oct 14, 2026, 8:40 AM Jay Vaughan <<a href="mailto:seclorum@icloud.com">seclorum@icloud.com</a>> wrote:<br></div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Just wanna add for James, DGX’ tooling environment is superlative and really pretty deep .. NVIDIA’s tooling is far better than any other platform (including Apple) in my opinion. It will be really interesting to see what Apple do in their tooling next year, but NVIDIA is way ahead of everyone at the moment .. so DGX Spark comes with some hefty tools, just sayin’, out of the box like ..<br>
<br>
j.</blockquote></div>