Muhammad Umar at Codeninja explains how to actually ship AI products. His team wired Anthropic's Claude into sales workflows and found that the real work isn't the model itself, it's the plumbing: reliability engineering, security hardening, and system integration that makes LLMs work in production.
Think about what kind of admin work that we can automate with cloudbot and plugging it with language models or open source models, whatever. There's lots of engineering and plumbing that goes into make AI work. And by the way in Codeninja, I mean we built, we're building our products, we've launched a couple of products. But one of the core thing that I'm passionate about Adil is passionate about is like make AI work for the customers because we think it's not about services or product, it's about there's so much plumbing that goes into making AI work. I mean we've, we've hooked Claude into automate most of our sales workflows. Right now Claude is doing a lot of my work. But the kind of plumbing and engineering that's required, for example, even just to make cloudbot harden enough that we can secure our secure reliability and security, it takes a lot of effort and lots of engineering and lots of plumbing.
FDE Epi : 16 | AI Agents, Billion-Dollar Infrastructure & the Future of Intelligence
