General
Share and discuss tech, products, business, startups, or product recommendations
Start new thread

When does it make sense to actually use less AI?

by•

I think AI is incredible but I do think people over-engineer solutions when it's not necessary. When would you say personally that adding AI would be a detriment to your product offering, or when do you think it makes more sense to look for more deterministic solutions.

22 views

Add a comment

Replies

Best

It comes down to structured vs. unstructured data. I build both AI apps and standard SaaS. If I'm dealing with messy, unstructured PDFs, AI (specifically local RAG) is strictly necessary. But for dev tools handling structured session data or analytics, forcing an LLM into the loop is usually just a marketing gimmick. Deterministic logic is faster, cheaper to run, and easier to debug.

my thoughts exactly. That’s why I believe we should try as hard as possible to make context deterministic. No need to have models in the loop to know if an app can deploy or not. Just deploy the container and check the logs

 100%. Container logs are the ground truth. It's crazy how the tech industry tries to force LLMs into systems that have worked perfectly for a decade. Keep it simple and reliable.

I'm refering to SaaS and dev tool products in particular, but more then open to hearing everyone's perspective.