Torben Anderson

Torben Anderson

Fractional CTO and AI Operations
SpotifyGitHubCursor

About

Fractional CTO and AI Operations Founders with traction who need to move fast ➡️ Let's talk http://rewired.co Building: 🤖http://slatemd.app 🗳️http://trustpoll.io 🫆http://icebox.my After 40 years building software - from early home computers to enterprise banking systems - I now help founders turn expertise into revenue-generating software engines. I have led teams of 60, delivered platforms handling billions in transactions, and built my own company to seven figures. Today I combine strategic CTO leadership with hands-on delivery. More: https://www.rewired.co/about

Badges

Tastemaker
Tastemaker
Gone streaking
Gone streaking

Maker History

  • Slate
    SlateThink in markdown. Reason with AI.
    Apr 2026
  • 🎉
    Joined Product HuntSeptember 1st, 2024

Forums

Kyan

2d ago

Are we over-engineering AI memory? (Markdown vs. Vector DBs for small datasets)

Hey makers!

Lately, I ve been looking closely at how independent builders and small teams are managing AI knowledge bases. It feels like the default "industry standard" is to immediately reach for a complex RAG pipeline and a heavy, paid Vector Database.

But I'm starting to wonder if we are over-engineering this for 90% of standard use cases.

Vector DBs are incredibly powerful for massive scale, but for smaller or non-massive datasets, they can be expensive, complex to query, and act as complete black boxes. If a search returns a weird chunk, diagnosing it is often a nightmare.

View more