AI engineer · writer · maker

Hey, I'm Shawn.
I talk about AI and practical ways to become more efficient, focused, and productive!

By day I ship machine learning systems to production. Here I write deep dives on the computer science nobody looks at, and share the AI prompts I use to get more done with members.

Also building: Krevaya AIvidfora

Shawn Ng

🧠

Deep dives that respect you

The ranking model deciding what you watch, the math holding up the internet: real systems, real numbers, no hand-waving.

The Vault

A growing library of battle-tested AI prompts for planning, writing, coding, and killing busywork. Less busywork, more real work.

🛠️

Built in the open

I ship my own products, Krevaya AI and vidfora, and the lessons from building them feed straight back into what I write here.

The Vault

Steal the exact prompts I use to work faster.

Not one-liners: complete systems with a role, a process, and an output format. Paste one into your AI assistant and it just works.

  • 24 battle-tested prompts, organized by job
  • Planning, email, meetings, learning, writing, and code
  • Works with Claude, ChatGPT, or any capable assistant
  • New prompts whenever I find something that works
Join me

No credit card. Just an email and a password.

Latest deep dives

Stories about the hidden computer science running the world.

All articles →

What Is Jev? TypeSafe AI's System One Model, and Why It Refuses to Talk

15 min read

Jev is TypeSafe AI's System One model: a non-autoregressive transformer that returns typed, calibrated decisions instead of text. How it differs from LLMs.

  • ai
  • llms
  • machine-learning

What A MEAN Stack Developer Actually Is (And What I'd Tell You Seven Years Later)

9 min read

MongoDB, Express, Angular, Node: what each layer does, what the job looks like day to day, and an honest reassessment of one-language-everywhere in 2026.

  • web-development
  • javascript
  • node

Recommendation Is Vector Search With a Query You Never Typed

14 min read

Search and recommendation run the same engine: encode a query as a vector, return the nearest items. Only the query's origin differs. Here is the geometry.

  • recommendation-systems
  • vector-search
  • information-retrieval

The State of AI: A Field Report From Someone Who Actually Ships This Stuff

11 min read

A working engineer's mid-2026 field report on AI: what changed, what plateaued, where production reality is messy, and where the real work moved.

  • ai
  • llms
  • machine-learning

What I'm building

Products I'm shipping right now: the same systems thinking from the blog, aimed at real problems.