Thanh Nguyen

Product mind × designer soul × marketing roots
Building small, real products with AI ✨
Daily OS → more experiments soon

[Dipanshu Kushwaha @Dipanshu_AI]

Instead of watching 1-hour of Netflix today, watch this Stanford lecture by ex-GoogleBrain & OpenAI engineers.

this is the best explanation on how LLMs like ChatGPT & Claude actually work, and how to unlock 100% of their potential.

worth watching whether you're a senior AI engineer or just taking your first steps in AI.

I took the key ideas and turned them into a practical guide on how to actually get 100% out of AI.

You can find it below with ready-to-copy prompts and solutions.

[Anatoli Kopadze @AnatoliKopadze]

Google Brain founder, Andrew Ng:

"Prompting will be dead in 6 months, graphs are what's replacing it."

In 2 hours at Stanford he shows how to build agents that work and improve entirely on their own.

The first 10 minutes cover what most $500 courses never do.

Watch the lecture first, then read the guide below on how to build a system that improves itself.

[Kirill @kirillk_web3]

A Chinese developer just explained the shift from Loop Engineering to Graph Engineering better than anyone.

most people are still building agents the way that's about to be obsolete.

> why single-agent loops break and go "goal blind"
> the 4 parts of a graph: nodes, edges, state, policy
> 3 topologies that run everything: diamond, supervisor, pipeline
> Anthropic's 5 official workflow patterns

the punchline: it's not how many agents you run. it's the determinism you build with verifiers, code fallbacks, and reality anchors.

I broke the same architecture down with Kimi K3. Full A-Z guide below.

[Thanh Nguyen @designedbythanh]

UI mistakes are easy to fix.
System mistakes are expensive.
That’s why building small beats perfect mockups.

[Thanh Nguyen @designedbythanh]

Daily OS taught me something uncomfortable:
the hard part isn’t UI
and it isn’t code either
It’s understanding how everything connects. 👇

[Thanh Nguyen @designedbythanh]

Even a small product has a moving parts:
user → state → data → logic
Miss one connection → everything breaks.

[Thanh Nguyen @designedbythanh]

Context matters.
AI doesn’t own context. I do.
Direction first. AI second.

[Thanh Nguyen @designedbythanh]

I don’t use AI for everything.
I’m picky.
Here’s when I trust it and when I don’t 👇

[Thanh Nguyen @designedbythanh]

I don’t trust AI for system decisions:
– boundaries
– data structure
– auth
– refactors

[Thanh Nguyen @designedbythanh]

AI doesn’t remove thinking.
It exposes where thinking is missing.

[Thanh Nguyen @designedbythanh]

Building with AI didn’t fail me.
My assumptions did.
Mistakes I made while building Daily OS 👇

[Thanh Nguyen @designedbythanh]

Mistake #3: I prompted for outcomes, not logic.
“Fix this bug” gave patches.
“Explain how this works” gave control.

[Thanh Nguyen @designedbythanh]

If you’re stuck trying to build your first product, which part worries you most?
– Idea
– Design
– Code
– Shipping
– Something else?

[Thanh Nguyen @designedbythanh]

A few people asked how I started building Daily OS.
I’m a product designer with zero engineering background.
I didn’t start with tools or features.
I started with one behavior I kept failing at.
Breakdown in replies 👇

[Thanh Nguyen @designedbythanh]

I shipped v0 in 5 days (1–2h/day).
Rules:
– not beautiful
– not perfect
– just usable
Shipping beats confidence.
Shipping creates clarity.

[Thanh Nguyen @designedbythanh]

After that: VS Code + Vercel + Supabase.
Sounds complex.
It wasn’t — with AI guiding me step by step:
setup → run → debug → deploy.
I didn’t “know” code.
I followed → understood → adjusted.