Claudia

I ❤️ math & languages. Data Scientist, polyglot and traveler🌏

✍️ Medium: AI EngineerBlog:

[Claudia @ds_claudia_]

I received my first donation of $10 to my AI language learning product, CantoAI!

It's a small amount, but I'd created something that at least one person values.

If you've been procrastinating out of fear: it doesn't get less scary, you just do it anyway.

[Claudia @ds_claudia_]

Lesson learned: AI fails silently. Unlike traditional software, it can produce plausible outputs that are completely wrong.

Monitoring AI products means tracking behavior, not just crashes.

[Claudia @ds_claudia_]

I built an AI to help people learn Cantonese. I forgot about it over Christmas.

API credits expired.

For two weeks, the AI returned “I don’t understand, please try again” for every query.

No errors, no alerts. Users dropped off quietly.

[Claudia @ds_claudia_]

@JesseTetsuya @pyconthailand Thank you @JesseTetsuya! I blogged about @pyconthailand and featured your presentation as one of my two favourites: https://t.co/RUtuSFCW5F

[Claudia @ds_claudia_]

Really enjoyed your talk at @pyconthailand, @JesseTetsuya!

As a former MLE, I’ve felt that same lack of flexibility when wrapping models in REST APIs. Which kinds of models do you think benefit most from being wrapped as MCP tools vs REST endpoints?

[Claudia @ds_claudia_]

To all the engineers who got paged during the AWS outage last night: I feel for you.

Being on-call is rough.
Being on-call for something you can’t fix is existentially rough.

You’re out here rebooting servers at 3 a.m., praying the cloud gods show mercy.

Take a nap today.

[Claudia @ds_claudia_]

People ask me how I learned Python without a CS background.

Honestly? I treated Python as a tool.

You don’t need to master everything.

Knowing pandas, JSON, and basic plotting are enough to start shipping small analytics projects.

Learn the rest when your project demands it

[Claudia @ds_claudia_]

You don’t need to know everything.

Just enough to apply it.

[Claudia @ds_claudia_]

When I was learning Python, I kept forgetting everything.

I’d ace a tutorial… then freeze the next day staring at a blank screen.

What helped wasn’t more studying. It was more doing.

Here's what I would tell myself if I could go back in time 👇

[Claudia @ds_claudia_]

If your goal is to use Python →
Build one small project that mimics your dream role.

Want to be a data analyst? Analyze a public dataset.

Want to do ML? Build a simple classifier end-to-end.

[Claudia @ds_claudia_]

In the past 2 weeks, 85 people tried my Cantonese AI partner:

213 conversations

993 interactions

A couple users came back 6–7 days straight

Most dropped after day 1

Now I’m stuck: Do I keep fixing bugs + adding features? Or pause and set up Stripe to see if anyone pays?

[Claudia @ds_claudia_]

I got a “fan message” for my AI prototype!!

It wasn’t about the tech. It wasn’t about features.

It said:

“Thank YOU so much for making this. I love it. I will keep going.”

🥹

[Towards Data Science @TDataScience]

In this Author Spotlight, @ds_claudia_ breaks down her biggest lesson in ML: domain expertise matters more than algorithmic complexity. She shares insights on mentoring, career transitions, and the realities of working with AI.
https://t.co/lvWBFqKLN6

[Claudia @ds_claudia_]

https://t.co/7w5kWcGq6q

[Claudia @ds_claudia_]

Woke up to see AI Weekender ranked #51 in Tech on Substack 🎉

I started on Jan 23 with one goal: publish every Thursday.
Some posts hit, others sank.
But showing up each week built momentum.

Biggest lesson? Consistency compounds.

[Towards Data Science @TDataScience]

✨ In our latest Author Spotlight, @ds_claudia_, who successfully shifted from a corporate role to freelance, provides hard-won advice on navigating career paths, mentoring newcomers, and building solutions you truly own.

https://t.co/lvWBFqKLN6

[Claudia @ds_claudia_]

Every project should either:

- Build skills
- Build assets
- Build your brand

If it’s doing none, stop.

[Claudia @ds_claudia_]

As a solo data scientist, I’ve found 3 types of leverage:
- Coaching gave me human leverage
- Consulting gave me applied leverage
- Content and AI tools? That’s scalable leverage

Read more here:
https://t.co/U2GCIsGezr

[Claudia @ds_claudia_]

When to tune prompt vs. build RAG vs. fine-tune:

Prompt: The AI knows but needs better instructions.

RAG: Your AI needs fresh or custom info.

Fine-tune: The AI doesn’t think like you want it to, consistently.