Andres

Backend Developer in Progress 🚀
Automation Engineer → Software Engineer
Building projects with Python | FastAPI | SQL
Sharing the journey daily

[Andres @AndresBuilds]

I’m transitioning into backend engineering.

I work with real-world systems (warehouse automation), but I’m leveling up in:

• Python (FastAPI)
• SQL
• AWS
• System Design

Building projects + documenting everything I learn.

[Andres @AndresBuilds]

@FluentInBizz Right now I’m doing an AI WhatsApp chatbot!

[Andres @AndresBuilds]

600 followers in 30 days. 🚀

No growth hacks.
No buying followers.
No going viral.

Just building in public.

I shared what I was learning, what I was building, what broke, and what I fixed.

The biggest lesson?

People don’t follow perfection.
They follow progress.

If you’re a builder or founder, start posting. Your next opportunity is probably one post away.

Road to 1,000. 🔥

[Andres @AndresBuilds]

🚀 AI helped me build a chatbot in 30 minutes.

Then one prompt broke the entire app.

Fixing it took over a day of debugging, tracing dependencies, and inspecting code.

🤖 AI generates code.
🧠 Engineers understand systems.
AI makes developers faster, but knowing how to fix what breaks is still the real superpower.

[Andres @AndresBuilds]

@buildwithyash @X Let’s connect

[Andres @AndresBuilds]

@ogbuildsapps I think I will do that 🫡

[Andres @AndresBuilds]

The interview process is undefeated.

Friday: “You’ll hear about next steps next week.”

Monday at 8:03 AM: Rejection email.

That was a very short next step.

[Andres @AndresBuilds]

Interesting how the solution wasn’t more models or more complexity.

Just better context and the right tools.

A good reminder that architecture often beats brute force.

[Alex Xu @alexxubyte]

How OpenAI Built Its Data Agent

Most teams building data agents stack routers, fine-tunes, and complex retrieval pipelines on top of multiple LLMs. OpenAI didn't.

Their data agent runs on a single model and only 13 tools, across 1.5 exabytes and 90,000 tables. It's "pretty vanilla" by design.

We spoke with Emma Tang, Head of Data Platform Engineering at OpenAI, to better understand the architecture and the engineering decisions behind it.

The article covers:
- The architecture behind the data agent
- The six layers of context that make a single LLM reliable across 90,000 tables
- How OpenAI Uses Codex Internally: 3 Use Cases
- Five practical lessons for any team building a domain agent
- Where OpenAI's data platform is headed next

[Andres @AndresBuilds]

@vektorastudio Nicee!

[Andres @AndresBuilds]

Quick roll call 👇

Who here is building something in 2026?

Could be:
• An AI agent
• A SaaS
• A mobile app
• An automation
• A side project

I’m always looking to connect with builders and learn from what others are creating.

Drop your project below 🚀

[Andres @AndresBuilds]

@yairszn @X Let’s connect

[Andres @AndresBuilds]

@Gltchdctr Let’s connect

[Andres @AndresBuilds]

@JustJerry121 Not good 🥲.. the webhook works but I think meta is not letting me get the real messages

[Andres @AndresBuilds]

@KathGerp @X Let’s connect

[Andres @AndresBuilds]

Quick question for builders:

Has anyone here built a WhatsApp AI agent using the WhatsApp Cloud API?

I’m trying to get real inbound messages working through webhooks and would love to hear about your setup, lessons learned, or any gotchas you ran into.

What stack did you use?

[Andres @AndresBuilds]

@svpino Thanks

[Andres @AndresBuilds]

@ai_injected Great work!

[Andres @AndresBuilds]

@PitchSparker Nice!

[Andres @AndresBuilds]

@YotamBlu Any time you need someone to test it let me know!

[Andres @AndresBuilds]

@mytwillot Sounds nice!