Skip to content
View santos-sanz's full-sized avatar
🎯
Focusing
🎯
Focusing
11 followers · 48 following

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLO

Highlights

  • Pro

Block or report santos-sanz

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
santos-sanz/README.md

Profile Views LinkedIn Gmail Location

Data & Growth professional by day | AI-assisted builder by hobby

I use AI-assisted development to prototype ideas, learn faster, and stay current with new tech.

About Me

I do not see myself as someone who has mastered every language in this README.

I build mainly as a hobby, and I use AI-assisted development as a practical way to:

  • explore new technologies quickly,
  • turn ideas into small working prototypes,
  • and keep learning in public while staying up to date.

Most of what I build here are learning projects, experiments, and tools that help me think better about product, data, and automation.

Professional Context

  • Current role: Data & Growth @ Revolut.
  • Background: experience across Revolut, Amazon, and Zennio.
  • Common ground with this repo: data thinking, process improvement, and hands-on problem solving.

Tech Stack

These are tools I use in practice and keep exploring through projects.

Tools I use often

Python SQL JavaScript TypeScript Pandas NumPy Google Cloud Git Docker Streamlit

Also used in analytics workflows: Looker, BigQuery, Airflow, GA4, Google Sheets, Excel/VBA.

Tools I explore in projects

PyTorch Hugging Face LangChain MLX OpenAI Swift iOS React Node.js Next.js N8N macOS Scikit Learn

Current Projects

Project Type Description
AI Agents Experiment AI-assisted prototypes for agent workflows and LLM tooling.
iOS Apps Learning project Small native app ideas to improve Swift and product thinking.
Automation Prototype Practical automations to simplify repetitive workflows.
Fintech/Data Learning build Analytics-focused side projects to test product and growth ideas.

What I'm Learning by Building

AI_assisted_development:
  - prompt-driven prototyping
  - practical LLM integrations
  - iteration speed with human review

Data_and_growth_thinking:
  - SQL/Python analysis workflows
  - experiment mindset (funnels, cohorts, segmentation)
  - decision support for product ideas

Product_and_automation:
  - turning ideas into small useful tools
  - workflow simplification with scripts and automations
  - balancing speed, clarity, and maintainability

Learning Highlights

Focus Current direction
AI-assisted development Building and iterating prototypes
Data + product mindset Applying analytics to practical ideas
iOS and automation Learning through side projects
Continuous learning Exploring new tools and workflows

Let's Connect

LinkedIn Email GitHub


Open to conversations about AI-assisted workflows, analytics, and side projects.

Build, learn, iterate, repeat.

Open Source AI Assisted

Pinned Loading

  1. dataclaw dataclaw Public

    Query agent for Kaggle datasets with SQL execution on DuckDB and Python fallback when needed.

    TypeScript

  2. mlx-lora-finetune-template mlx-lora-finetune-template Public

    Template for fine-tuning LLMs with LoRA using Apple MLX on Mac Silicon

    Python 9 1

  3. LLM_Vending_Machine LLM_Vending_Machine Public

    LangGraph-powered simulation where LLMs act as economic agents competing in a vending machine market. Benchmarking AI decision-making in dynamic pricing scenarios.

    Python

  4. doom-slayer doom-slayer Public

    AI-powered focus assistant using MediaPipe and TensorFlow.js to detect distraction (phone use, looking away) and keep you productive. 100% local, no backend.

    JavaScript 1