Skip to content
View debugbae's full-sized avatar
  • USA

Block or report debugbae

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 is supported. This note will only be visible to you.
Report abuse

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

Report abuse
debugbae/README.md

Hi, I'm Romina 👋

AI Builder & Solutions Engineer — I turn local LLMs and enterprise workflows into tools people actually use.

I'm a Solutions Engineer and AI Builder who ships working AI tools, not just prompts in a notebook. My focus is local-first LLM tooling (Ollama, no-API-key workflows) and enterprise SE/support automation — the kind of thing that saves a team real hours, not just a demo-day applause line.


🧰 Tech Stack

Python TypeScript PowerShell Ollama Astro Streamlit SharePoint HTML5


🚀 Featured Projects

se-enabler AI-powered customer conversation simulator for cybersecurity SE training.

HTML AI

fit-gpt AI nutrition assistant that scans meal/fridge photos, tracks macros, and suggests recipes from what's actually in your kitchen.

TypeScript Vision

eli5-anything Local AI tool that explains any concept at 4 reading levels (ELI5 → expert) — runs fully offline via Ollama, no API key required.

Python Ollama

support-case-summarizer CLI that turns raw support tickets into structured summaries with severity triage, impact assessment, and next actions.

Python CLI

🔭 Currently Building & Exploring

  • OpenClaw — digging into custom agent integrations and where local-first tooling can replace API-dependent workflows.
  • Local LLMs (Ollama) — building a small library of offline, no-API-key tools (eli5-anything, support-case-summarizer) as a bet that "runs on your laptop" beats "runs on someone else's API key" for a lot of enterprise use cases.
  • Prompt governance for enterprise AI — templates and guardrails for teams rolling out LLMs responsibly (see support-ai-prompt-library).

📌 Pinned Highlights

Project What it shows
se-enabler Domain expertise — AI applied directly to my own SE discipline
fit-gpt Full-stack product build (vision + TypeScript)
eli5-anything Local-first AI engineering, zero API dependency
support-case-summarizer Enterprise workflow automation with AI
support-ai-prompt-library Responsible AI / governance thinking at scale
open-prompts Open-source contribution, public-domain prompt library

📊 GitHub Stats

Romina's GitHub stats Top languages


🔗 Connect

I'm always happy to talk AI tooling, support ops, or prompt engineering strategy. Currently exploring roles at the intersection of AI program management and hands-on development — where strategy meets shipping.

Pinned Loading

  1. fit-gpt fit-gpt Public

    AI-powered nutrition assistant that scans meal and fridge photos, tracks macros, and suggests recipes from what's in your kitchen.

    TypeScript 1

  2. se-enabler se-enabler Public

    AI-powered customer conversation simulator for cybersecurity SE training

    HTML 1

  3. support-ai-prompt-library support-ai-prompt-library Public

    Production-ready AI prompt templates for support, services, and customer ops teams. Includes governance templates for responsible enterprise AI deployment.

    1

  4. support-case-summarizer support-case-summarizer Public

    AI-powered CLI that transforms raw support tickets into structured summaries with severity triage, impact assessment, and next actions. Runs locally with Ollama.

    Python 1

  5. eli5-anything eli5-anything Public

    Local AI tool that explains any concept at 4 reading levels, ELI5 to expert, using Ollama. No API key needed.

    Python

  6. open-prompts open-prompts Public

    Public-domain library of prompts for Claude and other LLMs.

    Astro