I'm Erfouni, an AI/ML builder interested in systems that do more than generate text—they retrieve useful context, call tools, automate workflows, validate outcomes, and produce real-world results.
- 🧠 Building with machine learning, RAG, and agentic workflows
- 🔌 Connecting models to tools and knowledge through MCP and REST APIs
- 🐳 Packaging ideas with Python and Docker
- ⚙️ Exploring AI-assisted CAD and SolidWorks automation
- 🧪 Current operating mode: prototype → test → break → learn → ship
Explore all merged contributions ↗
| System | What makes it interesting |
|---|---|
| 🧠 AI knowledge systems | Retrieval pipelines that give models the right context before they answer |
| 🔌 Tool-using agents | MCP and API integrations that let AI take useful, controlled action |
| ⚙️ Engineering automation | Intelligent workflows for CAD, design rules, and technical knowledge |
| 📦 Reproducible services | Python applications packaged to behave the same way outside my laptop |
I build OpenAI Codex plugins and MCP systems that connect AI-assisted SolidWorks workflows to curated engineering knowledge, deterministic validation, and consent-based learning.
design request
└──► retrieve standards + known patterns
└──► reason with constraints
└──► call CAD tools
└──► validate → learn → improve
def build_idea(idea):
while not idea.works:
idea = debug(idea, coffee=True)
return dockerize(idea)
# "Works on my machine" is a bug report, not a deployment strategy.
Waka waka — one contribution at a time.
Always learning. Occasionally debugging the debugger.