This is a submission for the Gemma 4 Challenge: Build with Gemma 4 Every time you paste sensitive...
PromptGuard intercepts and redacts PII from prompts on-device using Gemma 4 e4b (MoE/Ollama) before they reach ChatGPT or Claude. For GDPR-bound teams, it offers a practical local-LLM-as-filter pattern that decouples AI productivity from data sovereignty risk.
This is a submission for the Gemma 4 Challenge: Build with Gemma 4
Every time you paste sensitive data, legal documents, or personal details into ChatGPT or Claude, that data leaves your device. PromptGuard intercepts it first — and Gemma 4 running locally does the redaction before the prompt ever touches a cloud server.
Table of Contents
The Problem Nobody Talks About
What I Built
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 🎬 The Problem Nobody...
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built Every few...
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built After...
This is a submission for the Gemma 4 Challenge: Write About Gemma 4 Every AI app says it respects...
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I Built I built...
This is a submission for the Gemma 4 Challenge: Build with Gemma 4 What I...
