How I built an open-source PII firewall and governance policy engine for LLMs — blocks sensitive data before it reaches GPT-4o, with YAML rules, audit trail, and webhook alerts.
Three weeks ago I was benchmarking GPT-4o against a local Llama model. I was copying prompts from a real support ticket database to make the test realistic. Midway through the run I glanced at the terminal and saw this in the logs:
prompt="Hi, my name is Sarah Johnson, my account number is 4532-1234-5678-9012..."
provider=cloud
model=gpt-4o
Enter fullscreen mode
I build a security gateway for LLM traffic. It sits in front of the model as a transparent...
How I designed a self-hosted reverse proxy that scans LLM traffic for PII, secrets, and prompt injection in under 2ms.…
formaai.in Your AI agent just...
The Problem With the rise of ChatGPT and enterprise LLM integrations, a new attack vector...
If you have deployed a large language model in production, even just as a personal coding assistant,...
A few weeks ago I was on a call sharing my screen, walking a teammate through a prompt I'd been...
