Skip to content
DEV Community

DEV Community

[画像:AgentShield profile picture]

AgentShield

Building AgentShield — prompt injection detection for LLM agents. Fine-tuned transformer classifier, open source, 2ms latency. Previously film production, now making AI agents harder to hijack. Frankf

Location Hessen, Germany Joined Joined on Personal website https://agentshield.pro github website

Work

Founder at Eigenart Filmproduktion / Building AgentShield

Badges

1 Week Community Wellness Streak
Writing Debut

Skills/Languages

Python, TypeScript, PyTorch, FastAPI, LangChain, Docker. Focus on ML security, transformer classifiers, and API design.

Currently learning

Adversarial ML, prompt injection patterns, transformer fine-tuning for security classification. Also exploring eBPF for runtime agent monitoring.

Currently hacking on

AgentShield — open-source prompt injection detection for LLM agents. Fine-tuned DeBERTa classifier, sub-3ms latency, F1 0.921 on public benchmarks.

Available for

Conversations about LLM security, AI agent hardening, and prompt injection defense. Open to integrations and collaborations around agent safety.

Post 9 posts published
Comment 8 comments written
Tag 7 tags followed

Want to connect with AgentShield?

Create an account to connect with AgentShield. You can also sign in below to proceed if you already have an account.

Already have an account? Sign in
loading...
DEV Community

We're a place where coders share, stay up-to-date and grow their careers.

Log in Create account

AltStyle によって変換されたページ (->オリジナル) /