mattijs moens' profile on Product Hunt

About

AI security researcher and full-stack engineer. I build deterministic, fail-closed defenses for LLM and agent systems at SovereignShield, and I ship products that apply the same discipline. Draft & Check, my email verification API, is one of them: honest verification that returns "unknown" instead of a false "deliverable." Verify, don't trust.

Links

Draft and Check

SovereignShield

Badges

Tastemaker

Gone streaking

Maker History

Draft & CheckHonest email verification with real SMTP checks
Sep 2026
SovereignShieldImmutable deterministic security architecture for AI systems
Apr 2026

🎉

Joined Product HuntMarch 26th, 2026

Forums

•

2mo ago

Draft & Check - Honest email verification with real SMTP checks

Clean your lists before you send. Draft & Check does a real SMTP mailbox check on every address, with catch-all and disposable detection and typo rescue, then returns a clear verdict and a 0 to 100 score. When it cannot confirm a mailbox it says "unknown" instead of a false "deliverable." Pay-as-you-go, credits never expire, and about 3 to 4x cheaper than ZeroBounce. Upload a CSV or use the API.

p/sovereignshield

•

7mo ago

How is everyone handling prompt injection in autonomous agents right now?

Hi everyone! I'm Mattijs, and I'm launching SovereignShield tomorrow (a 7-layer deterministic defense suite for AI systems).

I built it because having LLMs grade other LLMs for safety feels like risk laundering to me, especially when you are giving agents access to APIs and databases.

•

7mo ago

SovereignShield - Immutable deterministic security architecture for AI systems

LLM agents get jailbroken. SovereignShield is a 7-layer defense suite protecting autonomous AI from prompt injection, malicious tool execution, and hallucinations. It combines OS-level hardware memory protection, deterministic keyword filtering, a self-learning adaptive engine, mathematical truth guards. Enforce aerospace-grade deterministic safety for your AI in production. (BSL 1.1)