Resources

Guides for teams shipping
secure software with AI

Field notes from our engineers — what actually works in a pipeline, written for the people who have to implement it.

Illustration of a security research library with glowing guides and a padlock

Browse by topic

Free download

Securing AI & LLM applications: the engineering checklist

A 24-point checklist covering prompt injection, data leakage, model supply chain, output handling and monitoring — mapped to the OWASP Top 10 for LLM Applications.

24 checks grouped across build, test, deploy and monitor
Mapped to OWASP LLM Top 10 categories
Owner and evidence columns for audit trails
Free — no credit card, no sales call required
Get the checklist →

Latest guides

No gated fluff — every guide is readable in full, right here.

AI SAST8 min read

AI SAST explained: how AI static analysis cuts false positives

What AI SAST actually changes compared with rule-based static analysis, where the accuracy gains come from, and how to roll it out in a CI pipeline without slowing developers down.

18 Jun 2026Read →
AI security10 min read

OWASP LLM Top 10: a practical checklist for engineering teams

A working engineer’s pass through the OWASP Top 10 for LLM Applications — what each risk looks like in a real product, and the concrete control you can ship this sprint.

2 Jul 2026Read →
Secret detection7 min read

Secrets in git history: finding, rotating and preventing leaks

Why deleting a leaked credential in a new commit does nothing, how to scan full git history safely, and the rotation-first response order that limits damage.

24 Jul 2026Read →
AI SAST9 min read

SAST vs DAST: what each one catches, and how to run both

A practical comparison of static and dynamic application security testing — what each method can and cannot see, where they overlap, and how to sequence both in one pipeline.

30 Jul 2026Read →
AI security9 min read

Prompt injection testing: building an adversarial suite for CI

How to test LLM features for prompt injection automatically — payload corpus design, what to assert, and how to wire the suite into CI so a prompt edit cannot silently remove a control.

4 Aug 2026Read →