Cover story
Featured report Security
Apex Field Report
An empirical study of 4,032 machine-generated findings across 612 production web applications and APIs.
Read the featureResource center
Practical intelligence for security teams building, reviewing, and operating critical systems.
Cantina field notes
Cover story
Resource library
30 reports, guides, checklists, playbooks, and webinars. Filter by program area or search by keyword.
No resources match your filters
Try a different program area or clear your search.
Latest research
From Cantina Research
Research
A Fix Is Not a Verdict: How Apex Verifies Security Patches
In a frozen three-month production cohort, Fix Review surfaced 97 issues across 62 of 193 fix pull requests. Here is what those patches missed and how Apex verifies them now.
· Isaac Chin
Research
How We Reduced Incorrect AI Fixes by 58%
With the right fix instructions, the strongest model fixed 90.4% of vulnerabilities correctly.
· Samarth Kumbla
Research
Why Not Just Use Claude or Codex?
A same-codebase comparison of Apex, Claude Code Security, and Codex Security across validated findings, token efficiency, false positives, and operator overhead.
· By Apex Team
Put these playbooks to work
See how Cantina operationalizes this guidance across your codebase, from continuous review to bug bounties and agentic monitoring.