Topics / Building software

How does AI help keep a product secure?

AI used to find vulnerabilities, review security, and the risks agents add.

6 passages from 4 organizations; 5 checked against the source. The page states no conclusion: these are the organizations' own words.

Over roughly six weeks, we’ve run thousands of scans, produced over 300 findings ranging from defense-in-depth improvements to resolved security incidents.

Zack DeveauTitle not stated on Deveau's author page; the post is written from Shopify's Application Security team · Practitioner, Shopify

Post: Building an agentic harness that outlasts the model, Shopify engineering blog, July 29, 2026.

  • 300 function agent volume, about six weeks, as of 2026-07-29. Level not stated

Checked against the source [ Grade B ] Said in the last year Shopify: $11.6 billion revenue, FY2025 Passage page

we have a security agent that processes over 7 billion tokens per day on Kimi. That would cost an estimated $2.4M per year on a mid-tier proprietary model. But on Workers AI, it’s 77% cheaper.

CloudflarePublished by the organization itself (post), no named author

Context. Cloudflare sells Workers AI, the product it describes running this agent on.

Post: The AI engineering stack we built internally, on the platform we ship, Cloudflare blog, April 20, 2026, at Act 1, "How we increasingly leverage Workers AI".

  • 7 billion tokens per day, per day, security agent on Kimi K2.5
  • 77% cost saving, versus an estimated $2.4M per year on a mid-tier proprietary model

Not yet checked [ Grade B ] Said in the last year Cloudflare: $2.2 billion revenue, FY2025 Sells AI tools Passage page

JSON: /api/v1/topics/security.json