AI/TLDR

Anthropic · 2026-07-06 · notable

Alberta government cybersecurity — Claude Code scans 466M lines in 20 hours

Alberta's Ministry of Technology and Innovation scanned 466 million lines of provincial-government code with Claude Code in 20 hours, using ~50 parallel agents to check ~95 security controls across 1,280 apps and 3,400 repositories.

Anthropic Alberta cybersecurity case study social card

Alberta scanned every line of provincial-government code with Claude Code — in less than a day.

Key specs

Lines scanned466M
Agents50
Hours to first pass20

What is it?

The Government of Alberta used Claude Code, driven by Claude Opus and Claude Sonnet, to systematically review every application it maintains for cybersecurity flaws. The rollout covered about 1,280 provincial-government applications and 3,400 code repositories.

How does it work?

Around 50 autonomous Claude Code agents ran in parallel, each checking roughly 95 security controls per application against Alberta's own security policy. The first pass across 466 million lines finished in about 20 hours, and the same pipeline now runs continuously so new code is reviewed against the same controls whenever it lands.

Why does it matter?

Alberta estimates a traditional manual review of that codebase would have taken about 6.5 years — so 20 hours of agent runtime replaces roughly 6 person-years of hand review. The province plans to expand the approach across the wider Alberta government this fall and will share its playbook with other governments at an industry day in July.

Who is it for?

government CIOs, enterprise security teams

Try it

https://docs.claude.com/en/docs/claude-code/overview

Sources · 3 outlets

Tags

  • claude-code
  • case-study
  • government
  • cybersecurity
  • enterprise
  • canada
  • anthropic
  • agentic-coding

← All releases · Learn AI