How AI-assisted engineering works today
Unmanaged laptops, shared tokens, direct repo access, and AI tools that act before security sees them.
AI Engineering Safety Lab
Govern AI on your repos in 60 minutes.
A live workshop for engineering, platform, and security leads rolling out Cursor, Claude Code, or MCP-connected coding agents across internal and external teams.
Workshop offer
- 60-minute live session over Zoom or Loom.
- Cursor / Claude / VS Code workflow examples.
- Prompt-injection and supply-chain scenarios.
- Guided 30-day pilot offer at the end.
Agenda
Two attacks to model
Prompt injection in code comments and supply-chain package drift that traditional CI checks catch too late.
Runtime governance pattern
Browser isolation, device-bound identity, scoped GitHub credentials, MCP policy, and signed audit chains.
Live governed-agent demo
An external developer or employee asks Claude for a risky action. The gateway denies it and links prompt, MCP call, repo, and policy.
Pilot plan
Leave with a 30-day pilot checklist: one repo, one governed agent workflow, one evidence export.
What attendees learn
How AI coding agents bypass CI/CD and secrets scanners, where an MCP gateway fits, and how to produce a complete prompt-to-infra audit chain for security review.
Success metrics
RegistrationsShow-up ratePilot bookingsTime to first blocked action
The follow-up is a 30-day guided pilot.
One governed workflow, one repo, one MCP policy set, one audit export. The goal is a blocked action and evidence pack in the first week.
Book the pilot call