🤝Hands-On Workshop - Top 5 use cases for automating code review, fixing failed pipelines, and remediating vulnerabilities with agentic AI. Live sessions for EMEA, AMER, and APAC time zones.
The future of software engineering is being written in real time. Join us June 10 for GitLab Transcend - live from London, streaming globally.
See threaded posts for the agenda from the event!
Your AI agent wrote perfect code.
Then it failed security scanning. Got blocked by your pipeline policy. Broke three integration tests. And sat in review for two days.
Agentic AI without platform integration is just faster code that still shouldn’t ship.
GitLab Duo Agent Platform operates inside the system that actually controls deployment. That's the difference.
Personal access tokens often carry far more permission than the job needs. If one leaks, the exposure spans every project that user can reach.
Fine-grained PATs, now in beta, let you scope a token to a specific project and a specific set of permissions. One token per job, nothing more.
Read more: about.gitlab.com/blog/fine-grai…
Your AI agents, your way.
GitLab Duo Agent Platform gives you the flexibility to work with agents built for how your team actually operates. No matter your workflow, there's an agent for it.
docs.gitlab.com/user/duo_agent…
AI coding tools are great at writing code, but shipping it securely is a different problem.
This tutorial shows how Claude Code + GitLab Duo Agent Platform closes the gap, from bug fixes to production, with CI/CD, security scanning, and code review built in.
1️⃣ Fix a bug with Claude Code and let GitLab CI/CD, security scanning, and GitLab Duo Code Review do the rest.
2️⃣ Add GitLab MCP context so Claude works from the context saved within the GitLab issue, and not just local files.
3️⃣ Use a Claude-powered external agent in GitLab Duo Agent Platform to address review feedback directly in the MR.
See how they work together in our blog: about.gitlab.com/blog/claude-co…