dnsmichi

Joined 6 years ago

Karma

313

Submissions

207

Member since

Jan 28

Michael Friedrich is a Staff Developer Advocate at GitLab, focusing on Embedded DevSecOps and responsible AI adoption. “How does a computer work?” led him from Hardware/Software Systems Engineering to DNS, monitoring, and authoring GitLab training. Michael loves to educate and regularly speaks at industry events and meetups. When not traveling, he builds LEGO models and embedded hardware projects.

View on Hacker News

Recent submissions

Comment · 1 year ago

GitLab team member here. Tutorials are available in the docs [1] and this extensive blog tutorial [2]. Specific use cases with help from Agentic AI are discussed in this guide/whitepaper: "CI/CD modernization: Break down barriers with agentic AI" [3]

In my experience learning and leveraging AI and LLMs in the past 2 years, GitLab Duo understands CI/CD configuration very well and can help with migration questions, tasks, and plans, or with actions where Duo Agentic Chat even analyzes and edits files in the IDE.

If you are using GitLab Duo Agent Platform (currently in Beta), there is also a specific Flow that helps convert a Jenkins CI into a GitLab CI/CD configuration. [4] This was released in 18.3, a demo video is inside the release post [5] (demo project here [6]). You can also find the Agentic AI use case in my GitLab DACH Roadshow talk slides [7].

[1] https://docs.gitlab.com/ci/migration/jenkins/

[2] https://about.gitlab.com/blog/jenkins-to-gitlab-migration-ma...

[3] https://about.gitlab.com/the-source/ai/cicd-modernization-br...

[4] https://docs.gitlab.com/user/duo_agent_platform/flows/conver...

[5] https://about.gitlab.com/blog/gitlab-18-3-expanding-ai-orche...

[6] https://gitlab.com/gitlab-da/use-cases/ai/gitlab-duo-agent-p...

[7] https://docs.google.com/presentation/d/e/2PACX-1vTX-DcBV9Rw6...

Comment · 2 years ago

Great idea ;-)

But actually, no. I had these helpful tips in mind, and wanted to share them with everyone quickly. There is always an opportunity to learn together, and get inspired from feedback :-)

Comment · 2 years ago

GitLab team member here. Thanks for your feedback :)

You can follow the migration to Claude 3 in this epic https://gitlab.com/groups/gitlab-org/-/epics/13297

(also shared in this thread https://news.ycombinator.com/item?id=40114647 )

Comment · 2 years ago

GitLab team member here. Thanks for your feedback.

You can follow the migration to Claude 3 in this public epic: https://gitlab.com/groups/gitlab-org/-/epics/13297

Comment · 2 years ago

GitLab team member here. Thanks for your feedback.

GitLab Duo provides AI-assisted features in the DevSecOps lifecycle. GitLab Duo Chat was released as GA last week [0] Code Suggestions are GA, too, and help with code completion and generation [1] The documentation provides more insights on availability and usage [2]

Helpful learning resources:

If you are looking for practical examples and prompt tips for Duo Chat, bookmark this longer tutorial "10 best practices for using AI-powered GitLab Duo Chat" in [3]

We have also updated the documentation to add hands-in GitLab Duo examples for different programming languages and environments, helping with how to integrate AI into your workflows efficiently: [4]

At QCon London 2024 two weeks ago, I spoke about "Efficient DevSecOps workflows with a little help from AI." The slides are publicly available at [5], talk summary in [6]

I also recommend the blog post "How to put generative AI to work in your DevSecOps environment" [7] to tackle important questions such as workflow assessments, AI guardrails and how to measure AI impact in your organization.

Last but not least, I started a learning series called "GitLab Duo Coffee Chat" on YouTube [8], showing AI and GitLab Duo in action. I plan to host more sessions in the coming weeks. [9]

Happy to help with more adoption questions, best practices, and development workflows :-)