Skip to content

ML Blog Post Series

Proposal

The Data Science section is running a 12-week blog post series detailing our efforts around AI/ML.

  • Intention: Rapidly prototype and experiment with various ML features and UI integrations and openly discuss our progress on the GitLab blog weekly. We want to allow anyone at GitLab to rapidly prototype with ML without worrying about the models or dataOps/MLOps needs that come with mature feature development.
  • Goal: Working demoable prototypes within the GitLab codebase to explore UI interactions and live data experimentation that we can share via gifs in blog posts and solicit customer feedback and possibly enable for customers to use with their own data. As we validate use cases and identify features that customers are excited about, we can explore productizing with our own models, models from partners, or allow customers to bring their own OpenAI keys.

View all the live blogs here: https://about.gitlab.com/blog/categories/ai-ml/

Blog Metrics https://app.periscopedata.com/app/gitlab/925951/ModelOps?widget=16581534&udv=0

Blog Schedule

Dates are subject to change, we may shift posts around as needed

#

Date Anticipated Blog Notes
20 2023-07-06

GPU Enabled Runners Overview

@gabrielengel_gl !122250 (merged)

19 2023-06-29

Visual Studio IDE blog

@phikai !126405 (merged)

18 2023-06-22

GitLab Duo

@david

17 2023-06-15
Code Suggestions for SM

@rogerwoo !125914 (merged)

16 2023-06-08

Training and Deploying AI models with Vertex AI: https://youtu.be/p7GTsbSQWF4

@rraquedan

!125512 (merged)

15 2023-06-01 Code Suggestions IDE support blog

@phikai !125272 (merged)

14 2023-05-25

Code Suggestions blog:   How can code suggestions accelerate the developer experience daily.

!125100 (merged)

13

2023-05-18

ML Experiment Overview: Summarize my merge request review
12 2023-05-16

Code Suggestions available to all GitLab tiers while in Beta

11 2023-05-11

Track your Model experiments with Gitlab and MLFlow

@eduardobonet published !123696 (merged)

10 2023-05-04

ML experiment: Answer product how-to questions

@sarahwaldner published !123077 (merged)

9 2023-05-03

AI Fireside chat overview

@tmccaslin published !124002 (merged)

8 2023-05-02

ML Experiment Blog: Explain this vulnerability * Supports this PR about Google AI partnership

@abellucci published !123007 (merged)

7 2023-04-27

ML Experiment: Generate tests in merge requests

@phikai published !123364 (merged)

6 2023-04-20

ML Experiment: Merge Request changes summary

@phikai published !122809 (merged)

5 2023-04-13

ML Experiment: Summarize issue content

@tmccaslin published !122704 (merged)

4 2023-04-06

ML Experiment: Explain this Code

Published !122526 (merged)

3 2023-03-30

ML experiment: Writing SQL is about to get a lot easier

@tmccaslin Published !121877 (merged)

2 2023-03-23

How AI-assisted code suggestions will advance DevSecOps

Published @nkhalwadekar !121876 (merged)

1 2023-03-16

What the ML is up with DevSecOps and AI?

Published @tmccaslin !121474 (merged)

Delayed Content

ML Experiment Overview: CodeReview.GPT

Drafted: !122165 @nick_vh https://gitlab.slack.com/archives/C3MAZRM8W/p1680000922908579


How We Built Suggested Reviewers GA
@mray2020


Designing for ML/AI
@katiemacoy


Code Suggestions Open Beta Blog

@nkhalwadekar


How To use GPU Runners (Self Managed, SaaSI) Draft placeholder:

Pending alignment with PR announcement

How to work with LLMs in GitLab @mray2020

ML Experiment Blog Format

In an effort to standardize the experiment blogs, we'd like to follow a similar format walking through the experiments:

  1. blog series intro and front matter

    ---

    title: "ML experiment: TITLE"

    author: YOUR NAME

    author_gitlab: GITLAB_HANDLE

    author_twitter: TWITTER_HANDLE

    categories: ai-ml

    posttype: product

    tags: DevSecOps, product, features, AI/ML

    description: "Learn how GitLab is experimenting with INSERT TITLE in this latest installment of our ongoing 'AI/ML in DevSecOps' series."

    image_title: /images/blogimages/gitlab-data-science-icon.png

    featured: yes

    twitter_text: "TWITTER TEXT"

    ---

    <i>This blog post is the latest in an ongoing series about GitLab's journey to [build and integrate AI/ML into our DevSecOps platform](/blog/2023/04/24/ai-ml-in-devsecops-series/). Start with the first blog post: [What the ML is up with DevSecOps and AI?](/blog/2023/03/16/what-the-ml-ai/). Throughout the series, we'll feature blogs from our product, engineering, and UX teams to showcase how we're infusing AI/ML into GitLab.</i>

  2. introduce the problem space - focus on customer problem

  3. connect to AI - how will AI help solve this

  4. prototype explanation - introduce the author and the product group of gitlab and explain the prototype

  5. screenshot/video - ideally include an animated gif of the feature, optionally link to a full video. Gifs make it easier to see the feature rather than watching a video.

  6. Next steps - what are we going to do with this? + Join the waitlist + legal disclaimer 

    _This experiment is just the start of the ways we're infusing GitLab with AI/ML capabilities to help GitLab users become more efficient and effective at their jobs. We are looking across the software development lifecycle for painful and time-consuming tasks that are ideal for AI-assisted features. We'll continue to share these demos throughout this blog series._

    Interested in using these AI-generated features? [Join our waitlist](https://forms.gle/9eeUkPJauKsbLaoz5) and share your ideas.

    Continue reading our "[AI/ML in DevSecOps](https://about.gitlab.com/blog/2023/04/24/ai-ml-in-devsecops-series/)" series.

    _Disclaimer: This blog contains information related to upcoming products, features, and functionality. It is important to note that the information in this blog post is for informational purposes only. Please do not rely on this information for purchasing or planning purposes. As with all projects, the items mentioned in this blog and linked pages are subject to change or delay. The development, release, and timing of any products, features, or functionality remain at the sole discretion of GitLab._

Edited by Taylor McCaslin