Automating Test Generation with Gemini 1.5 Pro & GitHub Actions

I’ve spent the last couple years exploring ways that AI can be used to automate parts of the software development process. In this video, you’ll see a demo of me taking a JIRA user story and automatically generating Cucumber tests and a basic implementation plan combining GitHub Actions with Gemini 1.5 Pro

What It Does

1. You fill in a JIRA story with the required information and acceptance criteria and set it to “Ready”

2. A GitHub Action that you set up pulls the latest story that’s “Ready” and generates a PR that contains Cucumber BDD tests that use the acceptance criteria as a guide

3. You review the generated Cucumber tests, make any edits that are needed, and merge the PR

4. Merging the Cucumber PR kicks off another job that generates a full implementation plan based on the story and the tests

Why It Matters

With just a few lines of code, we were able to create an AI pipeline that hints at the ability to drastically speed up development time and generate artifacts to be used in other parts of other pipelines. There’s already best practices forming around using Cursor’s agentic flows that include a step of having it generate an implementation plan. Why not automate that as well?

How To Get It

All the code for this is available at sublayerapp/crm on GitHub. The particularly interesting parts where we’re using AI are under the .github/workflows directory. To use it you’ll also need to set up a few API keys and environment variables. If you’re looking for help you can pop in to the Sublayer Discord and I should be around to guide you through it.