Has anyone used one LLM to generate a Gherkin script from a requirement, use another LLM to create code from the generated Gherkin script, and then use Cucumber to check the result?
Of course, you'll need to have someone review the Gherkin script and review the code, but it seems like there's a pipeline you can setup and use for creating some of your code. It'd be interesting to learn what kind of code this wouldn't work for. I'm thinking of this thing as an AI developer of sorts, and like any developer, there are some things they're just not very good at.
Of course, you'll need to have someone review the Gherkin script and review the code, but it seems like there's a pipeline you can setup and use for creating some of your code. It'd be interesting to learn what kind of code this wouldn't work for. I'm thinking of this thing as an AI developer of sorts, and like any developer, there are some things they're just not very good at.