Best Practices
Easy ways to get the most out of Engine
Engine behaves a bit like a remote software engineer. There are a few things to keep in mind as you get used to using Engine.
Setting up Engine’s VM is optional, but it will certainly improve results.
Configuring Engine’s machine is a bit like onboarding a new engineer to your team. It helps Engine understand how to run and check your code.
This helps Engine write code that passes any pre-commit checks and pipeline steps, and ensures Engine’s code does what you expect.
The more tightly scoped the task, the better Engine will perform.
Start with some small issues in your backlog to get some quick results and learn how Engine works.
As you get used to working with Engine and understanding it’s limits, you can start assigning bigger and more complex tickets.
Engine will also start learning more about your codebase and how you like to work as you go.
For now, we recommend that you review Engine’s code before merging it. This not only helps ensure it is correct, but keeps you in the loop on your own codebase.
This step can be faster if you have test suites, lint checks, etc.
It’s easiest to stay on top of Engine’s work by reviewing Engine’s PRs soon after they are made. This avoids code review piling up or PRs becoming outdated as your workflow speeds up.
If a task looks like it has gone off track or code reviews aren’t helping, it’s often best to close the PR and try again, or assign a new task.
Engine’s PRs are disposable (nobody spent any time on it!) and Engine won’t get offended if you decide to close a PR and move on.
The real value of Engine is not that it’s faster than writing code yourself - even if it usually is - but that you can assign a task to Engine and focus on something else.
You can also queue several tasks and review them all at once or assign tasks on the go.
This ansynchronous workflow can help you get the most value from Engine.