Practical GenAI · Part 2
Build research code
you can explain.
Work through a small project with a coding agent, learn how to check its work, and leave the next person a project they can pick up.
Pick up where Part 1 leaves off
Part 1: Practical GenAI Coding Guide takes us through planning, prompting, reviewing, and documenting code, including work with coding agents. Here we put those habits to work in a project with several moving parts: a Python package, tests, documentation, and saved results.
We use one small example throughout, so you can follow a change from the original request to the files you would share with a collaborator. Along the way, you will give the agent useful context, catch plausible mistakes, and decide when the result is ready to keep.
If you are new to using GenAI for coding, begin with Part 1. If you can already run a script and inspect a change, start here.
A practical learning path
From the first run to a reviewed change
Keep the project small so you can see the whole workflow.
Establish a working baseline
Install the demo, run the tests, and inspect a completed run before asking an agent to edit anything.
Run the quickstartMake the repository understandable
Use a README, agent instructions, a repository map, and data contracts to make expectations explicit.
Explore repository practicesChoose one small improvement
Describe the change and how you will check it. Review its plan and the files it changes.
Work through the lessonsLeave a useful result
Run the checks, inspect the outputs, and leave enough detail for a labmate to rerun the work.
Read the pipeline reference
Reuse the templates
Write a task brief, agree on the data, or hand off unfinished work.
Browse templates