A/B tests and shadows on the Build Your Own AI Platform track. An A/B test sends a fraction of traffic to a candidate and compares a business metric. A shadow run scores the candidate without showing it.
This lesson assumes you already worked through Rollback.
The idea in practice
Decide the metric and the stop rule before the test. Do not peek every hour and stop when you like the number.
A concrete check
goal = {
'track': 'Build Your Own AI Platform',
'lesson': 'A/B tests and shadows',
}
checks = [
'input available at decision time',
'score matches the real decision',
'failure case written down',
]
print(goal['lesson'])
for item in checks:
print('-', item)
Run the sketch locally if you have Python. The printout is a reminder of the checks, not a trained model. Replace the strings with the real inputs from your own example before you treat it as a design.
What usually goes wrong
Shipping the candidate because a dashboard looked greener for a day. When this happens, stop adding parameters or tools. Fix the check, the data, or the permission, then run the same example again.
What to write down
- The input you are allowed to use at decision time.
- The output and the score or pass rule.
- One failure you will test on purpose.
- What you will not claim the system can do.
Practice
Write the metric and the minimum sample you would require.
Self-check
- Say A/B tests and shadows in one sentence that mentions an input and an output.
- Name the failure mode in this lesson and the check that would catch it.
Done when: you can explain this lesson without the page open, and you have a written failure case.