An evaluation service on the Build Your Own AI Platform track. Evaluation runs a fixed suite against a candidate version and stores the report. Promotion can require the report to pass thresholds.
This lesson assumes you already worked through Experiment tracking in the platform.
The idea in practice
Include slices and a refusal or safety set if the model can act. Block promotion on a failed gate.
A concrete check
goal = {
'track': 'Build Your Own AI Platform',
'lesson': 'An evaluation service',
}
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
Optional eval that everyone skips when they are in a hurry. 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
Name two gates that block promotion.
Self-check
- Say An evaluation service 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.