Logging prompts and predictions on the Build Your Own AI Platform track. You need some logs to debug. You do not need to keep every prompt forever. Decide retention, access, and redaction before launch.
This lesson assumes you already worked through Observability.
The idea in practice
Redact secrets and payment data. Restrict who can read raw prompts. Sample if volume is huge.
A concrete check
goal = {
'track': 'Build Your Own AI Platform',
'lesson': 'Logging prompts and predictions',
}
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
A world-readable log of medical text. 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 retention and who may open a raw prompt.
Self-check
- Say Logging prompts and predictions 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.