A gateway in front of models on the Build Your Own AI Platform track. A gateway authenticates, rate-limits, routes to a version, and records latency. Callers do not get raw trainer credentials.
This lesson assumes you already worked through Config separate from weights.
The idea in practice
Route by model name and stage. Support a shadow route that scores a candidate without returning it to the user.
A concrete check
goal = {
'track': 'Build Your Own AI Platform',
'lesson': 'A gateway in front of models',
}
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
Apps embedding a provider key and calling around your logs. 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
Draw client, gateway, and model. Mark where the request is logged.
Self-check
- Say A gateway in front of models 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.