Getting unstuck on the AI Agents track. When the agent repeats itself or lacks data, it should stop and ask a specific question. A good question names the missing field. A bad one says 'can you clarify?'
This lesson assumes you already worked through Showing work to the person.
The idea in practice
Detect repeated actions. On the second identical call, switch to asking the user or a person. Record the stuck reason.
A concrete check
goal = {
'track': 'AI Agents',
'lesson': 'Getting unstuck',
}
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
Apologizing and trying the same call again wastes the budget and annoys the user. 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 exact question the agent should ask when order id is missing.
Self-check
- Say Getting unstuck 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.