Field-test AI on your phone: bad signal and interruptions
https://patrickz.ai/learn/test-ai-in-real-conditions/

OUTCOME
Try one AI task on your phone the way people really use it (distracted, on a bad connection, interrupted) and write three recovery rules.

YOU NEED
Your phone with any chat assistant app (or the AI tool you are building) and a notes app. No prototype needed. Use the invented to-do items below, not private information.

1. Pick one real task
Type or dictate: “Turn this into a three-item to-do list: call the plumber, buy milk, send Sam the slides.” Do it once with a good connection and full attention. Note what a finished answer looks like.

2. Break the connection
Turn on airplane mode and send the same request. Write down exactly what the screen shows and whether your text is still there. Reconnect and see whether you can retry without retyping. Then ask for something longer, such as a 300-word packing list, and switch airplane mode on while it is still writing. Is it clear the answer is incomplete?

3. Interrupt yourself
Start again, switch to another app for a minute, then come back. Repeat the task one-handed while standing. Note anything you had to retype, any double send, and anything that looked finished but was not.

4. Write recovery rules
For each problem, write what the person should see, the safe next step and what must be kept so they can resume. Paste your notes into the prompt below, then ask someone who did not watch you to repeat the three tests.

PROMPT
Here are my field-test notes for [task] in [app or tool] on [device]: [what happened offline, when cut off mid-answer, and when interrupted]. For each problem, write one recovery rule: the message the person should see, the safe next step, and what must be kept so they can resume. Then suggest one realistic condition I did not test and how to test it. Do not assume a reliable network or full attention.

EXAMPLE / EXPERIMENT
If the answer stops when the signal drops, a good app says something like “Not finished, tap to retry” and keeps your request. A half answer that looks complete, or a request you must retype, is exactly what this test should catch. If you are building your own tool, the same rule applies to uploads: pending should look pending, not like a checkmark.

CHECK YOUR RESULT
[ ] Pending, finished and failed answers look different on screen.
[ ] A dropped signal or interruption never silently discards what you typed.
[ ] Someone who did not watch you can repeat a test and recover using only what the screen shows.

IF IT FAILS
If nothing ever goes wrong, repeat the tests where the signal is weak, such as an elevator or parking garage, or ask for a much longer answer so there is time to interrupt it. If you are testing your own tool on a laptop, throttle the connection in the browser developer tools. Record simulated conditions honestly rather than claiming a field trial.

MY RESULT / NEXT CHANGE