The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+Run the project's unit tests locally and report failures before the 3pm demo. Execute the test…
Execute — do the immediate task
+Run the project's unit tests locally and report failures before the 3pm demo. Execute the test target in tests/, use the debug build, and stop if more than five tests fail so I can prioritize fixes. Summarize failing test names and first failing assertion for each.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Improve — make it easier to accept
+Before I hand test results to the team, make them actionable: show test failures grouped by failing…
Improve — make it easier to accept
+Before I hand test results to the team, make them actionable: show test failures grouped by failing file, surface the first assertion message up top, and mark tests that are flaky or time-dependent by comparing last three runs. Flag any tests that require network or GPU so reviewers know why they might fail on CI vs a dev laptop.
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Decide — diagnose the stuck moment
+I ran the unit suite on my laptop and everything passed, but CI reports a dozen failures in the…
Decide — diagnose the stuck moment
+Local tests pass but CI shows 12 failing unit tests
I ran the unit suite on my laptop and everything passed, but CI reports a dozen failures in the same module. The build environment differs by OS and uses a mocked time source. I can't reproduce the failures locally and the release is gated by CI. What is the likely mismatch and the fastest way to reproduce the failures locally so I can debug?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Flaky unit tests keep undermining my triage: I spend hours chasing nondeterministic failures that…
Become — change the pattern
+Tests are flaky between local and CI runs
Flaky unit tests keep undermining my triage: I spend hours chasing nondeterministic failures that don't reproduce on my machine, and the team starts ignoring test failures. As the engineer responsible for test reliability, what habit or small process change should I adopt to reduce flakiness and speed root cause identification?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Next to this one
Other programming language work people do in C++.
Every task here came from the work, not from a feature list — which is why the prompts name what you want done and never the button that does it. The tool changes; the work does not.
Copyright © LLOS.ai · 2026 — original pedagogy, voice, and design — all rights reserved.
The rest of the map
Same library, five ways in.