The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+I need to make sure uncaught promise rejections in the signup flow surface to Sentry and don’t…
Execute — do the immediate task
+I need to make sure uncaught promise rejections in the signup flow surface to Sentry and don’t leave the UI stuck. Wrap the async functions that run when the user clicks Create Account so the submit button is re-enabled and an error banner appears, then forward the error to Sentry, and do this before the end of today.
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 ship, make it obvious to a reviewer how an async failure behaves: show the user-facing…
Improve — make it easier to accept
+Before I ship, make it obvious to a reviewer how an async failure behaves: show the user-facing error message first, then the retry button, and below that the telemetry call to Sentry. Highlight any places where the UI might remain blocked or state left inconsistent.
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
+The Create Account button was clicked, the spinner started, and an uncaught rejection hit in the…
Decide — diagnose the stuck moment
+A promise rejection happened during form submit and the spinner never stopped
The Create Account button was clicked, the spinner started, and an uncaught rejection hit in the network code; now the spinner never stops and I can’t find the error in Sentry. I’m worried the button state and local store are inconsistent and I’m missing where the rejection is thrown. What’s the likely root cause and the least risky next fix to restore user experience and capture the error?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Across several releases we keep getting one-off crashes tied to different async handlers: WebSocket…
Become — change the pattern
+Occasional production crashes from uncaught async errors
Across several releases we keep getting one-off crashes tied to different async handlers: WebSocket reconnects, file uploads, and form submits. I spend time reproducing, patching, and then another slips through. What habit and guardrail should I adopt to stop these leaks, and how do I add a simple checklist so every async entry point has consistent error capture and state rollback?
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 JavaScript.
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.