The four heights
The same task, four distances: today's deadline, the next reviewer, the stuck moment, the pattern.
Execute — do the immediate task
+We need a reproducible production build today. Configure the bundler so it produces a single…
Execute — do the immediate task
+We need a reproducible production build today. Configure the bundler so it produces a single production bundle per entry with deterministic filenames, includes hashed assets for caching, generates source maps, performs tree shaking, and fails the build on unresolved imports. Document the exact build command our CI will run and the output paths for deployment.
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 the bundler config to operations, make it easier for a reviewer to validate. Show…
Improve — make it easier to accept
+Before I hand the bundler config to operations, make it easier for a reviewer to validate. Show where vendor code is split from app code, surface the largest modules and why they aren’t tree-shaken, list the file name patterns and cache headers we should use, and point out any long-running plugins that slow CI.
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
+My local production bundle is 1.2 MB but CI produces a 2.8 MB bundle with identical source.…
Decide — diagnose the stuck moment
+CI artifacts differ from my local build
My local production bundle is 1.2 MB but CI produces a 2.8 MB bundle with identical source. Deployments started failing because cache headers changed. I suspect a missing plugin or different node resolution in CI. I don’t know what exact config divergence to look for. What are the most likely causes and the precise checks to run to pinpoint the difference quickly?
Pasted it? When the reply comes back, push once: ask it to sharpen the weakest part. — Did this prompt help?
Become — change the pattern
+Every project lands its own slightly different bundler config and we lose time debugging subtle…
Become — change the pattern
+Config drifts across projects and teams
Every project lands its own slightly different bundler config and we lose time debugging subtle differences across teams. Builds behave differently in staging and prod and on developers’ machines. What consolidation or habits should we adopt so configs are consistent, easy to audit, and faster to update across repositories?
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.