score --dx --ax --prod --pricing --perf
Scorecard
How to read these scores
86+ is excellent, 74-85 is solid, and anything below 74 needs active scrutiny before a team or agent depends on it.
cat ./evidence/cursor.md
What Neurl built with it
Refactored a multi-page Astro resource surface and used repo-wide context for component and CSS edits.
Large repo refactor with existing style conventions, accessibility constraints, and production build verification.
- Installed in an existing codebase
- Edited multi-file UI slices
- Checked diff quality
- Ran build and browser verification
- Scores reflect Neurl hands-on evidence and should be re-verified before procurement or high-risk production adoption.
- Pricing, limits, model defaults, and product policies can change quickly; use freshness dates and vendor docs before final rollout.
when-to-use cursor
Use it when
- Large repo refactor
- Prototype to demo
- Agent tool use
- repo-aware feature work
- large refactors
- developer onboarding
avoid-if cursor
Not a fit when
- strictly terminal-only workflows
- teams that cannot allow editor telemetry
- non-code research tasks
pricing --teardown
Pricing teardown
Easy to justify for engineers who use AI assistance daily; team cost rises quickly if every collaborator needs a seat.
- Review model usage and privacy settings before rollout
- Occasional premium-model limits affect heavy sessions
prod --readiness
Production notes
Production-ready as a developer workflow tool, but output still needs normal review, tests, and senior judgment.
- Can overfit to local patterns
- Needs disciplined verification on generated edits
ls ./use-cases/cursor
Best use cases
Feature implementation
Best when the engineer can keep tight review loops inside the editor.
Repo onboarding
Useful for summarizing conventions before the first patch.