Surgical Cursor fixes after Claude Code draft
Drew switches to Cursor with tight prompts when Claude Code stalls on odd codebase patterns, then returns to Claude Code for polish and Playwright tests.
- Agent or tool
- Cursor
- Topic
- Software Development
- Reported on
- Blog
- Added
- 2026-10-15
Why it matters
Coding agents are moving from autocomplete to doing whole tasks: reading a codebase, making a plan and changing many files. This case is a concrete example of where that works in practice. It is one of 106 sightings filed under Software Development on Agent Sightings (number 47 by interest), and one of 30 involving Cursor.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into Cursor or any similar agent and adjust the details to your situation.
Fix only this function. Here are the API docs for the return values. Do not refactor callers. Show the diff and how to verify.
The prompt breaks down into 4 steps you can check as the agent works:
- Fix only this function.
- Here are the API docs for the return values.
- Do not refactor callers.
- Show the diff and how to verify.
Tip: Work on a fresh branch, ask for a plan before edits, and review the diff and test results before merging.
Source
Read the original first-hand account on Blog: https://drew.tech/posts/my-ai-coding-workflow. Our summary is a paraphrase; details are in the source.
Featured in these guides
Related sightings
- Prototype product features as a non-coding PM
- Keep coding agents running autonomously for long stretches
- Ship an iOS app in 17 days with agents
- Fix app bugs, harden security and ship fixes autonomously
- Two-hour Slack dashboard from meeting dumps
- Run a scheduled personal assistant that builds a task dashboard