By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.
How I AIThe beginner's guide to coding with Cursor | Lee Robinson (Head of AI education)
Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.
At a glance
WHAT IT’S REALLY ABOUT
Cursor coding guide: agents, linting, rules, and better writing workflows
- Cursor is presented as an AI code editor that blends a traditional IDE with agentic workflows, letting users work from basic autocomplete up to an autonomous agent that can read files, run commands, and apply verified changes.
- Lee explains how adding classic software engineering “guardrails” (TypeScript/typed languages, linters, formatters, and tests) dramatically improves agent reliability because the AI can read failures and correct itself.
- They demo an agent fixing lint errors end-to-end (run lint → identify issues → patch code → rerun lint to verify), then discuss running parallel tasks in the background while you keep coding.
- The conversation also covers power features—@-mentioning Git context, custom rules and reusable commands like “code review,” model selection (Auto vs manual), chat/context management—and ends with a writing workflow that uses a “banned words/phrases” prompt to reduce AI-sounding copy.
IDEAS WORTH REMEMBERING
5 ideasTreat Cursor as a spectrum: autocomplete → agent.
Lee frames Cursor’s UI as progressive autonomy: basic inline suggestions, then higher-autonomy agent actions that can create files and make multi-step changes. This helps beginners start small while giving pros leverage for bigger tasks.
Add engineering guardrails to make agents consistently useful.
Typed languages, linters, formatters, and tests provide machine-readable feedback loops. When an agent causes or encounters failures, it can interpret the errors and correct itself rather than guessing blindly.
Use agents for closed-loop fixes: run → detect → patch → verify.
The lint demo shows the ideal agent pattern: it runs the lint command, applies fixes, and reruns lint to confirm success. This “GPS, not turn-by-turn” approach reduces manual instruction and catches regressions early.
Always inspect diffs to learn and stay in control.
Claire emphasizes opening the red/green diff to understand what changed—especially for beginners. Reviewing diffs teaches code structure, builds trust, and prevents silent mistakes from being merged.
Run parallel agent tasks to keep momentum.
Lee describes keeping focus in the main editor while delegating side tasks (e.g., creating a new route) to the agent panel “in the background.” This turns the agent into a true pair programmer rather than a single-threaded bottleneck.
WORDS WORTH SAVING
5 quotesRather than giving you step-by-step instructions, you're just putting the thing into the GPS, and it just figures it out along the way.
— Lee Robinson
There are tools that you can take from traditional software engineering... and apply them to make your code more resilient to errors and help the AI models fix errors for you.
— Lee Robinson
You can't just vibe code your way forever.
— Lee Robinson
It's a linter and a formatter.
— Claire Vo
When I re-prompt... and I'm not very explicit about what actually wasn't good... the model can't read my mind.
— Lee Robinson
High quality AI-generated summary created from speaker-labeled transcript.
