✳flâneur — a map of the web's best reading
Best practices for coding with agents · Cursor
cursor.com · 2,922 words · saved by 1 readers
A comprehensive guide to working with coding agents, from starting with plans to managing context, customizing workflows, and reviewing code.
Blog / product Coding agents are changing how software gets built. Models can now run for hours, complete ambitious multi-file refactors, and iterate until tests pass. But getting the most out of agents requires understanding how they work and developing new patterns. This guide covers techniques for working with Cursor's agent. Whether you're new to agentic coding or looking to learn how our team uses Cursor, we'll cover the best practices for coding with agents. # Understanding agent harnesses An agent harness is built on three components: Instructions : The system prompt and rules that guid
Explore this link on the map →saved by
related reading
- Now – Updates from the Linear teamlinear.app
- Best practices for Claude Code - Claude Code Docsanthropic.com
- Arjun Virkarjunvirk.com
- A Guide to Claude Code 2.0 and getting better at using coding agents – sankalp's blogsankalp.bearblog.dev
- Best practices for using AI coding Agents | Augment Codeaugmentcode.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- How I'm using coding agents in September, 2025 — Massively Parallel Procrastinationblog.fsck.com
- How I Use Claude Code | Philipp Spiessspiess.dev
- Shipping at Inference-Speed | Peter Steinbergersteipete.me
- Cursor: AI coding agentcursor.sh
- Designing agentic loopssimonwillison.net
- Don’t Outsource Your Thinkingteltam.github.io