Practical guides for getting effective results with Claude Code, Cursor, Windsurf, and other agentic AI coding tools.
Based on analysis of 1,352 real development messages to identify what communication patterns lead to productive collaboration.
- Agentic AI Workflow Guide - The main practical guide with step-by-step approach and comprehensive FAQ
- Communication Guide - Deep dive into the 8 communication patterns and session dynamics
- Quick Reference - One-page cheat sheet
The skills/ folder contains reusable skill definitions for Claude Code:
- linked-intent-dev - Linked-intent development (LID) — structured workflow for design-before-code: HLD → LLD → EARS specs → Implementation plan
The shift from Copilot to agentic AI:
- Copilot: You write code, AI suggests completions
- Agentic AI: AI writes code, you steer and validate
What makes sessions effective:
- Be detailed - "I see X when I expected Y" not "it's broken"
- Close the loop - Report results back, even just "yup"
- Steer constantly - "Great. Now let's..." every few exchanges
- Validate assumptions - "What did you understand?" after work is done
The real anti-pattern isn't "too many turns" - it's frustrated circling. Exploration with back-and-forth is fine. Repeating "try again" without new information is the problem.
The analysis_data_index.md file describes the raw data files used in this analysis, with query examples.
MIT - See LICENSE