10 tips to level up your ai-assisted coding
summary
Rapid-fire checklist of actionable techniques: use sub agents with separate context to parallelize work (he demos splitting 100 PDFs into concurrent agents), keep active rule files like slashinit to generate project rule file (Claude MD / agents MD) and update them after every failure, prefer plan mode + “ultra think” before changing code, exploit MCPs for GitHub/Chrome DevTools but watch context bloat, use checkpoints/forks to rewind, and pick fast or heavy models (Composer vs Opus 4.5/Gemini 3) by cost and latency.
AI-written summary · about
chapters (17)
- 0:00AI-assisted coding evolution
- 3:58Why AI coding assistants now
- 7:09AI as junior developer
- 16:25Context in AI coding
- 26:23Rule files and context
- 32:59Planning with AI
- 39:45Breaking tasks down
- 41:30Right AI models
- 43:41Automate with slash commands
- 46:09Sub agents for parallel work
- 47:38Hooks to guide AI
- 50:27Skills and autonomous tasks
- 52:13Source control strategies
- 55:34Improve AI responses
- 55:56MCP servers integration
- 1:00:19Releasing agents safely
- 1:01:44Human in the loop
related talks
01h 01m10 tips to level up your ai-assisted coding
01h 00m10 tips to level up your ai-assisted coding
01h 01m10 tips to level up your ai-assisted coding
01h 02m10 Tips To Level Up Your AI-Assisted Coding
30mBeyond the Hype: Using AI Coding Agents Today
33mYou are the main thread: Multiplying your productivity with agents
27mAgentic Engineering: Working With AI, Not Just Using It
27mAgentic Coding with Discipline & Skill: Practical Techniques and Tips