10 tips to level up your ai-assisted coding
summary
Covers concrete tactics for making AI actually write, test and improve code: uses Claude Code, Cursor, Opus and MCPs, shows 1 million token windows and warns quality drops past ~70–80% fill, demos building skills, hooks and sub‑agents that run, test and fix code autonomously, and an agentation overlay that captures DOM feedback. Promotes compound engineering—have agents learn from mistakes and checkpoint learnings into files or Git. Good if you want hands‑on tricks and tool names to try tonight.
AI-written summary · about
chapters (12)
- 0:00AI-assisted coding intro
- 4:06Mindset for AI collaboration
- 9:27Context management
- 15:55Rules and compound engineering
- 21:59Skills and slash commands
- 24:45Plan before coding
- 31:52Human bottlenecks in AI workflows
- 36:29Tools for AI agent verification
- 41:52Best model for quality
- 47:47Reflecting on AI learnings
- 54:39Release agents and parallelize
- 1:01:14Q&A
related talks
01h 02m10 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 03m10 tips to level up your ai-assisted coding
30mBeyond the Hype: Using AI Coding Agents Today
25mFrom AI Chaos to Production Ready: Using AI Agents to Improve Your Code Quality
49mFrom autocomplete to agents: AI coding assistance state of play
26mI’m Not Writing Code Anymore—Now What? | The 7-Step Workflow