10 tips to level up your ai-assisted coding
summary
Packed, tool-first playbook that names the exact commands and weaknesses: uses Claude Code and Cursor, demonstrates slash init and cloud.md summaries, shows how subagents create separate ~200k‑token context windows to parallelize work (10 agents running in parallel as an example), and warns about MCP scope while recommending the GitHub CLI over the GitHub MCP. Expect concrete prompts (plan mode, “ultra think”), automation patterns (create GitHub issues, run bash from slash commands), and practical tradeoffs of cost, context limits and rollback.
AI-written summary · about
chapters (17)
- 0:00Introduction and background
- 9:12Pair programming mindset
- 17:28Compound engineering approach
- 19:12Context engineering basics
- 24:32Managing context windows
- 27:43Using framework docs
- 29:51Evolving rules over time
- 32:18Always start with a plan
- 39:15Breaking tasks into steps
- 42:24Choosing the right model
- 45:35Custom slash commands
- 48:02Using subagents effectively
- 50:37Hooks and self-learning
- 53:46Source control with AI
- 55:15MCP tools and security
- 58:50Automating agents with GitHub
- 1:00:15Human in the loop summary
related talks
01h 01m10 tips to level up your ai-assisted coding
01h 03m10 tips to level up your ai-assisted coding
01h 00m10 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
01h 03mAI Coding Agents and how to code them
24mMixing AI Coding in IDEs, CLIs, and Cloud
01h 28mAI Coding Agents and how to code them