Avthar
@avthar • 7,870 subscribers
CEO @ Alpha Clarity | https://t.co/lT9Bzde4SX Prev: Staff PM @mongodb, GM for AI @timescaledb, @Princeton
Videos
I use subagents for ~80% of my Codex tasks these days. If you're new to subagents, here's a quick primer: - Subagents = separate agents that work on a specific piece of work in a fresh isolated context window. - Your main thread can create subagents and delegate work to them. - Subagents report back when tasks are complete. - Codex subagents are especially useful for read-heavy tasks (e.g research, investigation, and review). - Also useful for testing and building parts of a project in parallel. Subagents are great for working on focused parts of a big task, like planning, implementation, testing, or review. My biggest pro tip for using subagents in Codex: You don’t have to design the entire delegation plan yourself. Just ask Codex to “Use subagents as needed,” and then Codex can then decide where subagents would help it in the task. Here's a demo of using subagents in Codex:
Avthar18,404 次观看 • 9 天前
💥NEW AI CODING TUTORIAL: 12 Months of Claude Code Lessons in 46 Minutes Claude Code just turned 1. So here's 52 lessons on how to get the most out of Claude Code, organized into 3 levels: Beginner, Intermediate, and Master. TIMESTAMPS 00:00 12 Months of building with Claude Code 02:01 LEVEL 1: Beginner 02:09 Installation and Setup 04:55 Models and Modes 09:04 CLAUDE.md (and what to put in) 10:30 Context Management 11:31 Debugging with Claude 12:22 Version control 14:12 Prompting, Just ask Claude 16:01 LEVEL 2: Intermediate 16:24 Customizations (Skills, Plugins, MCPs) 24:42 Workflows: Plan, Build, Test 29:52 Verifying and Documenting with Claude 33:10 LEVEL 3: Master 34:17 Multi-Agent Development (multi-clauding with git worktrees) 37:07 Self-improving Systems 38:45 Ralph Wiggum Agent Loops 40:11 Async Task Delegation 42:00 Agent Teams, Pre-configure permissions, Hooks 44:42 Continue your learning
Avthar62,263 次观看 • 6 个月前
NEW AI CODING TUTORIAL -- 6 Months of Claude Code Community Lessons in 27 Minutes 00:00 Claude: The New King of AI Coding? 02:14 Level 1: Beginner 02:29 Installation 03:37 Todo lists 04:16 Essential Commands 06:35 Debugging with Claude Code 07:57 Claude dot md file 09:33 Message Queue 09:57 Markdown file prompts 10:33 Level 2: Intermediate 10:51 Planning Modes 12:10 Thinking Modes 12:58 More than Code: Research, Documents, Changelogs 15:16 Github Actions Integration 15:59 Mindset for Success with Claude Code 17:23 Level 3: Master 17:48 Parallel Subagents 18:16 Multiple Claudes (aka "multi-clauding") with Git worktrees 19:30 Custom Slash Commands 20:50 Custom Subagents 22:50 MCP Server Usage 24:05 Cost and Value for Money 25:56 Conclusion: What's next?
Avthar42,646 次观看 • 1 年前
The future of AI is open-source. And ollama is the easiest way to build AI applications with open-source LLMs. Here's how to build a free, private RAG app using open-source tools. We'll use: - Ollama for LLMs and embedding models - PostgreSQL for data storage and retrieval - pgai Vectorizer for embedding creation and sync (I use Nomic for embeddings and tinnyllama as my LLM but you can substitute them for any models on Ollama)
Avthar34,261 次观看 • 1 年前
Maximizing your token throughput is one of the biggest productivity unlocks in Claude Code. So here's my guide to use multiple Claude Codes at the same time, effectively: - Run multiple Claude Code sessions at the same time, each on a different feature (Ghostty is great for this) - Use Claude Code's built in git worktrees to keep each instance isolated on its own branch (-w or --worktree flag) - Let Claude handle creating PRs or merging the worktree branches when you're done - Use the Claude Code Desktop app as your multi-agent control center Full guide below:
Avthar10,723 次观看 • 5 个月前
没有更多内容可加载