Avthar Sewrathan's banner

Avthar Sewrathan

@avthar • 7,902 subscribers

AI CEO & Teacher Claude Code, GrokBot, Codex Youtube: https://t.co/baKD644cyW Past: @mongodb, @timescaledb, @Princeton

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

💥NEW: CODEX POWER USER GUIDE 3 rules that Codex power users follow to build better and get more done. Rule 1: The Verify Rule - Give Codex a way to verify its own work using browser use, computer use, and tests (and TDD). - Frame your prompts as a goal (outcome + constraints + when to finish) instead of a task. - Require Codex to gather evidence (test outputs, screenshots, exit codes) to prove success. Rule 2: The Context Rule - Onboard Codex like you would a new employee or teammate. - Use Plugins to connect Codex to the tools and systems you use for development and knowledge work. - Create your own Agent Skills to encode business processes and workflows + make them legible to Codex. - Login to SaaS tools via Codex's in-app browser. - Combine plugins, browser use and skills with Scheduled Tasks to put meaningful work on autopilot. Rule 3: The Orchestrator Rule - Let Codex prompt and manage itself (Codex is better at prompting Codex than me or you). - Give Codex an outcome and ask it to spin up one or more threads to achieve it. - Use ChatGPT Voice Mode to talk to Codex like a chief of staff, have it spin up new threads to do work and report back with results. - Ask Codex to use subagents for planning, implementation and review. Any Codex tips or best practices I missed that you'd add? Watch my full full video guide (with examples and demos):

💥NEW: CODEX POWER USER GUIDE 3 rules that Codex power users follow to build better and get more done. Rule 1: The Verify Rule - Give Codex a way to verify its own work using browser use, computer use, and tests (and TDD). - Frame your prompts as a goal (outcome + constraints + when to finish) instead of a task. - Require Codex to gather evidence (test outputs, screenshots, exit codes) to prove success. Rule 2: The Context Rule - Onboard Codex like you would a new employee or teammate. - Use Plugins to connect Codex to the tools and systems you use for development and knowledge work. - Create your own Agent Skills to encode business processes and workflows + make them legible to Codex. - Login to SaaS tools via Codex's in-app browser. - Combine plugins, browser use and skills with Scheduled Tasks to put meaningful work on autopilot. Rule 3: The Orchestrator Rule - Let Codex prompt and manage itself (Codex is better at prompting Codex than me or you). - Give Codex an outcome and ask it to spin up one or more threads to achieve it. - Use ChatGPT Voice Mode to talk to Codex like a chief of staff, have it spin up new threads to do work and report back with results. - Ask Codex to use subagents for planning, implementation and review. Any Codex tips or best practices I missed that you'd add? Watch my full full video guide (with examples and demos):

Avthar Sewrathan

113,667 просмотров • 2 месяцев назад

I've unlocked 10x more from Codex since I've let the agent prompt and manage itself. I call this "The Orchestrator Rule". Here's why it works so well: - Models like GPT 5.6 Sol are getting better at inferring your intent. - Codex has the ability to create, monitor, and send messages to other Codex threads. - So you can just tell Codex the outcome you want, and Codex can turn that into detailed prompts, spin up one or more threads to do the work, and bring the results back to you. This changed my job as a builder: Instead of writing perfect prompts, I described outcomes with success criteria and verification methods. And Codex wrote the prompts and orchestrated the work for me. Hence the "Orchestrator" Rule. Here are 2 ways to let Codex prompt and manage itself: (1) Ask Codex to kick off a task in a new thread. - You can give it a short description of the outcome you want to achieve, and Codex will expand that into the detailed instructions it needs to deliver. (2) Keep one parent thread for each project and let Codex spin up new child threads for individual tasks - This pairs really well with Voice mode. - You can talk to your parent thread like a chief of staff. It can kick off the work using child threads and report back when it needs your input or when the task is complete. I demo both these methods below:

I've unlocked 10x more from Codex since I've let the agent prompt and manage itself. I call this "The Orchestrator Rule". Here's why it works so well: - Models like GPT 5.6 Sol are getting better at inferring your intent. - Codex has the ability to create, monitor, and send messages to other Codex threads. - So you can just tell Codex the outcome you want, and Codex can turn that into detailed prompts, spin up one or more threads to do the work, and bring the results back to you. This changed my job as a builder: Instead of writing perfect prompts, I described outcomes with success criteria and verification methods. And Codex wrote the prompts and orchestrated the work for me. Hence the "Orchestrator" Rule. Here are 2 ways to let Codex prompt and manage itself: (1) Ask Codex to kick off a task in a new thread. - You can give it a short description of the outcome you want to achieve, and Codex will expand that into the detailed instructions it needs to deliver. (2) Keep one parent thread for each project and let Codex spin up new child threads for individual tasks - This pairs really well with Voice mode. - You can talk to your parent thread like a chief of staff. It can kick off the work using child threads and report back when it needs your input or when the task is complete. I demo both these methods below:

62,604 просмотров • 2 месяцев назад

💥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

💥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

Avthar Sewrathan

63,326 просмотров • 7 месяцев назад

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:

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:

18,444 просмотров • 2 месяцев назад

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?

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?

42,646 просмотров • 1 год назад

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)

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)

34,261 просмотров • 1 год назад

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:

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:

10,754 просмотров • 7 месяцев назад

Больше нет контента для загрузки