Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

I was an AI coding skeptic until I tried plan mode. Without it? Slop. With it? Me-quality code. We'll cover: - What plan mode is - How it helps the agent - How it helps you - Tips for improving plans - "But surely coding solo is faster?"

Matt Pocock

291,504 subscribers

60,673 views • 5 months ago •via X (Twitter)

Education Science & Technology

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

AI has completely changed coding. Bytedance has just launched an IDE called Trae AI, a powerful new AI coding assistant that helps you code faster and smarter. It's 100% free... 🤯 Here's how it works:

AI has completely changed coding. Bytedance has just launched an IDE called Trae AI, a powerful new AI coding assistant that helps you code faster and smarter. It's 100% free... 🤯 Here's how it works:

Angry Tom

297,480 views • 1 year ago

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

With all the buzz around the Codex App, OpenAI Developers quietly snuck out a new CLI update (0.94.0) as well. And boy is it an important update! Codex Plan mode is now officially released to the general audience! I am very excited about this one as it has a really strong prompt that is unlike any other plan mode I've personally used. Codex Plan mode doesn't necessarily just ask you 3 questions up front. It goes, collects context, asks questions, collects more context, asks more questions (sometimes), and then writes an incredibly high quality plan. It is my favorite implementation of plan mode thus far. It also comes with Codex's own version of "AskUserQuestion!" Although, it only works in Plan mode for now. They really need to allow people to use it in Code mode as well, but one win at a time. npm i -g @openai/codex Below is a demo of how it works. Let me know what you think!

am.will

57,121 views • 4 months ago

Scott AI (Scott AI) is building coding agent plan mode with superpowers. Run multi-agent swarms to find your best spec faster. Congrats on the launch David Maulick (tryscott.ai) and Devin Cintron tryscott.ai!

Scott AI (Scott AI) is building coding agent plan mode with superpowers. Run multi-agent swarms to find your best spec faster. Congrats on the launch David Maulick (tryscott.ai) and Devin Cintron tryscott.ai!

Y Combinator

38,152 views • 7 months ago

AI helps you move faster, but it just accelerates software entropy. Here's how to de-slop a codebase ruined by AI, with one skill:

AI helps you move faster, but it just accelerates software entropy. Here's how to de-slop a codebase ruined by AI, with one skill:

Matt Pocock

76,112 views • 1 month ago

your coding agent sucks because it lacks context. so I built nia to fix that. here is how you can 10x your coding agent (thread):

your coding agent sucks because it lacks context. so I built nia to fix that. here is how you can 10x your coding agent (thread):

Arlan

54,135 views • 11 months ago

Alibaba just dropped an AI that doesn’t just write code. It runs it. Tests it. Fixes it. Until it actually works. Here’s what makes Qwen 3 Coder Next different: → Executes code, not just autocomplete → Runs tests automatically → Iterates until all tests pass → Handles multi-file repositories → Works fully offline This is a real coding agent, not a text generator. Save this video, you’ll rethink how coding gets done. Want the SOP? DM me. 💬

Alibaba just dropped an AI that doesn’t just write code. It runs it. Tests it. Fixes it. Until it actually works. Here’s what makes Qwen 3 Coder Next different: → Executes code, not just autocomplete → Runs tests automatically → Iterates until all tests pass → Handles multi-file repositories → Works fully offline This is a real coding agent, not a text generator. Save this video, you’ll rethink how coding gets done. Want the SOP? DM me. 💬

Julian Goldie SEO

20,956 views • 4 months ago

o3-mini 1-shoted the 40 Step Coding Plan for Cursor. This is huge! Coding models struggle to plan the coding workflow in Cursor/Windsurf. It is solved now. We already implemented it in CodeGuide Enjoy.

o3-mini 1-shoted the 40 Step Coding Plan for Cursor. This is huge! Coding models struggle to plan the coding workflow in Cursor/Windsurf. It is solved now. We already implemented it in CodeGuide Enjoy.

CJ Zafir

129,623 views • 1 year ago

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Nothing beats open-source! We now have a fully open-source coding agent that can compete with any proprietary solution out there: • 500+ available models • It doesn't train on your code • It doesn't charge a penny for tokens • It's open. You can change if you want. Kilo Code is the #1 app on OpenRouter right now, and the community is releasing new features on GitHub at rocket speed (about 20 releases in the last 30 days). I installed it in Visual Studio Code, but you can install it in pretty much any IDE. I need to spend more time with it, but here is a very interesting design choice: Most coding agents support two modes: an "agentic" mode for writing code and an "ask" mode for talking to the model without making any changes. Kilo Code supports 5 different modes: 1. Architect mode - Research, design, and planning 2. Debug mode - Problem solving and troubleshooting 3. Code mode - To write code. 4. Ask mode - To talk to the model. 5. Orchestrator mode - Combine every agent to solve problems. On paper, I really like this. I'll need more time to try out the specialized agents and see whether niching becomes an advantage. Here is the link to the website: Thanks to the Kilo for partnering with me on this post.

Santiago

73,062 views • 7 months ago

I built a Mission Control dashboard for OpenClaw and it became 10x more useful Helps me build projects faster, visualize my work, fix problems, and much more In this video I show my entire setup and how I built it with 0 coding Prompts included below

I built a Mission Control dashboard for OpenClaw and it became 10x more useful Helps me build projects faster, visualize my work, fix problems, and much more In this video I show my entire setup and how I built it with 0 coding Prompts included below

BentoBoi

34,908 views • 2 months ago

How does it feel to code with CyberCoder? Like this... 😎 Coding with the #1 AI Agent in the world feels different🔥

How does it feel to code with CyberCoder? Like this... 😎 Coding with the #1 AI Agent in the world feels different🔥

BLACKBOX AI

19,773 views • 1 year ago

I paid the $500 for Devin, the mega hyped AI coding agent, so you don't have to here's an in depth review of how it compares to Cursor:

I paid the $500 for Devin, the mega hyped AI coding agent, so you don't have to here's an in depth review of how it compares to Cursor:

Steve (Builder.io)

368,028 views • 1 year ago

Plan mode was built to be fully extensible 🧩 An example is the Conductor extension for Gemini CLI It uses both plan mode and the ask_user tool. Conductor enables Context-Driven Development, acting as an orchestrator for multi-step development tracks, guiding you through complex migrations or feature implementations. Have you tried it? 🚆

Plan mode was built to be fully extensible 🧩 An example is the Conductor extension for Gemini CLI It uses both plan mode and the ask_user tool. Conductor enables Context-Driven Development, acting as an orchestrator for multi-step development tracks, guiding you through complex migrations or feature implementations. Have you tried it? 🚆

Gemini CLI

58,548 views • 2 months ago

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

I tested a new coding assistant on 34,568 lines of code. (Cursor could not achieve what this tool did.) AI models are improving every day: - Faster inference - Longer context lengths But are AI coding assistants advancing at the same rate? Can they truly understand your entire project? I tested Augment Code on my ai-engineering repo with ~35k lines of code. Augment Code is a powerful AI Assistant built for developers working with large, evolving codebases—needing an assistant that understands the full context of their projects. In the video demo below, I asked it to: - Merge two projects. - Answer a global context question. Here’s what happened: - It understood dependencies across both projects. - It merged them intelligently—without breaking anything. - It even created a README file for the merged project. - It answered my global query instantly, pulling from the full codebase. This is the difference between AI autocomplete and an AI engineer that truly understands your repo. Augment Code is powerful because it indexes your entire repo upfront. This way, it can answer questions instantly, no matter how large your project is. Lastly, Augment Code is fully compatible with VSCode, JetBrains, Vim, Slack, and more. Try them now, I have shared a link in the next tweet! Thanks to Augment Code for showing me their powerful AI coding assistant and working with me on this post.

Akshay 🚀

30,799 views • 1 year ago

The Codiumate-Agent is the first step towards tandem development with your coding agent. It effortlessly slots into your development workflow, helps you be smart about your planning, and offers smart coding completions that make every feature development smoother.

The Codiumate-Agent is the first step towards tandem development with your coding agent. It effortlessly slots into your development workflow, helps you be smart about your planning, and offers smart coding completions that make every feature development smoother.

Qodo

774,196 views • 2 years ago

SHIPPED. Mistral Vibe is now the AI agent for long-horizon productivity and coding, and the home for Work mode, Code mode, the CLI, and a brand new VS Code extension. Let's go... 🧵

Mistral Vibe

225,274 views • 23 days ago

I HAVEN'T TOUCHED MY KEYBOARD IN DAYS ‼️ THIS IS HOW I TALK TO CLAUDE CODE NOW 🎙️ voice dictation + claude code = hands free coding here i walk you through my 10x morning routine Claude helps me with!

I HAVEN'T TOUCHED MY KEYBOARD IN DAYS ‼️ THIS IS HOW I TALK TO CLAUDE CODE NOW 🎙️ voice dictation + claude code = hands free coding here i walk you through my 10x morning routine Claude helps me with!

BOOTOSHI 👑

24,380 views • 5 months ago

CLAUDE CODE IS NOW FREE AND YOU CAN BUILD AN ENTIRE AI CODING SYSTEM WITH 1M CONTEXT, AGENT OS AND OBSIDIAN MEMORY WITHOUT PAYING FOR ANY OF IT. The stack gets smarter over time and costs you nothing to run.

CLAUDE CODE IS NOW FREE AND YOU CAN BUILD AN ENTIRE AI CODING SYSTEM WITH 1M CONTEXT, AGENT OS AND OBSIDIAN MEMORY WITHOUT PAYING FOR ANY OF IT. The stack gets smarter over time and costs you nothing to run.

0xMarioNawfal

51,173 views • 17 days ago

Hermes Agent is an INCREDIBLE AI agent It's better than OpenClaw in some key ways, but does it replace it? In this video I cover what Hermes agent is, how to use it, workflows that will explode your productivity, and if it's the OpenClaw killer:

Hermes Agent is an INCREDIBLE AI agent It's better than OpenClaw in some key ways, but does it replace it? In this video I cover what Hermes agent is, how to use it, workflows that will explode your productivity, and if it's the OpenClaw killer:

Alex Finn

136,648 views • 2 months ago

🚨just in: the first AI coding agent for serious builder is here AI copilots help you write code. ClackyAI helps you build software. your agentic coding studio → L3 agentic AI, full-stack awareness, real-time debugging, parallel tasking join the beta now:

🚨just in: the first AI coding agent for serious builder is here AI copilots help you write code. ClackyAI helps you build software. your agentic coding studio → L3 agentic AI, full-stack awareness, real-time debugging, parallel tasking join the beta now:

Nelly;

31,332 views • 1 year ago

Grok Build is coming. Not autocomplete… a full coding agent. You describe it. Grok plans, codes, and debugs. Up to 8 agents run in parallel. Apps, sites, full repos. Built from plain English. Arena Mode picks the best output. The local CLI keeps your code private. This isn’t “help me code.” It just builds. xAI Grok

Grok Build is coming. Not autocomplete… a full coding agent. You describe it. Grok plans, codes, and debugs. Up to 8 agents run in parallel. Apps, sites, full repos. Built from plain English. Arena Mode picks the best output. The local CLI keeps your code private. This isn’t “help me code.” It just builds. xAI Grok

Mario Nawfal

193,624 views • 1 month ago