Why I switched to Pi...

Name: Why I switched to Pi...
Uploaded: 2026-07-14T10:35:00.000Z
Duration: 15 min 19 s
Channel: AI Jason

AI JasonJuly 14, 202615m

Topics17

Introduction to Pi Agent and Sponsorship0:00 Cloud Code Playbook and HubSpot Sponsorship0:31 Understanding Pi Agent as a Coding Agent1:31 Limitations of Existing Coding Agent Harnesses2:00 Pi Agent's Design Philosophy and Extension System3:02 Real-time Extension Capabilities and Package Catalog4:00 Dynamic Workflow and Feature Parity5:01 Pi Hyper Package and Token Optimization6:01 Open Claw's Architecture and Extension Building6:30 Git Context Extension Example7:31 Custom Tool Creation and Clipboard Example8:01 Permission Gate Extension with Small Model8:31 Permission Testing and Pi Package Ecosystem10:01 Pi Agent Package Architecture10:31 Building Post AI with Pi SDK12:01 Web-Hosted Agent Development Considerations13:01 Resource Loader and Custom Extensions for Web Deployment14:01

In a Nutshell

Pi Agent's core advantage is its fully customizable extension system that lets you modify every part of the harness—tools, hooks, UI, session management—unlike Cloud Code or Codex which lock down their internals. This enables building agent systems like Post AI by extending the SDK with MCP, memory, permission gates, and custom workflows, while token-optimizing packages like Pi Hyper can cut token usage 80-90% by pre-processing tool results. The five packages (AI, agent loop, coding agent, TUI, up trader) provide the building blocks to scaffold both local and web-hosted AI products from scratch.

AI-Generated Notes

These notes were generated by AI and may contain inaccuracies.

Thanks HubSpot for sponsoring this video. If you're into AI agents, you've probably heard about this Pi agent quite a lot recently. Most people know Pi agent because it was what powering Open Claw. The goal is to give a breakdown of what's special about Pi agent, why it is one of the best option for building agent systems, and how to use Pi to build some agentic system like Post AI from scratch, which is an agent designed to launch and run a business.

Before diving into Pi, many users are already using coding agents like Cloud Code or Codec everyday. However, there's probably a 10 or even 100X difference between someone who just opens terminal, sends a prompt, and hopes for the best versus someone who fully utilizes every aspect of what this modern harness provides. Things like what type of Cloud or MD or agent.md actually works, how to structure code base that is agent ready, what hooks are set up, how to keep long running work on track with task state, and how to run more post sessions without creating a complete mess.

If you want to be on the right side of the gap, then the free Cloud Code Playbook created with HubSpot will get you there. This is a playbook that covers prompting patterns, how to set up Cloud or MD and project context, which hooks and guardrails to use, and how to manage task state for longer work. The favorite part is probably the parallel sessions setup that enables running not just one or two sessions, but 10 to 15 different agent sessions safely at the same time.

Although it is called the Cloud Code Playbook, the principles actually apply to Pi as well. Because for every Cloud Code feature, there's almost an equivalent package that can be plugged into the Pi agent. Most of the principles here are harness agnostic, which means no matter which agent is used, the approach can be adopted. The link is in the description below to download for free.

Fundamentally, Pi agent is a coding agent. When people ask whether Cloud Code is better or Codec is better, the answer for the past few weeks is that they are the same. There's no real difference between those coding agents anymore. However, the question is why Open Claw chose Pi Agent as the base to build upon.

CloudCode, CodeX, OpenCode all have their own SDK and CLI that allow building new agent systems by wrapping them. The core difference is that all the other coding agents harness, even though they're really powerful, can't really modify or change how the harness inside it works. Even CloudCode and CodeX are becoming increasingly similar to each other, but each one still has their own unique features. Like CloudCode has dynamic workflow, but if you're a user of CodeX, you can't just tell CodeX to implement this dynamic workflow as part of your harness, and vice versa.

Sign in to read the full notes

Get access to AI-generated notes, topic timestamps, and more.

Why I switched to Pi...

Introduction to Pi Agent and Sponsorship00:00

Cloud Code Playbook and HubSpot Sponsorship00:31

Sign in to read the full notes