Why I switched to Pi...

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: Why I switched to Pi...
- URL: https://www.youtube.com/watch?v=MsPhMhfvgD4
- Topic: Codex + Claude Workflows
- My current learning frame: Install Pi, add one community extension from the package catalog and write one of your own (a custom tool or a system-prompt context injector), then prototype a tiny hosted agent with the coding agent SDK using a custom resource loader for skills and guardrails.
- Why this matters: New playlist item from AI Jason; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:14 / Evidence 1: "about Pi agent, why it is one of the best option for you to build agent system, and in the end how can you use Pi to build some agentic system like Post AI from scratch, which is..."
- 1:50 / Evidence 2: "better?" My answer for the past few weeks just they are same. There's no real difference between those coding agents anymore. But why did Open Claw choose Pi Agent as the base to build upon? Because CloudCode, CodeX,..."
- 4:56 / Evidence 3: "popular Cloud Code Codex feature already implemented by someone that you can plug into your Pi Agent, like the Go feature, the MCP adapter, the Chrome browser access, the ask user question tool, sub agents, plan mode, and..."
- 6:58 / Evidence 4: "can utilize agent loops, large language model OS, and the session management, but also extend it with MCP, memory sub agent, ACP, and many other things. And those type of customizability would be otherwise very difficult to achieve..."
- 10:13 / Evidence 5: "time you actually don't need to learn building those extension yourself, cuz you can just talk to the Pi agent, it will self-evolve. However, the real power of Pi, from my point of view, is actually not just..."
- 12:49 / Evidence 6: "can also use Pi agent package to build web hosted agent product like this Posia replica I did. But there are some nuance you need to handle because the Pi e-coding agent SDK at default is designed quite..."
- 14:47 / Evidence 7: "hosted agent system that can launch and run company autonomously. It is using pi's coding agent SDK as agent runtime. Breaking down into 11 different agents with orchestrator that's built around task entity and persist the state and..."

Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule

Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
   - answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
   - 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
   - a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
   - one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.

Quality bar:
- Make this specific to "Why I switched to Pi...", not a generic Codex + Claude Workflows essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- If evidence is weak or missing, stop and say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.