What AI Agent Should YOU be Using?

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

Source video:
- Title: What AI Agent Should YOU be Using?
- URL: https://www.youtube.com/watch?v=CF8sq1kYIOo
- Topic: Agent Architecture
- My current learning frame: Take one real task you'd hand an agent, place the candidate tools on the persistence/access grid, then rate each on the six criteria to decide which agent fits and why.
- Why this matters: New playlist item from Riley Brown; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:27 / Evidence 1: "one of the best developers I've ever met. And he spends most of his time using coding agents. And by the end of this video, you're going to have a mental model that most people building with AI..."
- 5:54 / Evidence 2: ">> Quick break to show you how you can put claude code or codeex in your iMessage group chats. All you need to do is go to chorus.com and then you are just going to click create your..."
- 16:29 / Evidence 3: "unreliability. But I think it really showed the world what the next evolution of agents is. So we're going from like these co-pilots or these CLI first tools like cloud code and codeex and then we went to..."
- 21:14 / Evidence 4: "cost and so if that really matters to you using an agent that's built by them like Cloud Code and Codeex might be really really important to you but obviously there are limitations to that those agents and..."
- 26:24 / Evidence 5: "systems like managed agents. So you can upload your data to the cloud, but for the most part, it is local. Similarly, cloud co-work again local but it's in this like sandbox in your computer which is like..."
- 34:50 / Evidence 6: "they they want to give untechical people the ability to um to like use the power of cloud code because it's a coding agent. It's made for developers to use. But it turns out that coding agents are..."
- 40:36 / Evidence 7: "how we're going to see even like these local sort of agents like codeex or cloud code do more things in the cloud. So, for example, at the code with cloud summit, um Daario was up on stage..."

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 "What AI Agent Should YOU be Using?", not a generic Agent Architecture 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.