Herdr Gives You Full Control Over Multiple AI Agents

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

Source video:
- Title: Herdr Gives You Full Control Over Multiple AI Agents
- URL: https://www.youtube.com/watch?v=ZMehQM2sEjI
- Topic: Interfaces + Open Design
- My current learning frame: Set up Herdr with one workspace per project, install its agent skill, then recreate the coordinator pattern by running a ticket-style command on two small GitHub issues in parallel and shepherding both from worktree creation to opened pull request.
- Why this matters: New playlist item from Owain Lewis; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:37 / Evidence 1: "really valuable. All of the resources and the prompts that you need are going to be linked for free in the description below. So, let's get into it. Okay, so the first thing we're going to do is..."
- 2:18 / Evidence 2: "will be registered down here as an agent and then you can toggle between your agents. What's really nice about this is you can see when your agents are doing work and when they're stopped. So review the..."
- 4:51 / Evidence 3: "to show you now is my favorite use case for herder and my favorite pattern in general for working with coding agents. So we're going to start up claud code and I have a custom slash command called..."
- 6:36 / Evidence 4: "started up claude code and it's pasted in the prompt. So now we can work on this second task at the same time. So you can see here we have different agents. We have an agent working on..."
- 7:45 / Evidence 5: "different coding agent to implement this task. Use the Neo coding agent not claude code. Let's see if we can do this. I don't know if this will work. So we're going to say ticket paste in the..."
- 9:27 / Evidence 6: "description. If you scroll down to the hurder agent workflow project, all of the resources are here. So, inside the resources section, you'll find this command. And essentially, this is really simple. All we're doing here is basically..."
- 11:00 / Evidence 7: "a better interface to working on more complex software projects. I really moved away from using clawed code in the terminal because it was very difficult to stay organized. But with a tool like Herder, you can get..."

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 "Herdr Gives You Full Control Over Multiple AI Agents", not a generic Interfaces + Open Design 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.