I Audit Vibe Coded Apps for CEOs. Here's What I Keep Finding

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

Source video:
- Title: I Audit Vibe Coded Apps for CEOs. Here's What I Keep Finding
- URL: https://www.youtube.com/watch?v=XiXwOu_QJYA
- Topic: Interfaces + Open Design
- My current learning frame: Convert one risky workflow in an agent-built prototype into a delivery contract, collect a screenshot or recording as proof, and have a separate human or system verify it against the stated behavior.
- Why this matters: New playlist item from Brainqub3; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:16 / Evidence 1: "think it's excellent that you're doing that, and plenty of my clients sit in that category. But, I want to give you a warning. You should not believe everything that Claude Code or Codex tells you. Do not..."
- 2:21 / Evidence 2: "person is usually the best person to do that because they understand on the process. And from the audits I've done, most of the time those specifications are pretty good. So, we have a detailed specification, which already..."
- 5:53 / Evidence 3: "There are hundreds of tests that have been implemented retrospectively that aren't actually testing the intended behavior of the application. They're simply written to pass. That's it. So, inevitably, the question is, why does this happen at all?"
- 8:16 / Evidence 4: "the takeaway from this is do not blindly believe what Claude Code or Codex tells you it's done, especially if you're a vibe coding CEO or a vibe coding product manager that intends to have that software facing..."
- 11:36 / Evidence 5: "agentic system that delivered the proof artifact. I've done this in the past using my own eyes, manually verifying things and it depends on the scale and the velocity of the development. Or you can automate that verification."
- 13:19 / Evidence 6: "access, the delivery contract could be agent owned. A lot of this depends on risk appetite and other things You need to consider if you're doing this for anything serious. So, long story short, this is how I..."
- 14:50 / Evidence 7: "product manager that has built something with Claude, think about delivery contracts. You must prove that Claude has done the work or Codex or whatever agent has done the work that you've set it out to do. 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 "I Audit Vibe Coded Apps for CEOs. Here's What I Keep Finding", 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.