ThesisThe Future of AI Agents Just Arrived ( /goal for Claude Code & Codex) teaches a practical agentic engineering move: Treat `/goal` as an agentic completion contract: state the desired outcome, define proof of done, and let the agent continue through planning, execution, and verification.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
1:14Definition of done
“actually introduced by Codex just 2 weeks ago. It got really popular over at X and now the Entropic team pretty much just copied it from Codeex and I think that's fine because that just gives us more...”
The /goal feature is the Ralph loop built into the harness: you set a completion condition and the agent keeps reworking each turn until that condition is satisfied, so the quality of your definition of done determines whether autopilot succeeds. Write a /goal prompt for a small task and explicitly state a concrete, checkable definition of done (e.g. 'loads with no manifest errors and shortcuts work') rather than leaving it implicit.
6:42Haiku self-check loop
“weekly rate limits reset, you won't have any regrets with this huge portion of your tokens being unutilized. But now, let's actually use gold for a more complex task. And what we'll do is do that for both...”
At the end of each turn Claude Code invokes the lightweight Haiku model to assess whether your definition of done was met; if not, it loops again, which is also why you can frontload token-intensive batch work before a weekly rate-limit reset. Plan a batch task (like generating multiple newsletter drafts from a skill) and run it with /goal to consume otherwise-wasted tokens before your limit resets.
9:46Plan-driven goal runs
“a lot to be desired when it comes to the design and the visuals of this. And interestingly, Claude code when it described the different AI labs in here, it described entropic as honest, helpful, and harmless. Google...”
For complex tasks, first generate a markdown plan (stack, in/out of scope, constraints, definition of done, acceptance criteria, turn budget) and point /goal at it; the turn budget can be set to unlimited and acceptance criteria are what the model checks against to decide when to stop. Generate a 'plan for goal' markdown file for a non-trivial build, then refine the acceptance criteria (e.g. forcing generated sprites to actually be used in the final HTML) before executing it.
01Intent
Start with this video's job: Treat `/goal` as an agentic completion contract: state the desired outcome, define proof of done, and let the agent continue through planning, execution, and verification. Treat "Intent" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:14, where the video says: “actually introduced by Codex just 2 weeks ago. It got really popular over at X and now the Entropic team pretty much just copied it from Codeex and I think that's fine because that just gives us more...”
Task Packet
Use "Task Packet" to locate the part of the agentic engineering workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 6:42, where the video says: “weekly rate limits reset, you won't have any regrets with this huge portion of your tokens being unutilized. But now, let's actually use gold for a more complex task. And what we'll do is do that for both...”
Agent Run
Turn "Agent Run" into the reusable artifact for this lesson: A task packet that a coding agent could execute without wandering. This is where watching becomes something you can inspect and reuse.
Evidence
Use "Evidence" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
Review
Use "Review" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
Standard
Use "Standard" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
ExampleSource-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a task packet that a coding agent could execute without wandering..
ExampleClaim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
ExampleTeach-back module
Transform the lesson into a definition, a mechanism diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong- Treating the title as the lesson without checking what the transcript actually says.
- Letting the prompt drift into generic advice that could apply to any video in the playlist.
- Copying the tool setup without identifying the operating principle that transfers to your own stack.
- Skipping the artifact, which means the learning never becomes operational or inspectable.
