This Is How You Should Be Actually Using Claude Loops

AAI LABS
Computing/SoftwareInternet Technology

Transcript

00:00:00You've probably already heard about agent loops since everyone is hyping them up a lot right now.
00:00:05And you might think they're just a way for these AI companies to get you spending more on their
00:00:09products since these loops chew through a lot of tokens. But that only happens when you're using
00:00:13the wrong type of loop for the job. As you already know, we're a software company and we've been
00:00:18experimenting with these loops in our AI coding tasks. Along the way, we've mapped out the different
00:00:23types of loops and which use cases each one is actually suited for. So out of all the loops we've
00:00:28set up, we're going to share the ones we found genuinely useful. We'll also show you how to set
00:00:33up each one and how each loop is going to impact your workflow. Before we get into the different
00:00:38types of loops, let's quickly recap what loop engineering actually is for those of you who are
00:00:43new here. We won't go deep here, but if you want the full breakdown, we covered it in a previous video
00:00:48on the channel. The core idea of loop engineering is that you stop being the person writing the prompts
00:00:53that drive the agent and you turn it into a system that writes the loop itself. Instead of spending your
00:00:58time setting things up and writing long, carefully structured prompts just to get it to build, you
00:01:02let the agent handle everything on its own. It learns as it goes, grows from the problems it hits
00:01:07along the way and figures out what it needs to do next. That's what an agent loop really is. In that
00:01:12previous video, we split loops into two types based on the outcome you get, the deterministic loop and
00:01:18the non-deterministic loop. A deterministic loop is the kind where you already know the outcome,
00:01:22so the agent has a solid way to check its own work against it, and it keeps working until
00:01:27it gets there. A non-deterministic loop is the kind where you don't, so there's no solid way for
00:01:32the agent to check its work, which means you need other ways to handle it. But that was a broad split,
00:01:36and we showed just one way to set each of them up. They can be built in a lot of different ways,
00:01:41and each setup changes what you can do. The first type is one most of you have probably already used.
00:01:46It's basically the building block of every other loop, and the clearest example is the goal command.
00:01:51We call it the stateless loop, and basically it means the loop doesn't hold on to anything or improve
00:01:56itself as it works. There's no part where it learns from what happened and gets better. That's exactly
00:02:01what makes these the simplest loops there are. The one you've probably already seen of this type
00:02:05is the ralph loop, and it's stateless because it never kept any memory. It just ran the same task
00:02:10again and again, and the moment it saw the task was finished, it stopped. As you might already know
00:02:15about the goal command, it is the best example of the stateless loop. To use it, you tell it what
00:02:19you want to build, right after the goal command. From there, Claude sets that as the goal and starts
00:02:25working on it. Then every time the main agent decides a task is done, it uses a smaller model to
00:02:30double check the work. In Claude code, that smaller model is haiku. It checks everything the agent
00:02:35did against the requirements you gave in the prompt, and if the task isn't fully done,
00:02:38it re-prompts the agent to finish what it missed. But there's a problem with this loop. It leans
00:02:43entirely on the model to decide whether a task's done, with no standard to measure the work against.
00:02:48That's why it works best on features whose requirements you can check in some hard concrete
00:02:53way. One way to do that is with tests. Like we talked about in our previous video, we write the tests
00:02:58before asking Claude to build any feature. That way, if Claude changes that feature in a way it shouldn't,
00:03:03the tests throw an error and tell Claude its implementation is off. And once we've got tests
00:03:08for every feature, we can hand the agent real autonomy and let it work without worrying it'll
00:03:12break the other features or build the one we want the wrong way. Once you've written the tests,
00:03:17you can ask Claude code to set the goal as getting that feature to pass all the tests. And it keeps
00:03:22writing code, running the tests to check itself and keeps going until every test passes. Once they all
00:03:27pass, that means the feature is built correctly and Claude will mark the goal as complete. Since the agent's
00:03:33working on its own, you'll want to add one line to your Claude.md file. That line tells the agent to
00:03:38save every working version of the app. That way, if it breaks the app somewhere down the line,
00:03:43it can just roll back to the last version that worked and carry on from there instead of trying
00:03:47to undo changes from memory. But before we move on to more types, let's have a word by our sponsor.
00:03:53Minimax. Minimax just dropped M3 and it's the first open weight model to hit the frontier on three things
00:03:59at once. Coding, a one million token context and native multi-modality. So we plugged the M3 API
00:04:06straight into Claude code and gave it one real job, researched the top electric cars on sale now and
00:04:11build a live comparison dashboard. M3 took it from there on its own. It browsed the web, pulled real
00:04:17specs and prices, then shipped a working dashboard from scratch. You can search different EV brands,
00:04:22browse their latest models and everything updates in real time. On autonomous browsing, it beats Opus 4.7
00:04:28and its million token context held every page plus the whole code base in one window. But agent runs
00:04:34like this burn a lot of tokens and that's where the Minimax token plan comes in. Pick token plan for fixed
00:04:40costs or pay as you go for flexibility. Text, image, speech and music share the same token pool with the
00:04:46highest quotas. Plans start at just $20 per month, so hit the first link in the description
00:04:51and get an exclusive 12% off. The stateless loop we just walked through holds no state. It does everything
00:04:58on its own from the instructions with no self-improvement in the process. The next type works the opposite
00:05:03way and we call it the learning loop. A learning loop works differently. Instead of just getting a
00:05:08task done and stopping, like a stateless loop or the goal command, it focuses on improving something
00:05:13you'll use repeatedly, whether that's a skill or a workflow. The way it does that is simple. It runs the skill,
00:05:18observes how it performed and then improves it based on what it learned, keeping a complete record of
00:05:23every lesson along the way. So that when you run the skill, when you're actually using it, the agent
00:05:28knows what caused issues in past, so it won't lean towards that. You can put this kind of loop to work
00:05:33for a lot of things. For example, on the community website of ours, we built multiple skills to handle
00:05:38different repeated workflows while putting the site together. But building a skill raises an obvious
00:05:43question which is how you'd even know whether it's working the way it should. So to answer that, we set
00:05:48up a full learning loop. We did it by creating a skill loop command that triggers the loop. This command
00:05:53contains instructions to call a skill improver agent and keep calling it until there is no more
00:05:58improvements left. This skill improver is actually an agent we created which improves the skill by
00:06:03assessing its quality, testing it across multiple areas and watching for the issues that come up. To use it,
00:06:08you just run the command and pass in whichever skill you want to improve and it gets to work. This loop
00:06:14runs in multiple rounds. In each round, it runs a set of tests and checks after making its changes.
00:06:19Then it launches a separate Claude session that works only on the prompt you pass it, running in the
00:06:24background without stopping to ask permission for anything and reporting the output back. Inside those
00:06:29sessions, it runs the implementation two ways, one with the skill and one without, so it can measure the
00:06:34actual impact the skill has. That comparison lets it pin down exactly what needs improving and it makes
00:06:40those changes directly. But the most important part is the learning.md file it creates. This file
00:06:46gives the agent a way to know what works and what doesn't and it lives inside the skill itself. It's
00:06:51basically an improvement journal that documents everything the agent learns in a structured format.
00:06:56It records what it tried and what the result was, both with the skill and without it, then lists the
00:07:00lessons it picked up across all the rounds it worked through and that's how it keeps going round after
00:07:05round until the skill is refined into the best possible version of itself. You can use the same
00:07:09setup to improve any workflow you've got. In our previous video, we showed how to build a loop with
00:07:14two agents, one that handles the implementation and another that reviews the work and reports backfixes for
00:07:20the implementation agent to apply. There's a problem with that setup which is that a single review agent is
00:07:25handling every aspect of the review on its own. But a review is never about just one aspect. It always
00:07:30comes from different perspectives and that's too much ground for one agent to cover alone. It's
00:07:35better to split those across different agents because when multiple agents review across multiple
00:07:40dimensions, they cover the blind spots any single agent would miss and that makes the review way more
00:07:46complete. The idea is close to the LLM council that Andrei Karpathy released, which is a council of
00:07:51multiple agents that talk to each other and argue over a topic you hand them using the reasoning of
00:07:56several models to land on the right answer. For creating a multi-agent loop, you need to create
00:08:00multiple agents. So for example, we created four agents in the loop we set up. The first checks for
00:08:05factual correctness and it comes with tools like web search so it can ground itself in real sources.
00:08:10The second is a domain checker agent which checks whether whatever is being reviewed is actually
00:08:15relevant to what we're trying to do. The third is a safety critic agent which looks at the safety issues
00:08:20like sensitive content along with security risks and policy violations that could cause problems
00:08:25down the line. And the last is the style critic which makes sure the content is clear and well written
00:08:30and tailored to the style we're after. You can use these agents for any task whether it's coding or not.
00:08:35What ties these four together is an orchestrate command that we created. This command contains the
00:08:40detailed instructions for how it should manage and coordinate all four agents and handle the feedback
00:08:46each one reports back. To start the loop, you run the orchestrate command and ask it to review whatever
00:08:51you want and it spins up all the agents for the process. The orchestrate command runs in multiple
00:08:56rounds too, spinning up every agent in each round. The main agent applies all the fixes reported in round
00:09:01one then spins them all up again for the next round. By the end of the final pass, you're left with the
00:09:06app in way better shape. If you'd rather the agents communicate directly, you can use the agent team's
00:09:12workflow we covered in a previous video which gives you more of the LLM Council experience without one
00:09:17agent handling all the communication. But we chose the orchestrator because one agent needs to hold the
00:09:22context of the previous rounds to coordinate the workflow properly. Another type we reach for often
00:09:27is the verification loop. It uses multiple agents as well where one does the implementing and the other
00:09:33scores that implementation and the implementer's whole job is to get that score as high as possible
00:09:38against a set metric. To set that up, we created a command that coordinates the entire loop running the
00:09:43whole review workflow on its own. As you already know that Cursor has thermonuclear review. It's actually
00:09:48a really powerful review skill that checks how clean and healthy the code is so it stays easy to build on
00:09:54later. It audits all of the code and hands back an in-depth review with non-negotiable standards so
00:09:59you're guaranteed the highest quality review it can produce. To do that, it runs a dynamic workflow.
00:10:04The review has to span a lot of categories and a dynamic workflow is the best way to handle that,
00:10:09since it fans the work out across multiple sub-agents that each take on a different aspect at once.
00:10:15Like we mentioned earlier, we created two agents that act as the players in this loop. The first is
00:10:20the implementer whose job is to read the PRD and then build the required functionality. The second
00:10:25is the thermonuclear code reviewer and its only job is to hand back a review score. Since all it does
00:10:30is review and score, it doesn't have tools for editing. To trigger it, you run the review loop command.
00:10:35It starts by understanding what the app is meant to build, then kicks off a thermonuclear review for
00:10:40round one. That first review flags the issues it finds, including a critical one that's stopping the
00:10:45app from even starting. It records the findings in a JSON file and spins up the implementer agent to
00:10:51fix them. The loop keeps going from there, but keep one thing in mind. Because it's reviewing across so
00:10:56many dimensions, it takes a really long time and eats up a lot of tokens, since the dynamic workflow
00:11:01driving it fans the work across a whole set of sub-agents at once. So we wouldn't recommend it unless
00:11:06you've already built the whole app at a larger scale and want it thoroughly reviewed. You can also build
00:11:12this same loop without the dynamic workflow by using a normal reviewer agent, which takes less time and
00:11:17burns through way fewer tokens. And if you're enjoying the video so far, subscribe to the channel and hit
00:11:22the hype button. This small gesture of support goes a long way for us. Out of every loop we've shown you
00:11:28so far, none of them had a separate step for improving the loop itself, but that's really a core of what a
00:11:33loop is meant to do. That's where the workflow improvement loop comes in. What this loop does is go a
00:11:38step beyond just repeating the task. Instead of just running it again and again, it looks at the process
00:11:43itself and suggests improvements to the workflow. Now you might think the learning loop from earlier
00:11:48already does this, but there's a real difference. The learning loop improves a skill, one piece inside
00:11:53the process. This one improves the loop itself, the whole process you've set up. The entry point is an
00:11:58iterate command that acts as the orchestrator for everything that happens during each run. There are
00:12:03three agents this time. The first is a builder agent, which handles the implementation and delivers one of
00:12:08the app's requirements on each run. The second is a scorer that checks that implementation against a
00:12:13rubric we defined to act as the app's quality guardrail and scores the work out of 100. And the
00:12:19third is the process optimizer agent, which is the one that actually handles self-improvement.
00:12:24Normally, a loop runs through the same cycle where it plans, implements, verifies, and repeats, but this
00:12:29agent adds an extra step of going back over the loop iteration and suggesting ways to make it better.
00:12:35To use it, you just run the command iterate all. By all we mean we're implementing the entire app,
00:12:40broken into parts inside a single workflow. The loop starts by spinning up the builder agent,
00:12:44then the scorer evaluates what it built against the rubric and records the score in a JSON file that
00:12:49tracks every round. Then the process optimizer agent kicks in, going through the conversation to spot
00:12:55anything that could improve the workflow, making sure the app is built to a high quality and the
00:13:00right steps are being followed. So by the end of this workflow, you don't just walk away with a
00:13:04built app, you walk away with a workflow that's been tested and refined, with every step validated as
00:13:10one that actually needs to be there. That brings us to the end of this video. If you'd like to support
00:13:15the channel and help us keep making videos like this, you can do so by using the super thanks button below.
00:13:20As always, thank you for watching and I'll see you in the next one.

Key Takeaway

Moving beyond simple task execution, developers can engineer autonomous agent loops—ranging from stateless goal commands to multi-agent learning and optimization systems—that self-correct, refine their own processes, and ensure higher output quality.

Highlights

  • Agent loops shift developer roles from writing manual prompts to building systems that write their own loops.

  • Stateless loops like the Claude Code goal command use smaller models like Haiku to verify tasks against predefined tests.

  • Adding a command to save every working version of an application allows agents to roll back to functional states instead of relying on memory.

  • Learning loops utilize a 'learning.md' journal to record successes and failures, allowing agents to refine workflows over multiple rounds.

  • Multi-agent loops distribute review tasks across specialized agents, such as factual, domain, safety, and style critics, to cover blind spots.

  • Workflow improvement loops add a process optimizer agent to analyze and refine the iteration cycle itself, not just the task outcome.

  • Thermonuclear reviews employ dynamic sub-agents to audit code against non-negotiable standards, though this approach consumes significant token counts.

Timeline

Core Principles of Loop Engineering

  • Loop engineering replaces manual, long-form prompt writing with autonomous systems that write their own instructions.
  • Deterministic loops rely on predefined, verifiable outcomes, whereas non-deterministic loops require alternative validation methods.
  • Agent loops leverage continuous learning or re-prompting to handle tasks without human intervention.

This section defines loop engineering as a transition from static prompting to dynamic system design. The core objective is allowing an agent to manage its own development process, learn from errors, and determine subsequent steps independently. Loops are categorized into deterministic and non-deterministic types based on the presence of a verifiable outcome.

Stateless Loops and Automated Testing

  • Stateless loops like the Claude Code goal command run tasks repeatedly without retaining improvement data between runs.
  • Writing tests before feature development creates a concrete standard for the agent to verify its own work.
  • Implementing a rollback mechanism in the Claude.md file prevents total failure if an agent breaks working code.

Stateless loops serve as the fundamental building block for more complex systems. By requiring the agent to pass predefined tests before marking a goal as complete, developers ensure functional accuracy. This approach effectively uses smaller, cost-efficient models for iterative validation.

Learning Loops for Skill Refinement

  • Learning loops focus on improving recurring skills or workflows rather than completing one-off tasks.
  • A skill improver agent assesses performance and conducts tests to identify necessary adjustments.
  • The learning.md file serves as a structured improvement journal that documents lessons learned across multiple refinement rounds.

This architecture goes beyond simple completion by observing performance to enhance future outcomes. A dedicated agent repeatedly tests the skill and updates the improvement journal, creating a self-refining loop that matures a workflow into its most efficient form.

Multi-Agent and Verification Systems

  • Distributing reviews across specialized agents—factual, domain, safety, and style—eliminates the blind spots inherent in single-agent reviews.
  • An orchestrate command manages the coordination and feedback aggregation across multiple rounds of review.
  • Thermonuclear review loops use dynamic workflows to audit code against rigorous standards, though this method is resource-intensive regarding token usage.

Complex tasks benefit from delegating different perspectives to specialized agents. The orchestrator agent acts as a project manager, synthesizing feedback from various critics to refine the output. Verification loops specifically optimize for a high performance score against a strict rubric.

Workflow Improvement Loops

  • The workflow improvement loop optimizes the iteration process itself rather than just the specific task.
  • Three agents drive this loop: a builder for implementation, a scorer for validation, and a process optimizer for systemic improvement.
  • Running the 'iterate all' command results in both a completed application and a refined, validated workflow.

This advanced loop adds a meta-layer of optimization to the development cycle. By analyzing the entire iteration, the process optimizer suggests structural changes to the loop, ensuring that each step in the development workflow is essential and high-performing.

Community Posts

View all posts