What are Agentic Loops?

Everyone is talking about agentic loops, but the reality is most people don't know what it is or how to use them in this F.I. brought on Professor Ross Mike to clearly explain what it is Is it hype? Is it real and how to use it and if you stick around to the end of the episode He shows me the most concrete use case of agentic loops that you can use starting today Enjoy the episode Is it the time? Ross Mike welcome to the pod by the end of this episode what are people going to learn? You're going to understand what a loop is you're going to understand why people are fanny out about it And you're going to understand why it is a terrible mistake and unless you have money to burn that you are not to do it I'm also going to play the other side and I'm going to show you a loop that I use But the general consensus I think is wrong and we're going to talk about it Okay, so by the end of the episode people are going to understand what an agentic loop is why The most well-known people in the AI industry are obsessed about it You're going to keep it real with what we need to know about it and what we can avoid and you're going to show A real use case a real example of how to actually use an agentic loop Exactly exactly All right, bro. All right, let's get into it. So as always A lot of people love the diagrams. So we're just going to start with diagrams. I paid Like like I think three dollars to get these stick figures. So I hope people appreciate them This is me and you right this is your average joshmo who does not work at a thropic or API or open AI and this is Boris and Peter and anyone else who has unlimited access to Models now the way me and you have been working This is what is called a human in the loop is you and I will prompt our You know computer right, let's say this is our computer better. You know, say this is our AI agent Whether you're using cursor or clawed codex doesn't matter. You are prompting it yourself Right, you're telling it hey build me this landing page um You know build this feature x1c you are communicating with an AI agent to platform of your choice via a prompt And then a result is generated right a result is generated and usually what you and I will do is we will view this result We will test this result and we will keep on iterating this is the loop where it goes back to us Right, so let's say I'm working on an app and this app is a to-do list app Greg I'm the first thing I'll probably want to do is I want to build up the landing page because I want to get this out to the public So maybe they can sign up and join the wait list So I'll prompt and build me a landing page and let's say I like the landing page next. I'll work on authentication And then once I'm happy with other indication then I'll work on with the backend So this is what we are used to and this to be Sharp with it is called human in the loop meaning it is the agent that's building But it is you that is directing governing and allowing things to happen What everyone has been talking about particularly Boris and Peter and they said they don't write prompts They generate that they build loops and essentially what they're talking about is they're building a system And I'm just going to show you here where this is the AI agent right and then this is the result But instead of a human being in the loop the human is in the loop one time meaning it fires off Said loop, but then the rest of the time it's the agent Checking it's the agent generating a result that result is then fed back into the agent The agent then looks at the result and continues to work now This in theory sounds cool because what essentially we're saying is hey I'm just going to have some sort of spec.md file or some prd.md or whatever.md file And this is going to be like to do list a task list and this is going to give all of the information the AI agent needs to build this Now this sounds cool and this Loki might be the future But here is where it goes terribly wrong first and foremost I want to get paint this analogy. Let's say Quick break to talk about today's sponsor code rabbit We talk about agentic loops in this episode and most of them are still hype Code rabbit is one of the few that actually works my team literally uses it every day You open a pull request and code rabbit reviews it automatically It catches bugs. It suggests fixes and it's one click to commit It learns your team standards over time. So it just gets better and better They just shipped code rabbit review which takes a big messy pull request and reorganizes it So you can actually understand what's change and why in minutes instead of hour something I've wanted for years My team at LCA and idea browser love it. There's a 14 day free trial If you want to learn more about code rabbit go to the link in the description We we're building a startup right you and me Greg we're building a startup We hire a very smart developer and we tell this developer This is the app we want to build these are the things that it needs and the developer goes on and builds the entire thing without consulting us In building that entire thing that developer is going to have to make assumptions right Assumptions of how the product looks how it's going to feel certain architectural decisions There's a lot of assumptions that are going to be made in the nitty gritty now You might think your plan document covers everything but truth to the matter it never does There's always an edge case. There's always something that's missed So what the developer is going to do is that developer is going to make a lot of assumptions Those assumptions might not be aligned with our product vision Now you have a developer who's come with a finished product and now there's a bunch of things in order But it's not the way we want it in the same way when you have this stacked prd.md Follow this whatever markdown file you have and you give it to an agent and you run it in this loop Meaning it takes the feedback it takes the result takes it as feedback and continues to generate Code what happens is you now have an agent that's going to make assumptions and believe me when you give the agent The forward to give assumptions most of the time it's going to get it wrong But not only is it going to get it wrong. It's going to burn a lot of money Now I say this with all love But Boris and Peter come from a place where they have no token budgets Right they can burn unlimited tokens if I had unlimited tokens I've been doing the same thing too But this is not productive. This is great for research And I'll actually share a loop that I use but this idea of construct of constructing like a meta harness Where you give the agent feedback Automatically like it gets like the information the results generated and it loops on it It is a catastrophe and we've tried this right. We had Ralph loops. We had Ralph Wiggum There's even like slash goal which has been pretty popular the last couple weeks These are great to build prototypes These are great to experiment with like let's say you wanted to experiment with something you want to like some Miniscule tool built up but you didn't care about the nitty gritty details These are great But if you're if you care about the details and you don't have tokens to burn This is the worst thing to be trending right now in my humble opinion I'll stop right here just to make sure I'm making sense because as you can see I'm pretty passionate about this So slash goal is also trending at the moment You know is slash goal a loop like how should people think about slash goal and a loop? They're all the same thing they have different names like slash goal I know on cursor. I think it's slash loop and then on another tool at slash whatever They're all the same thing and basically how all of them work on a high level is you you know You type in slash goal and then you give it some prompt right like you give it Some prompt and then you can also like attach some you know markdown file and you tell it like yeah build this entire thing out Don't stop until you're done. Don't make any mistakes Again, these are cool But the two issues are number one. They burn a lot of tokens, right And if you are not like this shouldn't even be a thought if you're not on the $200 a month plan Like not a thought like if you're on the $20 or I think there's a $100 a month plan You shouldn't even think about this right because it's just gonna burn your token usage Number two You think your plan is good, but it's not because it's impossible for you as a human to contextualize every single detail about the product that you want In one document right things evolve trends change You know one day liquid glass is cool the next day. We're changing how liquid we want it like it's very impossible for you to fill like Your thoughts and exactly how you want the product to be one and one and one document if anyone works in service Whether you run an agency or you like for example, we developed software for other for other people and companies It I we try all the time to get all the thoughts out of someone's head There's always something. There's always a you miss this or I wanted it like this. This is what I meant How much more do you think an AI agent is going to understand you if we as humans have hard times understanding each other right? So this should only be used In the following Experimentation like let me do a new line Experimentation right? Let's say you wanted to like I'll share with you fun cool little tool I built the other day Greg I was doing a talk and I wanted to build an among the simulator for for AI models right Basically to this game where there's one bad guy one impostor and everyone's trying to figure out who it is And I wanted to have like my own benchmark to find out which models like are good at lying And I didn't want to I didn't care about the details. I didn't care about how it looked I just wanted the simulation of the benchmark to work So I told it I want the simulation. I want this benchmark. I wanted to do this Go and do it it took about I think an hour and a half and it got it done now There were a lot of details that I had admired That it completely got wrong that I didn't specify in the initial instruction set But guess what because I didn't care about the what it built in a sense Like I didn't really care for the details. It was a great thing. I didn't spend a lot of time I just got slash gold to take care of everything But when you and I are trying to use AI to build something meaningful I 100% 100% 100% stand in the fact that the human still needs to be in the loop AI can replicate sauce. It can't create sauce So if I just have these giant loops running And then once they're done maybe I'll go in and fix things up Sure you can make that argument, but I hope you have money to burn Right like and that's the ultimate thing this will burn Money it sounds cool, but it'll burn money What I'm hearing you say is that the loops are going to Create a slot machine machine That's basically what it is now I have no doubt the Borses and the Peters are building very sophisticated Like loops like I can imagine like let me drag this over to here I can almost imagine they have something like again I'm not sure this is just me guessing But I can imagine they almost have like some sort of Test suite right where like they write Tests for the agent to run the code against so it's a certain type of quality I'm sure they also have some sort of browser Browser use capability so the agent can see the page live and can take screenshots like I'm sure they have a insane harness or meta harness Around the agent so that this loop can be more successful than the our average loop But at the end of the day the one argument I'll fight back with is this is going to burn a lot of tokens And if you don't believe me all you have to do is look at Peter's tweet where in one month He burns 1.3 million Dollars worth of tokens, but I don't want to sound like a You know like I don't know what the word is like a doom or like all like like an old guy like These fuck there are use cases and I'll share one Greg if that's okay where my My code review process is a loop and I'll explain how it works. So I use cursor for the most part not sponsored. I use cursor for the most part as my harness of choice And with cursor I will use github as my source control basically a place where I store code version code and all that stuff And every time I push a feature like every time I build a feature I push a feature or whatever the case may be I am pushing code to github and In github I have a code review agent installed. There's many kinds my particular one that I use is greptile But I know people use code rabbit microscope. They're all great. I use greptile and What happens is whenever I push a feature to github The code that's being pushed to github is a generator But then I have a code review agent that reviews the air generated code and what's cool about greptile is it gives me this review Right, it'll be like oh you missed this. There's this security thing you this is broken in this edge case It's pretty it's pretty good But my favorite thing is it gives you a score a score out of five right it can be two out of five one out of five Five out of five four out of five whatever. It's a score out of five And what I the the mental model I now have is I will not Push anything to production meaning I will not allow code to go live Unless the score is greater than four out of five right if the score is not greater than four out of five This code needs to be reviewed now here is where I loop I have this skill called grep loop right and basically it again I don't want people to think it's complicated. I just want you to understand where loops make sense It's basically a skill that tells the agent oh check github read the review and then fix the review and then push to github So what happens is when I see a score Let's say you got a two out of a three out of five again. My rules Is that it has to be at least four out of five and greater So what I'm gonna do is I'm gonna go back to cursor I'm gonna write grep loop and then when I write grep loop what happens is cursor reads the review that greptile wrote on github And then it feeds the review back into cursor Cursor that makes the changes pushes the changes to github and then waits for grep tile to do a new review every time You push to github grep tile does a new review if the review still is a three out of five Guess what happens the loop continues and then more changes are made and then let's say it's a four out of five It doesn't give up it keeps it takes the feedback and then pushes it back to github It won't stop unless it's taken five turns and then it'll give up or it won't stop until it gets a five out of five now This is basically a loop, but if you notice this Greg this is a very closed off Very goal-oriented loop essentially. I have a feedback engine, right? I have a co-review agent that's giving a score What I'm telling cursors read the review Understand it and get that score to a five out of five This makes sense for co-review because there's a fixed feedback loop But when I'm building an app again, I have no idea what I want Completely in that very moment So it's very hard for me to generate a loop on an app that I have in my mind But I can't even fully visualize just yet now if you're great at visualizing you're a master You never miss details. You've never forgotten your auntie's birthday You don't forget your wedding out you're just perfect and you have a million dollars Go ahead and build loops But for me and myself the only place a loop makes sense is in a very confined constraint process with a very fixed feedback loop Um a very defined feedback loop and that's in co-review and can I be honest with you this loop actually quite breaks at times It's not perfect and you know when it breaks anytime I push over 1,000 lines of code 1k lines of code like if the if the code that it has to reviews more than 1000 lines I can almost never get a five out of five Because it's too much code for the agent to fully review and contextualize and understand so even in this fixed sort of ecosystem loop that I have here Even here There's there's there's reasons and places for it to break right so every time I push a change I have to make sure it's 1k lines of code or less or I have to tell the agent cursor Split this into multiple PR's multiple code pushes so greptalkan review I say that all to say I'm not a hater but Loops just don't make sense right now especially for building apps They make sense for code review they maybe make sense for like you Are trying to do some SEO and you have like an SEO formula and you want like 300 pages generated and all the pages look and sound the same go ahead But for anything that requires a slight bit of creativity Unless you're looking to donate money to companies. They're about to go public at trillion dollar valuation This just this just doesn't make sense to me The person listening to this podcast. I mean, it's literally called the startup ideas podcast. They're building apps you know, so What they're doing you know is they want to create an app a website a startup a SaaS a micro SaaS an agent first startup That has the highest likelihood of success and in order to do that You have to show your app to people in order to get feedback So what's missing from the the loop is there's no Sharing your app for feedback halfway through right you're just pressing or slash goal or you're just like Basically, it's think of it as like full self-driving you're going from Miami All the way to Charleston South Carolina and you're pressing go and there's no like you're gonna Go off and you see a really you know cute diner on the side of the road and you're gonna go order a fried chicken sandwich You can't you're you're on this you know, you're on this ride and Whether you like it the train has left the station. That's what this is and so My my belief on loops is actually a lot similar to yours. By the way, I love your rant I apologize and again if any of the companies are planning on sponsor you whatever I love you guys But this is I can't lie to the people you don't have to be like I got to be honest like I've seen a lot of people excited about this and in an idea. This is cool But like I know my some people got $20 subscriptions $100 subscriptions This will burn through that and it's not productive at all. So yeah, I just have to be honest I think where where the output is binary meaning black or white with no creativity There is a room for loops. That's my so that was my when I was reading all that was going on like I was like, okay To your point like with code rabbit or reptile the you know Code review or SEO or think you know those pages like It's it's binary either they did the job or they or they didn't so I think there's room for it but for for the people listening to this that are like I'm gonna go Build a startup and I'm gonna I need a loop to go build that startup You know make me a million dollars make no mistakes Right like that's where I think that this is a little bit misleading that being said To the credit of Boris and to the credit of Peter and to the credit of people who are talking about it Um, I do believe that we will get to a point 100% at some point in the future 100% in the future right that this will be possible Just not now just maybe not as of recording June 929 And again, like I don't fault them like I don't think they're malicious at all But it's like if you have like I'm telling if I had a limited token budget as well Greg why the heck would I prompt like tokens don't matter to me right and it makes sense They have to experiment. They have to like they they need to work on self-healing agents and all that type of stuff So their position makes sense my issue is everybody else who's you know creating content and teaching these things saying Well, this is creme de la creme is like no unless you want to donate to trillion dollar companies This is not it right now. It could be it in a month and I could look like a fool but right now This just does not make sense human in the loop is the best loop Thanks for clarifying it and and keeping it real with us Ross mic is his youtube name I'll include a link where you can follow him in the show notes and in the description and on acts Thank you for coming on here. You're You're you're just the person I needed to come on the show to just say go off king You're a loop you're a loop in the sense that You were the loop around just explain this clearly and keep it real just don't stop Well, I appreciate you for having me Greg is always it's a pleasure man. Thank you. I'll see you next time