# Vibe Coding with Confidence — Itamar Friedman, Qodo AI Engineer · 2025-08-06 Itamar Friedman, CEO of Qodo, argues that the command-line interface (CLI) is the future for achieving 'vibe coding with confidence' in enterprise software development. He contrasts vibe coding's greenfield success with the challenges of large codebases, where context, workflows, and multi-agent collaboration are essential. Friedman explains Qodo's multi-agent architecture, including tools for code review (Qodo Merge) and coverage (Qodo Cover), and announces the soft launch of a new CLI tool that lets developers create and pipe agents, supporting MCP and A2A protocols. He envisions a future 'swarm of agents' each specialized with credentials and best practices, enabling end-to-end workflows across the SDLC. The episode emphasizes moving from chat-based agents to command-driven multi-agent systems for reliable, high-quality code generation. ## Questions this episode answers ### What is 'vibe coding with confidence' according to Itamar Friedman? Itamar Friedman discusses how even Andréj Karpathy, who coined 'vibe coding', later acknowledged its limits, advocating for context and workflows. Friedman argues that 'vibe coding with confidence' means integrating rigorous testing, automated code reviews aligned with company best practices, and agentic workflows across the SDLC, shifting from vibing to producing reliable, maintainable software. [9:41](https://aie.addtry.com/23f2da27-be36-4ed9-a2ea-633d2bbda181?t=581000) ### What is Qodo's new CLI tool and why is it important for AI-driven development? Qodo's CLI tool, soft-launched at the AI Engineer World's Fair, enables developers to put AI to work across the entire software development lifecycle. It emphasizes command-line control to run, pipe, and orchestrate specialized agents (like Qodo Cover for test coverage or Qodo Merge for code review) directly in the terminal, allowing automated workflows, background execution, and seamless integration into existing pipelines—making vibe coding practical and trustworthy. [13:55](https://aie.addtry.com/23f2da27-be36-4ed9-a2ea-633d2bbda181?t=835000) ### How did Itamar Friedman demonstrate creating an AI agent on the spot using Qodo's CLI? During his talk, Itamar Friedman used the Qodo CLI to create a new review agent by simply prompting: 'please create an agent with this goal'. The CLI initialized its MCP tools, searched for capabilities, and after a couple of minutes generated a complete 'Merge Review Agent'—complete with instructions, tool definitions, and an output schema—which he then immediately called to review code, showcasing the CLI's ability to produce specialized agents on demand. [15:18](https://aie.addtry.com/23f2da27-be36-4ed9-a2ea-633d2bbda181?t=918000) ## Key moments - **[0:00] Intro** - [0:30] Qodo soft-launches a CLI tool for Vibe Coding with Confidence during Itamar Friedman's talk at AI Engineer World's Fair. - **[2:26] AI Evolution** - [3:01] The next AI development game changer will be CLI for end-to-end agentic workflows, says Itamar Friedman. - **[3:55] Confident Vibe Coding** - **[6:19] Squeezing the V** - [6:19] Vibe Coding lacks the 'red team' review process necessary for enterprise heavy-duty software, asserts Itamar Friedman. - [8:50] Squeezing the software development V-shape with multi-agent workflows is the game changer, says Itamar Friedman. - **[10:06] Carpati Revisited** - [10:24] Andrej Karpathy reconsiders Vibe Coding, saying 'code I actually and professionally care about contrasts Vibe Code.' - **[12:36] Qodo Multi-Agent** - [13:30] Qodo launches a CLI tool enabling multi-agent workflows across the SDLC, announced by CEO Itamar Friedman. - **[14:48] Live Demo** - [15:35] Itamar Friedman live-demos creating a code review agent from scratch using Qodo's CLI tool. - [17:08] Piping AI agents together via CLI enables code generation, test coverage increase, and review in one pipeline, demonstrates Itamar Friedman. - **[20:05] Swarm of Agents** - [20:42] Itamar Friedman predicts a 'swarm of agents' specializing in different tasks will dominate software development by 2025-2026. ## Speakers - **Itamar Friedman** (guest) ## Topics Vibe Coding, Agent Engineering, Multi-Agent Orchestration ## Mentioned Qodo (company), Wiz (company), ChatGPT (product), Claude Code (product), Codex CLI (product), Qodo Cover (product), Qodo Merge (product) ## Transcript ### Intro **Itamar Friedman** [0:15] Okay, so my name is Itamar Friedman, CEO and co-founder of Qodo, and I'm going to talk about, yeah, Vibe Coding, but more on the confidence part and why—this is maybe surprising—why CLI might be the new interface leader for that. And we are soft-launching a CLI toolright now, five minutes ago, so you can go—so you can go and install it. It's soft-launch, play with it, give us feedback, there is some capacity. And in order to verify, like, who is in the audience, just like, if you can tell me if you tried Claude Code or Codex CLI, okay. And I guess if I ask about AIDEs, you would also—also do that,right? And the question is why, and I'm going to talk about it a bit, okay? So the agenda is that I'm actually going to do is really zoom out to the Gen 3.0, what do I mean by that, and from the autocomplete to the multi-agent workflow. And workflows, you see it's a theme that we're returning here, CLI is something that can support that, and how do we believe at Qodo is going to be the real shift in software development. And, like, why is the CLI the future in, you know, being able to do Vibe Coding with confidence. And eventually I'm going to connect—zoom out again, I'm going to zoom in, zoom out, even with a demo, and connect the dots. And I will say what—explain a bit what is Qodo. I didn't do itright now, and we'll do it a bit later, but that's something I'm going to cover shortly. So, AI for developers, and I just think that most of people here are developers, according to the amount of hands that were raised. So I think, like, we first got some tools that we liked, AI tools, then we got some tools that we loved, and I'm not that sure that we actually get tools into our hands that completely become a game changer for us. Okay, might—it's maybe unpopular opinion, I'm going to elaborate a bit. So in order to do that, I'm going to differentiate developers between noobs and enterprise. It's a bit weird, like, it's not necessarily juniors, like, there are juniors and enterprise,right, but still, you know, like, let's use that for a second, noobs versus enterprise. So I think Gen 1.0 was the autocomplete moment,right? We started being able to generate, writing our code and getting a few lines ahead of us, we really liked that. If you weren't a developer, like, you couldn't really do more,right? ### AI Evolution **Itamar Friedman** [2:42] So you needed to be a developer already. And then came the Gen 2.0, the chat, the agentic chat, and I think, like, we saw even junior developers generating much more lines of code. Maybe the seniors or the enterprise liked it, but also had a lot of problems with it, they need to review much more code, not necessarily high-quality code. I hear that a lot, and I'm going to show you, like, 500 tweets about it, not really, but from some opinion leaders. And I think that the game changer moment is when we will move from chat, agentic chat, to actually being able to—and it's a spoiler—command, command line interface, to give commands to our agents as if they're, like, team members and they do end-to-end flow. What is an end-to-end flow is something I'm going to talk about a bit. And I think, like, you will see different players in different parts of this map, like, I mean, different tools. Let's think about it again. So I think, like, in the autocomplete moment we saw first ID plugins. Again, it's not a game changer, I'm just, like, going to complete more lines of code for you, we liked it. And then let's rethink how we do coding inside ID, so we saw ID forks. And then what's the third wave? ### Confident Vibe Coding **Itamar Friedman** [3:55] Sometimes I hear forking people, I didn't say that. What I think is actually we're going to see is, like, AI Across the SDLC, okay? Like, being able to do end-to-end flows that are specific, closing a task that's specific in the SDLC, but more importantly, using AI Across the SDLC. Again, not only in the ID, hence, how do we do that, command line,right? It's one of those tools. A lot of spoilers. So I think when we had the aha moment with the autocomplete, the next aha moment was, you know, all the hype around Vibe Coding, and I'm going to touch about that. And I think the next, like, thing that I think we're going to hear about is, like, hey, I'm really doing 100x, choose a number, 10x, 50x, 100x development, and I'm doing that with confidence, not just, like, vibing through it. I think that will be a game changer moment for us. It means that we totally broke the way we work, we're going to get to that. So I think, like, I differentiated between—I separated between noobs and enterprise, for example. I think for noobs it means end-to-end means, for example, that you prompt and get a software, a fully managed software for you,right? We—I guess we're all playing it with, even if you're a developer, you're doing some POVs or some side or being able to do some simple games. But then in the enterprise setup and the heavy-duty setup, then basically what it means for us, like, AI Across the SDLC is reliable, versatile workflows. And when I say workflows, we had a few sessions, amazing sessions, I'm actually, like, combining them, which is one of the points that were made there. Like, I think Charles made a point where an agent is creating workflows and calling them, and then there was a discussion about, like, workflows and, you know, using agents, etc. So when I say workflows, I already mean agentic workflow. Let's move on, like, workflow agent, who cares, like, so it's going to be combined. And I think, like, in order to do that with trust, you need to be able, more importantly, is to have workflows or agents that are related to trust. For example, having really high-quality reviewing capabilities, really high-quality testing capabilities, being able to do a variety of jobs to be done that we do as developers end-to-end-ish and high-quality. So that will be a game changer. Let's be a bit more specific. ### Squeezing the V **Itamar Friedman** [6:19] As developers, we do a lot of things, not just write code. I took, like, four parts, which is, like, I think less than a half of what we do. And I think, like, basically Vibe Coding was very focused on, let's, like, do initial planning and write code fast. Like, and, you know, Vibe, whatever we get, like, that implementation or that, we feel it and move on. But actually in heavy-duty software, we need to do many other things. We need to do, for example, bug fixing, or we need to do refactoring and changing features, etc. We want to move fast with fault-breaking things. So I think we need to have not the testing and the writing as a handsite, which you can do, like, testing and reviewing inside ID tools that are very mature. But not as a handsite, but rather, like, really being the red team,right? Thinking as a tech lead that is reviewing code and having, like, fitting technology for that. So if we are able to put, like, AI in each one of those, like, parts, maybe then it will be a game changer. But I think even then, like, we already have tools for code review, for testing, shameless plug, we're going to talk about later, that's what we do at Qodo. We focus being more on the red team. Even though we have tools for the blue, we are focused more on the red team. Still, I don't think it's a game changer, okay? And I think, like, a first, like, feeling of a game changer, as I mentioned, not only putting AI Across the SDLC, but having workflows across parts of the SDLC. So one semi-game changer could be, like, if we manage to shift left the review and the testing. As you write code, then you also get those suggestions and get high-quality code that is already according to your company best practices, and you don't need to wait for the AI review tool to tell you that only after you pushed it,right? But I think, like, I think we have even a better way to do that, a bit more agentic. So let's reanalyze these four blocks, these four tasks. So instead of having one, like, the X-axis, now there's also a Y-axis, it's executability. If you know the V-shape in Wikipedia or whatever, wherever you're searching now, ChatGPT, V-shape, software development, Y-axis, executability, X-axis, time. So we start with planning, it's not executable, then we write code, in most cases you're not doing, admit it, like, a TDD, okay? So you write your code, and then you write your test, and in most cases, and that's executable, but it's not application code, so it's a bit higher. And then you do the review. A game changer is, like, when we actually manage to take that V and squeeze it and have, like, different workflows and agents talking to each other. And that's why, like, I had the word MCP and A2A, and I'm going to get to that later. I guess, like, if you're in this conference, you know what I'm talking about, that where maybe there's different agents that are talking to each other, maybe it's one agent using tools that are able to connect all of these, like, all at once. That will be a game changer. So to, and to some extent, what it means is that, like, the game changer moment is when we're looking at all of these steps, like, rigorously, and one holistic solution. If you like, Cloud is mature for 10 years, and then Wiz came and said, we can't put in a security application for each part of the cloud, like, or each necessity of security. Let's build one holistic solution for cloud security. The same thing will happen to us in the game-changing moment for intelligent software development. Zooming out back again to Vibe Coding with Confidence, it didn't happen a long time ago when Carpati wrote about Vibe Coding, like, you know, really, like, I saw it, like, a decade already in AI years. And the interesting thing, it didn't take too much time, like, a month or two, where we started seeing pushbacks,right? This is not me, by the way. And actually, just a few weeks ago, the same Carpati came back and rethought Vibe Coding. ### Carpati Revisited **Itamar Friedman** [10:24] Notice what he's saying, like, code I actually and professionally care about contrasts Vibe Code. The same Carpati, okay? And it's really interesting, I think, to analyze what he's saying. The first thing he's saying, okay, code that I care about, probably heavy-duty software, or I like the quality, it's maintainable, we're going to get to that. And then he tries to offer a solution. I love him. I mean, like, I never met him, but we all saw his videos,right, like, 15 years ago, 10 years ago. So he's giving a solution, not only, like, being annoying, like, okay, no, I said Vibe Coding, no Vibe Coding anymore. So first he's saying, the first number one is context. He's saying, like, bring context. Here he's saying doing it manual, but that's not a game changer if now I need to start bringing it manually. And then he's giving also two, three, four, five, six, seven. Like, this is a workflow. He's actually suggesting a workflow. That's one of the topics of the three talks that we had now, okay? So now, like, this is really important, I think, like, how do you Vibe Code with Confidence? You need to, like, you say, like, just Vibe Coding, probably you don't care about cloud quality. You do care. You need to bring theright context and have workflows. And these workflows can be connected to agents, could be part of the agent, could be part of your flows. And that's what, like, in the nine minutes or so, some of the things I'm going to talk about. Carpati and others are not the only one. This is just, like, from a week ago, if you, you know, this very great person, great material. He's saying, like, AI coding tools are so much less useful on existing large code bases, okay? He's saying that, and this is differently than compared greenfield work. And it's not surprising because if you have a greenfield work, or it's a simple software, code generation is all you need, okay? Like, it's magnificent, the tip of the iceberg, give a prompt, you get your software. But when you're talking about enterprise heavy-duty software, then there's much more than that. We all know it,right? There is maintainability, testing, reviewing, etc. And shameless plug, well, I am the CEO of Qodo, I have to say, we are looking at that as a holistic, like, how can we really bring a game changer moment is if we look at all of this in a holistic approach. That's why we have a multi-agent architecture. I am not going to go over it one by one because there is one specific thing that I wanted to show. So we have a tool, we have an agent that is focused on, let's call it deep research, deep ask in code. ### Qodo Multi-Agent **Itamar Friedman** [12:53] And then we have a tool that is specific, that's our flagship for code review, called Qodo Merge. And then finally, we have, like, a tool that is inside IDEs that enables to shift left, like, bring that context, bring that best practices that were collected over time. The Qodo Merge tool, the Qodo Review tool collects best practices over time, and this is the context that is coming from the Qodo Aware and the best practices coming from Qodo Merge, helping you rather whatever code generation tool you're using, or using directly Qodo tool, to make sure that it's in high quality. But recently, like, 20 minutes ago, we released also a CLI tool. And that is meant to help you with the workflow parts. The workflow is already integrated into our solution, but this, like, really a workflow on steroids. There's another thing very important that is coming out in two months, and stay tuned, follow us, whatever, any platform that you want. I kind of, like, didn't want to show itright now. So CLI tool, why? I hope, like, I gave enough, like, hints and so far. And the main reason is putting AI to work across the SDLC, and I remind you that starting five minutes ago, you can go download it and play with it. It's a soft launch. We're going to announce about it more deeply, like, in a couple of weeks. So interestingly, who saw Simon's, like, talk? Like, he's magnificent. What? Some people didn't? Okay. So please go, go out of the room, I mean, and then come back after and watch online later. And it's amazing, like, when he wanted to demonstrate something, did he open, like, one of the IDEs? He did not. Like, everything he did was with a CLI tool. Like, that's, if you're a developer, like, that's the idea that you can run it in the background, you can run it in different workflows, you can make workflows. That's part of what I'm going to show you. And basically, with Qodo, the CLI tool, which is live here, then I can, for example, chat with it. And very interestingly, that is quite, like, there are a few tools that we talked about before that you can do that. ### Live Demo **Itamar Friedman** [15:05] But interestingly, you can call agents. For example, I can call the explain agent. It's a dedicated agent. Due to lack of time, I'm not going to show that. I'm going to show something else. So how did we made this explain agent? You can actually, with Qodo, the agent, you can make other agents. And soon I'm going to show you how you also create workflows and things like that. So basically, I can go and ask it, if the internet works well enough, you can go and ask it, please create an agent with this goal. And by the way, you can, like, give much more information than what I'm doingright now. I'm asking for it to create a review agent, okay? If then it works, it's going to start working. It's initializing MCP, it's going to search what it can do, what it cannot do. And now it's going to work for a few minutes, okay? Like, if I would ask you to do it, you would do it, take it in two hours. So let's give it two minutes. Meanwhile, I'm going to progress and tell you that I think one of the interesting things about it, it's working. So one, most agents, like, I can't think of one that won't, would have tools. For example, the Qodo Cover agent, by the way, we have an open source for Qodo Cover. It's a tool that automatically generates coverage. It increases the coverage, automatically increases coverage. But you don't need anymore to go download this open source, etc. You just get it as part of, as one of the agent, okay? So, but if you do want to play with the open source, etc., it's fully open source, okay? Back to my point, I can go and call Qodo Cover, which uses different tools. For example, it uses tools related to coverage reports. And I can look what I can do in a command line. I can tell it, dump all the logs somewhere,right? How do you do that with an IDE plugin? You can, but you need to hack it. Hack it. But the interesting thing, what can we do with command lines? And many here are developers. You can pipe, you can pipe tools together, agents. You can pipe, like, workflows, etc. So I want to run Qodo Code, generating code. I don't want to run the cover that, like, you know, increase the coverage testing. Maybe the code will generate a few tests, but I have an agent that is specializing in increasing coverage. And then I want a review agent that is now cooking and finished. And I'll go back to it in a minute if I have time. Now, this is not no agent or agent communication. I did a pipeline that just passed a result. But what if we can, and before I exemplified with MCP, but what if we can invent a command line for A2A? So those agents will run in parallel as you go, and they will have some communication between them. So I actually have to say that yesterday we had, like, 50 people, like, those that you had, speakers, and I asked who is using A2A, no one is using it. So it's still a way to go, but this is an example. Oh, yes, come talk to me later, so I'll know one person. Okay, thank you. So, and then I'll edit all the posts. I know one person. And, but we're getting there, okay? This is an example. You need multiple agents. You need A2A, you would want to use it if you want discoverability between agents or handshakes. So this is a good example if you have many agents, and you can run them in the background, etc. So in this case, the agent finished, and I have the definition, I have the definition of the agent over here. It's called Merge Agent, and you can see, like, all everything, the instruction that was made for it, like, what tools it is using. I'm going to add one that sometime I want to be very clear it's there. And by the way, it also has, like, an output scheme. I'm going to remove that, move that for a second, okay? And then I can go back and just call it, it was called Merge Review. Qodo Merge Review Agent, it was just generated a minute ago, and it will review. I didn't give it any, you see that there's a parameter automatically created, like, that I can tell it what to review, etc. Give instruction, it's very flexible, but I didn't. Okay, so I'm almost stuck of time, so I won't show you, but what I just will tell you that basically I can tell it to use best practices from the organization, important for Vibe Coding with Confidence, and I can also tell it to have some success or failure criteria, to know that something happened well or not. For example, if it managed to get some coverage, okay? That's how you work with Confidence. Yeah, and you can connect things to pre-commit, post-commit, okay? Everything you can do, you can do automatically. Very interestingly, and with that, almost reached the end, very, very interestingly, you can say the CLI tool is very lame. But notice, did you notice what Simon did? He used the CLI, but eventually checking content, he used different interfaces. So you can, from the CLI itself, automatically generate interfaces that are fitting for your task. And one of those, for example, is an interface for code review. ### Swarm of Agents **Itamar Friedman** [20:25] So who cares anymore about IDEs when you can have flexible IDEs? And with that, I'll finish, and I'll just tell you that I think we're going into a future where we're going to have swarm of agents, each one specializing and having different credentials, different best practices, etc. And it's coming really fast, 2025, 2026. Thank you. --- This library is powered by PodHood (https://podhood.com), the podcast website platform.