back to indexVibe Coding with Confidence — Itamar Friedman, Qodo

Chapters
0:0 The Evolution of AI in Development
3:8 The Rise of the Command Line Interface (CLI)
3:50 AI Across the Software Development Life Cycle (SDLC)
6:40 The Importance of "Vibe Coding with Confidence"
8:15 The Role of Workflows and Agents
12:21 Qodo's Multi-Agent Approach
13:55 Why the CLI is the Future of AI in Development
20:33 The Future: A "Swarm of Agents"
00:00:00.000 |
Okay, so my name is Itamar Friedman, CEO and co-founder of Codo, and I'm going to talk about, 00:00:19.640 |
yeah, Vibe Coding, but more on the confidence part, and why, this is maybe surprising, why CLI 00:00:26.320 |
might be the new interface leader for that, and we are soft launching a CLI tool right now, 00:00:33.760 |
five minutes ago, so you can go and install it, it's soft launch, play with it, give us feedback, 00:00:40.080 |
there is some capacity, and in order to verify who is in the audience, just like if you can tell me if 00:00:46.160 |
you tried Cloud Code or Codec CLI, okay, and I guess if I ask about AIDEs, you would also do that, 00:00:54.880 |
right, and the question is why, and I'm going to talk about it a bit, okay. So the agenda is that, 00:01:01.840 |
I'm actually going to really zoom out to the Gen 3.0, what do I mean by that, and from the autocomplete 00:01:08.400 |
to the multi-agent workflow, and workflows, you see it's a theme that's returning here, CLI is 00:01:14.480 |
something that can support that, and how do we believe that Codo is going to be the real shift in 00:01:20.320 |
software development, and like why is the CLI is the future, and you know, being able to do vibe coding 00:01:27.280 |
with confidence, and eventually I'm going to connect, do zoom out again, I'm going to zoom in, zoom out, 00:01:31.680 |
even with a demo, and connect the dots, and I will say what, explain a bit what is Codo, I didn't do it 00:01:38.240 |
right now, and we'll do it a bit later, but that's something I'm going to cover shortly. So AI for 00:01:45.120 |
developers, and I just think that most people here are developers according to the amount of hands that 00:01:50.960 |
were raised, so I think like we first got some tools that we liked, AI tools, then we got some tools that we 00:01:56.800 |
loved, and I'm not that sure that we actually get tools into our hands that completely become a game 00:02:05.600 |
changer for us. Okay, it's maybe unpopular opinion, I'm going to elaborate a bit, so in order to do that, 00:02:12.080 |
I'm going to differentiate developers between noobs and enterprise, it's a bit weird, like it's not 00:02:17.120 |
necessarily juniors, like there are juniors in enterprise, right, but still, you know, like let's use 00:02:23.200 |
that for a second, noobs versus enterprise, so I think gen 1.0 was the autocomplete moment, right, 00:02:30.000 |
we started being able to generate writing our code and getting a few lines ahead of us, we really liked 00:02:36.880 |
that, if you weren't a developer, like you couldn't really do more, right, so you needed to be a developer 00:02:42.720 |
already, and then came the gen 2.0, the chat, the agentic chat, and I think like we saw even junior 00:02:49.440 |
developers generating much more lines of code, maybe the seniors or the enterprise liked it, 00:02:54.640 |
but also had a lot of problems with it, they need to review much more code, not necessarily high quality 00:03:00.320 |
code, I hear that a lot, and I'm going to show you like 500 tweets about it, not really, but from some 00:03:07.280 |
opinion leaders, and I think that the game changer moment is when we will move from chat, agentic chat, 00:03:13.760 |
to actually being able to, and as a spoiler, command, command line interface, to give commands to our 00:03:21.600 |
agents as if they're like team members, and they do end-to-end flow, what is an end-to-end flow is 00:03:27.040 |
something I'm going to talk about a bit, and I think like you will see different players and different 00:03:32.160 |
parts of this map, like I mean different tools, let's think about it again, so I think like in the 00:03:38.560 |
an autocomplete moment, we saw first ID plugins, again it's not a game changer, I'm just like going 00:03:43.120 |
to complete more lines of code for you, we liked it, and then let's rethink how we do coding inside 00:03:50.960 |
ID, so we saw ID forks, and then what's the third wave, sometimes I hear forking people, I didn't say that, 00:03:58.560 |
what I think is actually we're going to see is like AI across the STLC, okay, like being able to 00:04:05.120 |
do end-to-end flows that are specific, closing a task that is specific in the STLC, but more importantly, 00:04:14.080 |
using AI across the STLC, again, not only in the ID, hence, how do we do that, command line, right, 00:04:21.040 |
it's one of those tools, a lot of spoilers, so I think when we had the aha moment with the 00:04:27.600 |
autocomplete, the next aha moment was, you know, all the hype around vibe coding, and I'm going to touch 00:04:32.800 |
about that, and I think the next thing that I think we're going to hear about is like, hey, I'm really 00:04:38.800 |
doing 100x, choose a number, 10x, 50x, 100x development, and I'm doing that with confidence, 00:04:46.160 |
not just like vibing through it, I think that will be a game changer moment for us, it means that we 00:04:52.880 |
totally broke the way we work, we're going to get to that, so I think like, I differentiated between, 00:04:58.640 |
I separated between noobs and enterprise, for example, I think for noobs, it means end-to-end means, 00:05:03.280 |
for example, that you prompt and get a software, a fully managed software for you, right, we, I guess 00:05:08.800 |
we're all playing with, even if you're a developer, you're doing some POVs, or some side, or being able 00:05:13.920 |
to do some simple games, but then in the enterprise setup, in the heavy-duty setup, then basically, 00:05:20.240 |
what means for us, like, AI cross-desk, you'll see as reliable, versatile workflows, and when I say 00:05:26.240 |
workflows, we had a few sessions, amazing sessions, I'm actually, like, combining them, which is one of the 00:05:31.520 |
points that were made there, like, I think a child made a point where an agent is creating workflows and 00:05:38.640 |
calling them, and then there was a discussion about, like, workflows and, you know, using agent, 00:05:43.440 |
et cetera, so I'm, when I say workflows, I already mean agentic workflow, let's, let's move on, like, 00:05:48.800 |
workflow, agent, who cares, like, like, so it's going to be combined, and I think, like, in order to do that 00:05:54.640 |
with trust, you need to be able, more importantly, is to have workflows or agents that are related to trust, 00:06:02.240 |
for example, having really high-quality reviewing capabilities, really high-quality testing 00:06:08.000 |
capabilities, being able to do a variety of jobs to be done that we do as developers in end-to-end-ish 00:06:14.800 |
and high-quality, so that will be a game-changer. Let's be a bit more specific. As developers, 00:06:20.480 |
we do a lot of things, not just write code. I took, like, four parts, which is, like, I think less than 00:06:25.280 |
a half of what we do, and I think, like, basically, vibe coding was very focused on, let's, like, do 00:06:32.000 |
initial planning and write code fast, like, and, you know, vibe, whatever we get, like, that implementation 00:06:38.720 |
or that, we feel it and move on, but actually, in heavy-duty software, we need to do many other things. 00:06:45.520 |
We need to do, for example, bug fixing, or we need to do refactoring and changing features, etc. 00:06:52.160 |
We want to move fast without breaking things, so I think we need to have not the testing and the writing as 00:06:57.520 |
a hand site, which you can do, like, testing and reviewing inside ID tools that are very mature, but not as a hand site, 00:07:06.160 |
but rather, like, really being the red team, right, thinking as a tech lead, as reviewing code and having, 00:07:13.360 |
like, fitting technology for that, so if we are able to put, like, AI in each one of those, like, parts, 00:07:21.680 |
maybe then it will be a game-changer, but I think even then, like, we already have tools for code review, 00:07:28.160 |
for testing, shameless plug, we're going to talk about later, that's what we do at Codo. We focus being more 00:07:33.040 |
on the red team, even though we have tools for the blue, we are focused more on the red team, 00:07:35.920 |
more on the red team. Still, I don't think it's a game-changer, okay, and I think, like, a first, 00:07:40.640 |
like, a feeling of a game-changer, as I mentioned, not only putting AI across the SDLC, but having 00:07:46.800 |
workflows across parts of the SDLC, so one semi-game-changer could be, like, if we manage to 00:07:54.000 |
shift left the review and the testing, as you write code, then you also get those suggestions and get 00:07:59.840 |
high-quality code that is already according to your company best practices, and you don't need to wait 00:08:05.360 |
for the AI review tool to tell you that only after you pushed it, right? But I think, like, I think we have 00:08:12.080 |
even a better way to do that, a bit more agentic, so let's reanalyze these four blocks, these four tasks, 00:08:18.560 |
these four tasks, so I, instead of having one, like, the x-axis, now there's also y-axis, it's 00:08:25.200 |
executability. If you know the v-shape in Wikipedia or whatever, where we're searching now, chat GPT, 00:08:30.640 |
v-shape, software development, y-axis executability, x-axis time, so we start with planning, it's not 00:08:36.720 |
executable, then we write code, in most cases, you're not doing admitted like a TDD, okay? So you write, 00:08:42.560 |
you write your code, and then you write your test, and in most cases, and that's executable, 00:08:47.600 |
but it's not application code, so it's a bit higher, and then, and then you do the review. 00:08:51.280 |
A game changer is, like, when we actually manage to take that v and squeeze it, and, and have, like, 00:08:58.240 |
different workflows and agents talking to each other, and that's why, like, I had the word MCP and A2A, 00:09:03.680 |
and I'm gonna get to that later, I, I, I guess, like, if you're in this conference, you know what I'm 00:09:08.000 |
talking about, that where maybe there's different agents that are talking to each other, maybe it's 00:09:11.920 |
one agent using tools that are able to connect all of these, like, all at once, that, that will be a 00:09:17.120 |
game changer. So to, and to some extent, what it means is that, that, like, the game changer moment is 00:09:23.680 |
when we're looking at all of these steps, like, rigorously, and, and one holistic solution. If you like, 00:09:29.520 |
cloud is, is mature for 10 years, and then Wiz came and said, we can't put in a security application for 00:09:37.040 |
each part of the cloud, like, or each, uh, necessity of, of security. Let's build one holistic, uh, solution 00:09:44.160 |
for, for, for cloud security. The same thing will happen to us in the game changing moment for, for, uh, 00:09:49.280 |
intelligent software development. Zooming out back again to vibe coding with confidence, uh, it, it didn't 00:09:56.480 |
happen a long time ago when Karpathy wrote about vibe coding, like, you know, really, like, I thought it's like a decade 00:10:02.880 |
already in AI, uh, years, uh, and, and the interesting thing, it didn't take too much time, like, a month or two, 00:10:09.200 |
uh, where, where we started, where, where we started seeing pushbacks, right? This is not me, by the way. 00:10:15.440 |
Uh, and, and, uh, and, and actually just a few weeks ago, the same Karpathy came back 00:10:22.160 |
and rethought vibe coding. Notice what he's saying, like, code I actually and professionally care about 00:10:28.320 |
contrast vibe code. The same Karpathy, okay? And it's really interesting, I think, to analyze what he's 00:10:34.160 |
saying. The first thing he's saying, okay, coded I care about, probably have a duty software, or I like 00:10:39.360 |
the quality, it's maintainable. We are gonna get to that. And then he tries to offer solution. I, uh, 00:10:45.280 |
I love him. I, I, I mean, like, I never met him, but, but, uh, we all saw his videos, right? Like, 00:10:49.360 |
15 years ago, 10 years ago. So, uh, he's giving solution, not only, like, uh, like, being annoying, 00:10:54.800 |
like, okay, no, I said by coding, no by coding anymore. So, first he's saying, the first number one is, 00:10:59.680 |
is context. He's saying, like, bring context. Here, he's saying doing it manual, but that's not game 00:11:05.600 |
changer if now I need to start bringing it manually. And then he's giving also two, three, 00:11:10.160 |
four, five, six, seven. Like, this, this is a workflow. He's actually suggesting a workflow. 00:11:15.680 |
That's one of the topics of the three talks that we had now, okay? So, now, uh, like, this is really 00:11:22.000 |
important, I think. Like, how do you vibe code with confidence? You need to, like, you said, it's like, 00:11:27.360 |
just vibe coding, probably you don't care about quality. You do care. You need to bring the right 00:11:31.840 |
context and have workflows. And these workflows can be connected to agents, could be part of the agent, 00:11:37.440 |
could be part of your flows. And that's, like, in the nine minutes or so, some, some things I'm going 00:11:41.680 |
to talk about. Karpati and others are not the only one. This is just, like, from a week ago, uh, if you, 00:11:46.960 |
you know, this, uh, a very, uh, great, great person, great material. He's saying, like, AI coding tools are 00:11:53.440 |
so much less useful on existing large code bases, okay? He's saying that, and, and this is differently 00:12:01.120 |
than compared green for greenfield work. And it's not surprising because if you have a greenfield work 00:12:06.480 |
or it's a simple software, code generation is all you need, okay? Like, it's magnificent, 00:12:12.320 |
the tip of the iceberg, give a prompt, you get your software. But when you're talking about enterprise, 00:12:18.160 |
heavy-duty software, then there's much more than that. We all know it, right? There is a maintainability, 00:12:22.720 |
testing, reviewing, et cetera. And shameless plug, well, I am the CEO of Koto, I have to say, 00:12:27.680 |
we are looking at that as a holistic, like, how could we really bring a game-changer moment as if we 00:12:33.120 |
look at all of this at a holistic approach? That's why, uh, we have a multi-agent, uh, architecture. 00:12:40.000 |
I am not going to go over it one by one because there's one specific thing that I wanted to show. 00:12:45.360 |
So, we have, uh, a tool, we have an agent that is focused on, let's call it deep research, deep ask, 00:12:52.000 |
in code. And then, uh, we have a tool that is specific, that's our flagship for, for code review, 00:12:58.160 |
called code merge. And then, finally, we have, uh, like, a tool that is inside IDEs that enable to shift 00:13:06.160 |
left, like, bring that context, bring that, uh, bring that best, best practices that were collected 00:13:12.400 |
over time. The code merge tool, the code review tool collects best practices over time. And this, 00:13:17.600 |
the context that is coming from the code aware and the best practices coming for code merge, 00:13:22.480 |
helping you rather whatever code generation tool you're using or using directly code tool to make 00:13:28.480 |
sure that that's in high quality. But recently, like 20 minutes ago, uh, we released also a CLI tool. 00:13:37.760 |
And that is meant to help you with the workflow parts. The workflow is already integrated into our 00:13:43.360 |
solution, but this, like, really, uh, a workflow on steroids. There's another thing very important 00:13:49.600 |
that is coming out in two months, and stay tuned, follow us, whatever, any platform that you want. I 00:13:55.360 |
kind of, like, uh, didn't want to show it right now. So, CLI tool, why? I hope, like, I gave enough, 00:14:00.880 |
like, hints, um, and, uh, so far. And the main reason is putting AI to work across the CLC. And I remind 00:14:07.680 |
you that starting five minutes ago, you can go download it and play with it. It's a soft launch. Uh, 00:14:12.400 |
we're going to announce about it more deeply, like, in, in, in a couple of weeks. So, interestingly, who, 00:14:17.440 |
who, who saw Simon, like, uh, talk, like, he's magnificent? What? Some people didn't? Okay. So, 00:14:23.360 |
please go, uh, go out of the room, I mean. And, uh, and then come back after and watch, uh, online later. 00:14:30.240 |
And it's amazing, like, when he wanted to demonstrate something, did he open, like, one of the IDEs? 00:14:35.760 |
He did not. Like, everything he did was with, with a CLI tool. Like, that's, if you are a developer, 00:14:42.800 |
like, that's the idea that you can run it in the background, you can run it in different workflows, 00:14:46.640 |
you can make workflows. That's part of what I'm, what I'm going to show you. And, and basically, 00:14:51.600 |
with, with Codo, uh, the CLI tool, which is live, uh, live here, uh, then I can, for example, chat with 00:14:58.960 |
it. And very interestingly, that is very, quite, like, there are a few tools that we talked about 00:15:03.680 |
before that you can do that. But interestingly, you can call agents. For example, I can call the, 00:15:08.320 |
the explain agent. It's a dedicated agent. Uh, due to lack of time, I'm not going to show that. I'm going 00:15:13.360 |
to show something else. So, how does, how did we made this explain agent? You can actually, 00:15:19.040 |
with Codo the agent, you can make other agents. And soon, I'm going to show you how you also create 00:15:24.960 |
workflows and things like that. So, basically, I can go and ask it, if the internet works, uh, well 00:15:30.320 |
enough, uh, you can go and ask it, please create an agent with this goal. And, and by the way, you can, 00:15:36.240 |
uh, uh, uh, like, give much more information than what I'm doing right now. I'm asking for it to 00:15:41.840 |
create a review agent. Okay? If the internet works, it's, it's going to start working. It's initializing 00:15:48.000 |
MCP. It's going to search what it can do, what it cannot do. And now it's, it's going to work for, 00:15:52.880 |
for a few minutes. Okay? Like, if I would ask you to do it, you would do it, take it in two hours. So, 00:15:56.720 |
let's give it two minutes. Meanwhile, I'm going to, to progress and, and, uh, and tell you that the, 00:16:02.960 |
I think one of the interesting things, uh, about it, it's, it's working. So, one, uh, most agents, 00:16:09.280 |
like, I can't think of, of, of, of one that won't, would have tools. Uh, for example, 00:16:15.200 |
the Kodo cover agent, uh, by the way, we have an open source for Kodo cover. Uh, it's a tool that 00:16:21.360 |
automatically, uh, generates coverage, coverage, uh, it increases the coverage, automatically 00:16:27.920 |
increases coverage, but you don't need anymore to go download this open source, et cetera. 00:16:32.320 |
You just get it as part of the, uh, uh, as one of the agent. Okay? So, uh, but if you do want 00:16:38.480 |
to play with the open source, et cetera, it's, it's fully open source. Okay. Back, back to my point, 00:16:43.360 |
I can go and call Kodo cover, which uses different tools. For example, it uses tools related to coverage 00:16:48.080 |
reports. Uh, and, and you, I can look what I can do in a command line. I can tell it dump all the logs 00:16:53.440 |
somewhere, right? How do you do that with an ID plugin? You can, but you need to hack it, hack it. But 00:16:59.200 |
the interesting thing, what can we do with command lines? And many here are, are developers. You can 00:17:03.840 |
pipe, you can pipe, uh, uh, tools together. Agents, you can pipe, like, uh, uh, uh, workflows, et cetera. 00:17:11.200 |
So I want to run Kodo code, generating code. And then I want to run the cover that, like, you know, 00:17:15.920 |
increase the coverage testing. Maybe the code will generate a few tests, but I have an agent that is 00:17:21.040 |
that is specializing in increasing coverage. And then I want the review agent that is now cooking 00:17:25.840 |
and finished. Uh, um, and I'll go back to it in a minute if I have time. Now, this is not no agent 00:17:32.560 |
to engine communication. I did a pipeline that just passed the result, but what if we can, and, and, and, 00:17:37.920 |
and before I exemplified with MCP, but what if we can invent a command line for A to A? So those agents are, 00:17:45.440 |
uh, uh, will run in parallel as you go and they will have some communication, uh, between them. 00:17:51.440 |
So I actually have to say that yesterday we had like a 20, uh, 50, uh, like people like, like those that you had, 00:17:57.440 |
uh, we, uh, uh, speakers and I asked who is using A to A? No one is using it. So it's still a way to go, 00:18:04.800 |
but this is an example. Oh, yes. Come to talk to me later. So I will know one person. Okay. Thank you. So, uh, uh, uh, 00:18:12.000 |
and then I'll edit all the posts. Uh, I know one person and, and, uh, and, and, and, but, but we're getting there. 00:18:17.520 |
Okay. This is an example. You need multiple agents. You need A to A. You, you would want to use it if you 00:18:22.560 |
want discover, discoverability between agents or handshakes. So this is a good example if you have many agents 00:18:28.960 |
and you can run them in the background, et cetera. So in this case, the agent finished and I have the definition. 00:18:34.480 |
Uh, I have the definition of the, of the agent, uh, over, over here. Uh, it's called merge agent and you 00:18:41.440 |
can see like, like all everything, the instruction that was made for it, uh, like what tools it is, 00:18:47.520 |
it is using. Uh, I'm going to add one that, uh, sometime I want to be very clear. It's there. 00:18:52.480 |
And by the way, it also has like a, uh, output scheme. I'm going to remove that, move that for a second. 00:18:58.800 |
Okay. And then I can go back, uh, and, and just call it, it was called merge review, uh, 00:19:05.760 |
Kodo merge, uh, review agent. It was just generated a minute ago and it will review. I didn't give it 00:19:13.280 |
any, you see that there's a parameter automatically created like, uh, uh, that, that, uh, uh, I, I can 00:19:19.840 |
tell it what to review, et cetera, give instruction. It's very flexible, but I didn't. Uh, okay. So, uh, 00:19:25.280 |
I'm almost lack of time, so I won't, uh, show you, but what I just will tell you that basically 00:19:30.320 |
I can tell it to use best practices from the organization important for vibe coding with 00:19:34.800 |
confidence. And I can also tell it to have some success or, or, or failure criteria to know that 00:19:41.360 |
something happened well or not. For example, if it managed to get some coverage, okay, that's how you 00:19:46.160 |
work with, with confidence. Um, yeah. And you can connect things to pre-commit, 00:19:51.840 |
post commit, okay. And everything you can do, you can do automatically. Very interestingly, 00:19:56.800 |
and, and with that, uh, almost reached the end, very, very interestingly, you can say the CLI tool 00:20:02.800 |
is very lame. But notice, did you notice what, what Simon did? He used the CLI, but eventually 00:20:10.080 |
checking content, he, he used different interfaces. So, you can, from the CLI itself, automatically generate 00:20:17.760 |
interfaces that are fitting for your task. And one of those, for example, is an interface for, 00:20:23.360 |
for code review. So, who cares anymore about IDEs when you can have flexible IDs? And with that, 00:20:29.760 |
I'll finish, and I'll just tell you that I think we're going into a future where we're going to have 00:20:34.080 |
swarm of agents, each one specializing and having different credential, different, uh, best, best practices, 00:20:40.560 |
etc. And, uh, and, and, and it's coming really fast, 2025, 2026. Thank you.