# AI Code Flood: ROI, Quality, and Context

**Podcast:** Dev Interrupted
**Published:** 2026-06-16

## Transcript

Welcome to Dev Interrupted by Linear B.
Today, we're doing something really awesome.
We've got both Linear B founders in the room with us.
We have Ori Karin, CEO and co-founder, and Dan Lines, COO and co-founder.
Yeah, Ori, Dan, welcome to the show.
Hey, great to be here.
Thanks for having us.
Thanks, BLP.
Now, the reason that the four of us are all in one discussion is because Linear B has been moving really fast all year.
And all four of us, we have a lot to say about it, especially you two, and about where the industry is going and what our company has been working on, but also the opportunities that you see for everybody right now in the industry.
Because something that we all talk about a lot on the show is making predictions and understandings about where the industry is going, because that's the insights that we get to work with here at Linear B.
And so I'm really excited to dig in to some of the stuff that y'all been learning.
And I actually just want to kick it off Ori by.
Giving the first question to you, because when we talked with you at the top of the year, you predicted that organizations, they would struggle to digest all of this AI-generated code.
We'd be under a delusion, a flood of all of this new AI-generated content that teams are going to struggle with.
And I want to check in with you now that we're about midway through the year.
How do you feel about that prediction?
Do you think it's coming true?
What do you see?
Yeah, I think, by the way, even a year ago, I said something like productivity will actually dip and then it will start rising.
And I think this time, yeah, people will start.
Yeah, we're definitely seeing it.
I think data-wise, our data is showing, and it's also backed by, you can read a lot of other research and other papers, that there's around 2x more pull-width throughput.
So more code is actually hitting the pipes.
But yeah, definitely teams are swamped because there's not enough people to review the code.
There's not enough people to test the code.
There's not enough people to handle the releases.
Organizations are actually saying, yeah, we're generating 2x more code, but the gains that we're getting are actually...
somewhere between 10 to 15% of productivity, even if you ask them qualitative or even if you measure something.
And I'm not even talking about the fact that quality has degraded a little bit.
People are reporting more failures.
So yeah, I think it's definitely what's happening.
Yeah, code generation is faster, but the rest of the pipes and the rest of the operations that need to support shipping software faster are still not there.
Yeah, most companies are still in this productivity pain point that you called out last year, you called out again this year.
We're still suffering through understanding how to actually make sense and gain all of the productivity you can from these tools.
Exactly.
Yeah.
And we've been covering here on Dev Interrupted a lot how we're in this messy middle of AI and adoption and success with it has been very lumpy.
Some teams, some organizations see really great successes with it and they learn how to replicate that across their organization.
Whereas others maybe only see tiny pockets of these improvements.
And meanwhile, the rest of the company maybe is actually starting to look worse over time because of AI.
So, Dan, I'm curious to hear from you on this.
What are you hearing from our customers and the engineering leaders that we talk to every day about how AI is reshaping their challenges and what they're coming to Linear B to solve?
Has the concerns changed or have they just gotten bigger as AI has ramped up?
Yeah, man.
Great question.
I mean, first, we got to start with what kind of customers are we talking to?
So when I'm talking to customers, when Linear B is talking to customers, these are the best companies in the world.
These are like Fortune 500, Fortune 1000 companies.
These companies are dominating markets right now.
And so what they're going through is more so this transformation from their SDLC to their ADLC.
And I think the difference, at least from what I see from the beginning of the year, beginning of the year was like...
Still a lot of hype, still a lot of experimentation, things like that.
Okay, we're trying it in some pockets.
Okay, all of our developers are using something, co-pilot, claw, this is fun.
It's transformed now.
What I'm hearing is let's get back to business.
Let's get back to results.
I need ROI for the business.
So there's three things that they're saying to me.
Thing number one, trust and proof.
Ori mentioned it, with quality.
They're on their journey to full autonomy, But they need to see, can I really release this code to prod?
Are the floodgates going to open here?
Am I ready for that?
I'm not fully ready.
I need quality.
So I hear a lot.
Quality, quality, quality.
That's number one.
Number two, what I hear.
I think we're going to talk about it more.
Cost versus ROI.
This stuff's not cheap anymore.
It's not going to stay cheap, right?
We're all hearing the reports.
It's going to be expensive.
So now they're saying, okay, I got to make sure that my cost is intact.
When we're working with these agents, that's number two.
And then the third thing I'm hearing, and we can break it down, but they're almost dissecting their SDLC.
They know they need to get to this AI DLC, this ADLC.
They're almost dissecting it.
They're saying, okay, I got these assisted coding agents.
Maybe I have some full autonomous.
But what's my specs like?
Is that AI driven?
Or where's my bottleneck before it was like the code review?
So they're kind of like, how do we deploy it?
So they're kind of breaking down each part of their SDLC and saying, okay, this is what I need to transform.
I need to unlock all these bottlenecks.
So it's shifted a lot, man.
It's pretty crazy what's happening, but it's really exciting.
Yeah.
And you hit on a couple of points that I want to just double click on for a minute.
And that is, you mentioned quality.
And I've been looking into the data on this a little bit, you know, just from our own customer base.
And like, it looks like things like rework are just like plummeting at this point as one example of where, you know, AI is, it tends to default to generating new code rather than trying to rework an existing system.
And refactoring is kind of similar.
And again, it just depends greatly on how you look at how you slice the data, you know, because across the industry, we can see the broader trend.
at the micro level when you look at individual companies there's there's so many outliers where they they've just like there's clearly major problems that are being introduced into their their sdlc um and then yeah on cost we've been we've been covering here a lot how usage costs are exploding right now github copilot just changed to a fully usage-based pricing system i think that's going to be the norm for most developer tooling and you know we can't just keep spending and limitless amounts of tokens, you know, because it's going to make costs just go out of control.
So yeah, I think those are really two big things that like, it's the elephant in the room.
We all have to be talking about those things.
The bill is coming due.
The bill is coming.
I talk about this so much on the show and I feel like a broken record that like this cost of using these tokens is only going to go up.
Your ability to learn and figure out where those bottlenecks are will never be more subsidized than it is right now.
It's so funny.
This is probably going to make me sound old.
Do you remember when it switched from cable TV to these streaming services?
Oh, yeah.
And it was super cheap.
It was like, oh, okay, your cable bill was like $250.
Now it's like $19.99 a year.
The bill has come due.
How many streaming services do you have?
It's like $500 a year.
Now that's how I feel about what's happening here.
It's exactly what's happening.
It's like they're subsidizing it, they're bringing in low, so we're incentivized to reinvent and blow up all of our process and get it in there really deep just for them to hike up the price.
But also that's the reality of...
understanding the intelligence capabilities that you're drawing down, the costs of them, when to use certain models over others, when to choose to use your own local models.
These are all really high-level AI fluency, AI hygiene conversations that companies are having right now.
But since we did just have this whole year, year and a half of like...
really heavily subsidized AI cogen, you got these teams that really went at break speed and hit these bottlenecks and found new bottlenecks in their cogeneration process.
And like, for example, in our 2026 benchmarks, like it shows that agentic AI pool requests, you know, they wait five times longer to get picked up and they get...
merged at less than half the rate at the human authored ones, which points at a major gap in the code review process.
And that creating the code is only one small step of actually getting it to deliver value to customers.
And because folks are...
contending with that uncomfortable reality of like, oh, there's bigger problems in my code base than just getting the code into existence.
You know, I'm curious to know from you, Ori, like, how have you seen teams handle these shifts in their bottlenecks?
Have there been other bottlenecks that have been really prominent for you to think about as like a leader in the space?
Yeah, so first of all, I think this is super interesting.
I think there are two problems.
We talked about the flood of code.
And like you said, it was very cheap.
Not going to be cheap anymore.
But it was very cheap in the last year.
So think about a lot of code is hitting the system.
What I'm seeing and what I'm hearing when I'm talking to customers, and then spoke about it depends on what type of customer you are.
But what I'm seeing is that not all the companies are ready.
to say, okay, I generated the code.
Let's do an AI-based review and figure out what's happening with that change downstream and let it maybe go out.
The universe is not ready for that yet.
Maybe some companies are doing that.
So what's happening right now is that senior developers across all companies are swamped.
They are tired.
They're underwater.
They need to read all this code and approve all these changes.
So I'm actually very concerned for two things.
One, what's going to be something that solves this?
And the second thing is, how do you not get into a situation where a lot of knowledge is lost?
Because those senior developers are the people that know, they have good understanding, good grasp of, okay, this service might be in risk.
you know, this tribal knowledge of where things could be broken.
So you deploy them now, like, to just review all these codes so we can make sure we ship things faster.
And then we say to the organization, yeah, yeah, we are moving faster.
So you lose them as knowledge centers.
You don't grow the next, what we call, like, senior developers.
That's, like, a high concern that I'm hearing from a lot of companies.
And, yeah, you talked about, like...
the fully agentic pull request, it's still the same old problem.
Like if an agent wrote a quote, who's going to tap on someone's shoulder?
Hey, can you please look at my PR because I need to get my feature delivered?
Nobody does that.
So the ownership problem is huge.
How do you solve for that problem is also big.
I guess junior developer is the best job in the world now.
Let me just create all this code and give it to the senior developers to burn them out.
They have all the context.
They know all the intricacies of the system.
Yeah.
And we don't want to burn out our senior developers.
That sucks.
And I wonder, the thought that I have then is like, when will junior developers will become senior developers?
Because maybe this event won't happen anymore.
It's like.
It's super risky.
What makes a senior developer?
I think you said that they have the context.
They know all the areas of the system.
They know the architecture.
They know where the skeletons lie.
I guess that's one aspect.
I don't know.
Yeah, that's a great question to ponder.
I don't know what the future is for junior developers, but they're probably, if I was a junior developer, be going like...
You have to almost all agentic.
That's where your value lies.
I don't know if they'll evolve.
Let's see.
But yeah, that's also like another thing that you guys spoke about before.
Like I think organization know how to deploy AI now very strongly to greenfield.
To like, okay, if I have to build new stuff, I'm actually obsessed about success stories of companies who we factor like beef.
chunks, like being monolith and what did they do to get there.
And when companies are successful with that, that's like, I think opens up like a true like new level of productivity.
I'm obsessed with these stories.
Whenever I like ran into one of these, like I want to understand what did they do.
Usually it's like a lot of tests like to hold, make sure everything is working.
But then I'm hearing stories about projects that they thought are going to cost eight many years that they do now in two, three months, which this part is amazing.
That part is amazing.
The way that like huge pre-existing companies can transform their brownfield code bases using AI and perform things that were always sitting on a back burner, like really important security migrations and system updates and even just like refactoring stuff that's been sitting in a closet for a decade.
I think whenever like a company is able to.
have success using AI at scale relatively autonomously, like they come in and it's doing its thing, is really impressive.
Because that speaks to that they were able to distill their domain expertise and what matters to them as engineers into a loop that is able to do something end-to-end for them effectively.
And that's way, way, way more impressive, I think, than people that are going out there and building.
you know, brand new Greenfield things as exciting and as cool and as big as the opportunities will be for those in the future.
It's much more exciting for me from an engineering standpoint to think about how those big pre-existing teams with those old, you know, built up cruft kind of applications managed to become agentic, managed to transform with the technology.
Because Ori, to your point, the catalyst between becoming a junior engineer and a senior engineer is going to be really blurry.
That's what a senior engineer has, to your point, Dan.
It's like they know where the skeletons are.
And you only know where skeletons are by thinking about the problems a lot, being in it and being a part of the process.
And the more abstracted that junior devs are from that process and never get close to it, the less opportunities they're going to have to grow into those senior developers.
So this is also too like...
personnel and like kind of like how you go about organizing your team's thing as well.
Like AI is not just code.
It impacts your team and its shape as well.
100%.
If your AI bill went up this year, but you can't show what it bought, this one's for you.
Andrew and I are hosting a live workshop, Life Beyond Token Maxing, AI efficiency for the long term.
We'll get into why token counts fall flat in executive conversations.
where AI is moving the bottlenecks in your pipeline, and how the APEX framework builds on existing productivity metrics frameworks to measure what matters in the AI era.
Everyone who registers for the event gets early access to our new guide on measuring efficiency in the AI-driven SDLC and controlling the executive conversation around these discussions.
The link is in the show notes.
Come hang out with us on June 25th.
So we've been talking about cost a lot so far.
And, you know, one thing that we've seen from some of the data that we've collected is that it's still a big challenge for engineering leaders to translate those costs into ROI and impact on the organization.
So, Dan, I want to give this question to you.
You know, as we're seeing AI, like, evolve and, you know, these organizations are maturing with it, you know, how are people justifying the investment today?
You know, because...
A year ago, it was like everyone was just thinking about adoption.
It's like we just want to get developers to use it.
It seems like adoption is basically universal at this point.
But now we need the next thing that shows that that adoption is actually driving something.
So what are you hearing?
Yeah, it's not just fun and games anymore.
It's not just that, hey, how many developers have adopted?
You know, that's like the first stage of the journey.
But like I was saying, and this is actually honestly what it was before AI.
It is going back to business value.
This cost is increasing so much that I have to say, as I'm having my developers use agents, I have to justify that the value being shipped to production, usually for our customers, could be the cost, like the debt reduction too.
I think that's like a good thing to use tokens on.
But it has to say, yes, it is increasing the amount of value that we're delivering.
Our cycle time is...
decreasing, the amount of incidents found in production is going down, our quality remains the same.
This is what the best engineering organizations are already proving.
I don't know if I want to jump too far ahead, BLP, but I saw a demo.
I saw a demo within Linear B where now we're able to show, okay, here's all of your agents.
Here's the cost of your agents.
Here's how they relate to the teams using them.
Here's how they relate.
I mean, this is what the customers are asking for.
All right.
So maybe we say like we're in this alpha beta stage.
I don't want to ruin the surprise.
This is what they need.
That's why we're building it.
Every single conversation is okay.
I got to justify this now.
Fun and games are over.
So that's what I'm super excited about for us.
And that's what I'm hearing the customers need and want.
Yeah.
And, you know, we've been talking a lot about how like the patterns of.
behavior are changing.
Like the way you do work is fundamentally changing, including for developers now.
And, you know, there's a new type, there's new stages in the life cycle of like a developer's day, right?
Like they, they create, they spend time creating a prompt and then there's some idle time while the agent is doing work.
And then there's, then the agent needs the human to come back and provide feedback.
And there might be idle time as it waits for, for the human, you know.
There's these whole new dynamics now that we've had to start thinking about because we can see that AI is just fundamentally changing how we get work done day to day.
It's funny.
I heard, I think, Ori, you might have told me, I've been hearing this.
There's almost like, okay, there's this classic outer loop, let's call it the outer loop, that's always existed.
And you can kind of frame that by, you know, Dorometrics, cycle time, MTDR.
That's like the outer loop.
And it's still very important, but there's like an inner loop now.
And that's what you describe, BLP.
There's like this inner loop of a gentic circle that's happened.
It's like, is my agent running?
How long did it run?
Oh, did it get stuck?
There's something that's changed there with this inner loop that I think is really interesting maybe to touch on here.
Yeah.
And I'm curious, you know, because we meet a lot of companies that are just sort of at all stages of AI maturity.
So I'm just wondering from your perspective, like, what does that look like now?
Like, where is the typical organization?
Where are the leading organizations?
Like, what are you seeing?
Man, it depends on the size of the org.
Like I'm saying, OK, maybe you have two different style organizations.
Were you born pre-AI or post-AI?
Did you go and dominate a market before AI was here?
These are like your Fortune 500s and your 1000s.
Or are you new?
The incumbents.
The incumbents.
Yes.
Are you that?
Or were you born in the last three years?
I think that totally is a different ballgame.
If you're born now, okay, yeah, you started with agentic development.
You're all about how...
Long my agents are running without me having to go and tell them what to do next.
But if you're like a lot of the larger companies that we work with, you're in a different path.
You have like 4,000, 1,500 developers.
You're trying to shift an entire organization.
And I think even for those, it's more like move beyond just like, okay, how many developers are using.
I think they've gotten into like, okay, what are the quality gates?
What's my AI code review?
And now I see them start saying, okay, let's say that I'm okay with the code gates and stuff.
They're still kind of working there.
How am I generating the specs?
How am I testing?
So it's kind of like totally depends on when you were born, when this company was born, to be honest with you.
Yeah.
I completely agree.
It's very interesting to see within these companies, like these big companies, all of a sudden you have one team that's like, whoa, like a head.
And they're like behaving like, because I keep thinking about it like three phases.
There's like this visibility and all you care about is visibility and adoption.
Then there's like experimentation.
Then there's like, okay, transform.
Now, some companies, like you said, then were born transform.
Now, what is super interesting, like you can see these teams that are like taking off within the big company.
And yeah, they're like, of course, like my inner loop is like a new inner loop.
Like Dan said, it's like, it includes like idle time for agents and everything is spec driven development.
And it's super interesting because the big companies are looking for these teams and they want to identify them.
And kind of say, okay, how do we replicate that behavior?
Yeah, it's really like an apples and oranges thing.
Like those two different types of teams and what they're going to get out of AI are very different.
The strategies they have to employ to not only like transform it, but to survive are totally different.
And like for the ones that have like all the pre-existing stuff built up, for them to be able to identify.
those individuals and those teams that are managing to find those new inner loops and are managing to unlock new speed and success.
Like the way that they, those organizations can mature on their AI pathway is to uplift those employees and to enable them across the entire organization and really figure out what is working so specifically well for them and how can we replicate across everybody.
Because I'll say as somebody who has found a lot of success using the tools, you don't want to be that person, that thousand X engineer that's doing everything and everything just falls into your black hole of engineering.
You want to be able to distribute that ability to work to everybody so the whole organization can up level.
So it's a really great partnership.
that you see between like these orgs and with these leaders and these teams that do manage to unlock that, you know, like Ori, what have you seen from like teams and what do you think about like teams that are, have these kinds of like, you know, maybe hidden gems within their org and how do they unlock them and transform everybody else?
You mean like, um, um, How do they find ways to infect the entire org or something?
Yeah, how do you find it and then uplift it and get it to everybody else?
So first of all, like we said before, you need to identify them.
It's not easy.
Think about what Dan said.
You have, I don't know, 2,000 developers, 500, I don't know, 4,000.
You got to have ways to identify those teams.
What I've seen people doing that is very successful is like, Even internally, I've seen us doing, our organization is doing, is giving autonomy to teams to try new things.
For example, there's one team who's like, okay, everything is spectator and development end-to-end.
And then, okay, I was actually a part of a town hall meeting for a big customer of ours where the one team that said, okay, we cracked the code, was standing in front of everybody.
was describing how they work, etc.
There's another great thing that if you learn how to work better, so there's the human element, right?
Think about our industry.
If you know that you need small TRs, before that, what you had to do is go and say something like, okay, let's run an education program and explain to everybody how important it is, etc.
Improvement now is, yeah, educating the teams, but...
Sometimes it's just like prompting better.
So all of a sudden, like you don't have to wait to teach everybody how to work.
You sometimes just like prompt better your agents.
So then like it's becoming infectious.
Like even the team who didn't like that still need to learn are getting like better working agents.
So that's a very interesting topic.
Our improvement is becoming exponential now when it's not like just humans.
You can just tell the agent, hey, this is the right way to work.
Yeah, I love that insight.
The idea of like, oh, this is ultimately just a prompt or a context engineering change.
And it becomes easier to experiment and find those results.
Yeah, before that, it was a six-month education program.
Think about it.
And I want to make a shameless plug real quick.
What I've been describing this as is almost like the agentic halo effect.
Like you want to find the developers that both have high AI usage, but are also on a team with high AI usage.
And you want to find the teams where you have individuals that have a high AI usage, but low usage across the rest of the team.
And I've actually been playing around just with Linear B to like dig into our own data.
And it's like really surprising how you can just like quickly find like that person who is like clearly at the center of some sort of transformation.
And then it's just a matter of like doing, bringing their success to the rest of the team, you know?
Yeah, 100%.
So.
I have a provocative question I want to put on the table for you, Ori.
You know, we've had some discussions in this chat about Greenfield versus Brownfield code bases.
And Linear B is one of those what you call incumbents.
We were existing before AI entered the scene.
But if Linear B was an AI native company and you were launching Linear B this year, you know, what would you do differently?
How differently would you build it?
Yeah, thank you for the provocative question.
I was talking to Dan the other day and, you know, trying to kind of frame it.
We understand like the engineering teams, they need context, right?
And by the way, they needed context before, but AI made it like mission critical.
If you don't have context, it's like, what do you do?
Like, how do you even move?
And it hit me that actually Linear B, what we build is the engineering context layer.
That's what we built.
By the way, without knowing at the beginning that that's what we built in full transparency.
Like I said, before that, improving something was an education program.
And all of a sudden, now you have context.
So if I would build Linear B today, and it's not just a theoretical question because my role is to navigate the company, to do this change, and to make sure our product and our vision aligns with that.
I would say, hey, this is the operational context store.
And it has like two legs, almost like one for AI native development.
So these agents, like we spoke before, they need like context around repos, et cetera.
But they need also super interesting context about teams.
And then, okay, if I have to find someone with knowledge, how do I do that?
incidents and services that are up or down.
So they need like, so one leg would be like the, what I call the AI native development context.
And then the other leg would be the engineering operation context, which is, by the way, excites me sometimes even more than the coding part.
Because remember how we spoke before about how to jump over the 10, 15% like productivity level?
That will happen not only when you fix testing and reviewing and all of that.
That will happen once, and we have customers who are doing it today, which is amazing.
Once roadmapping, you won't go into a roadmapping session before you have an analyst agent to look at all your data, all your goal calls, and say, hey, this is probably what should be the roadmap.
When you think about even your iterations, your team lead, you wouldn't go into this planning session.
for half a day before you have an analyst agent crunching your data and saying, hey, this is what probably should be working and that's what's realistic.
And even staffing decisions and bigger things.
So to sum it up, I would build like a context store and that's what we're actually building, right?
That's like the transformation that we're going right now for AI and native development, but also for the engineering operation side, if it makes sense.
Yeah, completely.
It's like you see the opportunity is that teams need to understand not only what's going on in their org, but convert it into this context layer and something that's navigable by humans, but then also act upon something that can be acted upon by agents.
It becomes this harmonious middle.
And I really think that's the differentiator.
between Linear B and other platforms as well is because it has the follow through.
And not only is going to give you that, you know, we're calling it a context engine.
It's like you turn it on, you drive it, like it takes you somewhere because it's giving you not only the information.
but it's also letting you do follow through.
And acting on that context, I think, becomes a big differentiator.
And so now, even in the space that we're moving into in this reality, in the incumbent Linear B world, how does that capability evolve?
How does Linear B go from, you know, it's not just a context layer, it's a context engine.
You can drive it, you can take action with it.
Yeah, so...
Dan and I were always obsessed, even before we understood that we built the engineering context engine on how to help our customers take action.
So Linear B has GitStream, which is their orchestrator, if you will, when you want to speed up coding decisions, like what do I merge, who do I route this pull request to, etc.
Well, we're thinking about GitStream now is, okay, orchestrator is great, but what if we give this context also to the existing agent that can make better decisions?
That's one direction that we're going.
And the other one is on the other side that I spoke to you about, like the engineering operation side.
So think about like we built like a library of skills that you can use exactly for those use cases that I just described.
Like when you go into a roadmap session, activate this first.
and all the amazing contacts that we have will help you take smarter decisions.
So we're in the phases of developing it.
It's available for some design partners.
And we're already thinking about the ideas of making it like a marketplace and collaborating with our customers on it.
Because again, this is the area where I think we'll give actually the 2x and the 3x the people who want to.
We have customers that are automating like hundreds to like thousands of developer months or developer hours a month through Linear B, you know, and we've always like really thought hard about like making sure that we were enabling organizations to get better, not just like understand their data.
So, you know, as AI continues to get rolled out and it matures and the technology changes, Dan, I'm curious about what you see in customers that are getting ahead and what they're doing to prepare.
for all of these changes versus customers that are maybe falling behind the curve?
Well, listen, the first thing that customers are doing to get ahead, they're getting their end-to-end observability.
That's why they come to us.
If you want to go fully autonomous, fully agentic, the first step, this is like the responsible thing to do, you have to know.
How does my SDLC look today?
What is my efficiency today?
What is my quality today?
What is my ROI today?
And how much is it costing?
You have to know that.
Now, after you know that, that's when you can then go and start dissecting.
This is what I was talking about earlier.
Dissecting your SDLC and transforming it to your ADLC.
So now you can start saying, okay.
I'm going to make a change now.
I'm going to start having agents do all the coding work, but I'm going to put a quality gate in place.
I'm going to make sure that the code going out, the rework isn't going to spike to something insane.
The incidents aren't going to spike to something insane.
Maybe that's the first step.
And then the second step.
Okay, I understand now we talked about context being super important.
Are my specs looking good?
Are my specs AI driven?
Ori talked about bringing in gong call data.
The best, I would say the most mature organizations, I'll use the word maturity, the most mature organizations that are on the hook to deliver actual business value, not just go like all greenfield and go crazy with agents, but you have to deliver business value at cost.
They are mapping their SDLC with data and then they're using the context.
This is what Linear B provides.
to make the agents better, make better decisions, get my analyst agent.
That's what they're doing, BLP.
Kind of jumping off of that, as we're coming into the end of our discussion and our time here together, we've explored some of how...
Linear B customers have been using the platform to transform their SDLC into this ADLC that you've identified to find those outer and inner loops.
And really, I think the common through line of all of these stories and everything that people at engineers have been working on in the last two years for sure.
and all of our predictions we've made here is that there's just a huge amount of transformation and disruption in new stuff out there all the time.
And we're reevaluating things that we carried in from our past engineering lives, from the eras before into today.
And part of that too is like, maybe like the tooling and the technology and the way that we write and ship code is just not even sufficient for the shape of the engineering projects that we do now.
There's lots of talks about people.
Being like, oh, we don't even need programming languages.
We need some new language that is closer to the agent and is more natural language.
And you have other folks over here that are saying that, you know, where the code lives and how we even share code with each other is insufficient.
And that one really sticks with me.
It's like the idea of the Git forge itself maybe being insufficient now for like the era of agentic development is really fascinating.
I want to just end on one last thought-provoking question for you, Ori.
It's open-ended about like where things are going to go.
Do you think the Git forge is sufficient?
Do you think that even Git itself is going to change?
There's nothing we should take for granted.
First of all, you're right.
There's nothing we should take for granted.
Like, I think we don't know where this will go.
I think I've heard people exactly talking on the net side, hey, you know what?
The code is not even the source of the application anymore.
The spec is.
So yeah, like you said, maybe a new language, maybe a redundant language.
Like, okay, agent, take this back and deploy this application.
And we don't know where this will go.
I don't think it will go that fast there.
I think spec-driven development is amazing.
It's used right.
Like we said, it's allowing you to apply AI also, not only to Greenfield, but to refactor.
And I think, and I'm seeing some interesting companies who are starting to do things like that, that like the commit, the Git as the source of truth of like the, okay, Git is the source of truth of the code, but you can also infer about the process if you look at Git, right?
You can understand like reviews and pull requests and all of that.
That's not sufficient anymore.
And I'm seeing some cool companies who are doing something interesting and saying, no, the Atom.
of the development, if you will, is different because it has to capture the interaction with the agent and exactly like we said, what was the agent idle time and was my prompt good and did the agent wait for me long and did I do three things in parlance?
So the session the developers have with the agent is also becoming the sort of truth of the development process.
About where the code lives, I don't know if it will change that fast, but for to infer deeply into the development process, the commit and Git is not enough anymore.
And then think about all the amazing stuff you can extract from that, whether by humans or by agents.
So short answer, yeah, Git is not sufficient to infer the development process anymore.
You need something that captures the sessions.
Awesome.
Well, it's always really great to hear y'all's perspective on the industry because we are really in a unique position where we're getting to sort of witness firsthand how engineering productivity is changing for the AI era.
And I really love the conversation around building context engines.
We talk about that a lot on the show.
And insight compression is a really valuable thing that you can get out of platforms like Linear B.
Yeah, Ori, Dan, thank you so much for coming on the show today.
It's always really great to get updates from you.
And we'll drop links to some resources in the show notes.
Thank you, guys.
You did a great job.
It was great being here.
Thanks, guys.