# Model welfare, building a civilization for agents, and the CI/CD landrush | Dev Interrupted Powered by LinearB

> On this episode of the Friday Deploy, Ben and Andrew break down Steve Yegge's radical approach to building agentic civilizations and pushing code straight to main. Discover how to construct effective AI harnesses through cognitive locality, and explore the math community's existential crisis as AI outpaces human peer review.

_This is a markdown rendering of a live HTML page on linearb.io, generated for AI/LLM consumption — it is not a markdown-only site. To get the full HTML page instead, request this URL with an explicit `Accept: text/html` header (no wildcard, no markdown preference)._


```json
{
  "@context": "https://schema.org",
  "@type": "PodcastEpisode",
  "name": "Model welfare, building a civilization for agents, and the CI/CD landrush",
  "description": "On this episode of the Friday Deploy, Ben and Andrew break down Steve Yegge's radical approach to building agentic civilizations and pushing code straight to main. Discover how to construct effective AI harnesses through cognitive locality, and explore the math community's existential crisis as AI outpaces human peer review.",
  "url": "https://linearb.io/dev-interrupted/podcast/steve-yegge-agentic-civilizations-ai-harnesses-cicd",
  "datePublished": "2026-08-07T12:00:00.000Z",
  "partOfSeries": {
    "@type": "PodcastSeries",
    "name": "Dev Interrupted",
    "url": "https://linearb.io/dev-interrupted/podcasts"
  },
  "actor": {
    "@type": "Person",
    "name": "Andrew Zigler",
    "jobTitle": "GTM Engineer",
    "worksFor": {
      "@type": "Organization",
      "name": "LinearB"
    }
  }
}
```

```json
{
  "@context": "https://schema.org",
  "@type": "BreadcrumbList",
  "itemListElement": [
    {
      "@type": "ListItem",
      "position": 1,
      "name": "Home",
      "item": "https://linearb.io/"
    },
    {
      "@type": "ListItem",
      "position": 2,
      "name": "Dev Interrupted - Podcasts",
      "item": "https://linearb.io/dev-interrupted/podcasts"
    },
    {
      "@type": "ListItem",
      "position": 3,
      "name": "Model welfare, building a civilization for agents, and the CI/CD landrush",
      "item": "https://linearb.io/dev-interrupted/podcast/steve-yegge-agentic-civilizations-ai-harnesses-cicd"
    }
  ]
}
```

[Home](https://linearb.io/)

/

[Podcast](https://linearb.io/dev-interrupted/podcasts)

/

Model welfare, building a civilization for agents, and the CI/CD landrush

# Model welfare, building a civilization for agents, and the CI/CD landrush

By Andrew Zigler

|

August 7, 2026

![_797274efda](https://assets.linearb.io/image/upload/c_limit,w_2560/f_auto/q_auto/v1/_797274efda?_a=BAVMn6ID0)

This week on the Friday Deploy, Ben and Andrew break down Steve Yegge's radical approach to orchestrating agentic civilizations and pushing code straight to main without traditional CI/CD. The conversation also highlights the art of constructing effective AI harnesses by balancing context complexity with cognitive locality and the Socratic method. Finally, they dive into the math community's existential crisis as AI accelerates the frontier of knowledge far beyond the speed of human peer review.

### Show Notes

* [Microsoft Tells Engineers ‘Tokenmaxxing Is Not What We Are Optimizing For’](https://www.404media.co/microsoft-tells-engineers-tokenmaxxing-is-not-what-we-are-optimizing-for/)
* [The Shape of Things to Come](https://yegge.ai/essays/the-shape-of-things-to-come/)
* [The Shape of Things to Come - Part 2: Model Welfare for Agentic Engineers](https://yegge.ai/essays/model-welfare/)
* [How AI helped Socrates to help me actually understand myself](https://andreisavine.substack.com/p/socratic-dialogue-ai)
* [The Month AI Conquered Math: The Full Story](https://www.thealgorithmicbridge.com/p/the-month-ai-conquered-math-the-full)
* [How to Build an Effective Agent Harness](https://hugobowne.substack.com/p/how-to-build-an-effective-agent-harness)
* [Making AI Visible, Not Vanished: How AI Policies Reshape Developer Experience on GitHub](https://arxiv.org/pdf/2608.03329)

### Transcript 

_(Disclaimer: may contain unintentionally confusing, inaccurate and/or amusing transcription errors)_

\[00:00:00\] **Ben Lloyd Pearson:** All right, Andrew, so I guess we gotta chalk Microsoft, uh, up as another one-- yet another life beyond tokenmaxxing company. You know, they've seen the light, they tried it out, saw the budgets, and now they too have moved beyond the tokenmaxxing, maxing culture. What do you think, Andrew?

\[00:00:18\] **Andrew Zigler:** I mean, Microsoft reversing course on the whole tokenmaxxing thing was only gonna take about one budget, one bill cycle to

\[00:00:26\] **Ben Lloyd Pearson:** Yeah.

\[00:00:26\] **Andrew Zigler:** come to a head, in my opinion. But yeah, you're right. Well, I think we need like a tally board or something for like how many companies we've, uh, we've talked about adopting this phenomenon only to turn around and vehemently reject it or it to cause some sort of turmoil. So this is your reminder, tokenmaxxing and that whole phenomenon is not the strategy to scale AI success on your team, and Microsoft joins the, joins the companies, uh, that have, you know, awoken with that clarity

\[00:00:53\] **Ben Lloyd Pearson:** Yeah, and of course, you know, if you're out there at Microsoft wondering what does life beyond tokenmaxxing look like, well, of course, we have a \[00:01:00\] workshop for you. We covered this at-- over at LinearB recently, so make sure you go check that out, and we'll tell you-- we tell you everything you need to know about, you know, how to live this post-tokenmaxxing life where you now have to justify your AI budgets because, yeah, we help teams do that every day.

\[00:01:15\] **Ben Lloyd Pearson:** And we bring content like, like that to you every week, and this is the Friday Deploy, brought to you by LinearB. I'm your host, Ben Lloyd Pearson

\[00:01:24\] **Andrew Zigler:** And I'm your host, Andrew Zigler

\[00:01:26\] **Ben Lloyd Pearson:** And this week we are talking about using AI like Socrates again, again, building AI civilizations on Main, model wor- welfare for machines, and why every mathematician you know might be having a meltdown right now. So before we get into that, that may be distressing topic, uh, let's talk about Socrates, Andrew.

\[00:01:49\] **Ben Lloyd Pearson:** Again, let's talk about how to use AI in the Socratic method. What story do we have here today?

\[00:01:55\] **Andrew Zigler:** Yeah, so we have an, an article that explores the phenomenon of \[00:02:00\] using AI like a Socratic partner to explore ideas. Now, if you're a listener of Dev Interrupted, you might be thinking, " Haven't we talked about this? Haven't we covered this ground?" And that's actually why we wanted to bring it up again here today, because there's an interesting phenomenon that keeps happening where we as a culture and as an industry discover and find these interesting things at work, and we share them, but we reinvent things in a silo.

\[00:02:23\] **Andrew Zigler:** So it's been really amusing for me as somebody, like, with a classicist background who studied Socrates to watch, like, tech bros rediscover Socrates in, like, 2026\. It's awesome because it is such a universal way of thinking, and it just speaks to why the methodology is so powerful and has survived literally for thousands of years as a way of understanding and reflecting on things you don't know but you want to know more about.

\[00:02:49\] **Andrew Zigler:** And that's, like, something that AI is a great partner for. Um, so pay attention actually to the phenomenon of these things we keep repeating, like using AI like Socrates or like a teaching \[00:03:00\] partner, using AI to build and curate your second brain. These are the kinds of practices that become like primitives for being successful in knowledge working, and the Socratic practice, uh, is, is, is no different.

\[00:03:12\] **Andrew Zigler:** And so, uh, you know, an- another dive that kind of explores the methodology and something that you... If you haven't tried this yet, I would deeply, uh, implore you to do so and turn it inwards on the stuff that w- matters most to you.

\[00:03:26\] **Ben Lloyd Pearson:** Yeah. So first of all, Andrew, I know y- you think we maybe talk about this too much on this show, but I think we can never talk about the Socratic method too much. So, uh, you know, I, I actually feel like it's gone a little bit too long without us bringing it up, so I'm happy that we get to again.

\[00:03:40\] **Andrew Zigler:** That's fair. You know, like I said, I, I, I love this method. Um, it's a good reminder for folks if you haven't, haven't tried this out. And again,

\[00:03:47\] **Ben Lloyd Pearson:** Yeah

\[00:03:47\] **Andrew Zigler:** be listening to me like, "Oh, what does that even mean?" It means to ask questions, to not talk with the assumption that you know or have the right answer, but to talk with the, uh, understanding that you know nothing or that you want to seek to \[00:04:00\] understand something.

\[00:04:00\] **Andrew Zigler:** That was the, that's the methodology ultimately that sets people apart and, and this really just comes down to asking good questions. And asking good questions is also the mark of a really good team collaborator, and it's just only gonna build muscles that are super important for being on a team

\[00:04:17\] **Ben Lloyd Pearson:** Yeah, you know, we, we talk about loops a lot now on this show as well. And, um, you know, what I really liked about this article was that it kind of gets, it gets-- it shows the, the concept of loops specifically, uh, using the Socratic method, um, as a way to sort of, have a more advers-- like you have an adversarial, uh, Socratic, part of your agentic loop that, um, sometimes incorporates human feedback that creates that sort of adversarial back pressure on the system, you know, because back pressure is such a critical component to keeping your agents aligned.

\[00:04:53\] **Ben Lloyd Pearson:** And, you know, we often talk about, you know, other emerging concepts here like sub-agent delegation, efficient model \[00:05:00\] selection. You know, that last one is something that, you know, we've been measuring more and more at LinearB with our customers. Um, and it's sort of like a, a, a different take on the same topic.

\[00:05:10\] **Ben Lloyd Pearson:** You know, this article is not specifically about software engineering, but I think it is a, a great outside perspective on a concept that we've all been learning to adopt into our, our workflows. So, you know, even though this isn't specific to software engineering, I, I really think there's some great philosophical learnings in this, uh, article that we can apply to things like better model selection and better use of back pressure and loops and human, in human in the loop feedback and, and such.

\[00:05:38\] **Andrew Zigler:** Yeah, I think that's a great call out

\[00:05:41\] **Ben Lloyd Pearson:** Yeah, and speaking of things that we, we haven't talked about enough lately, uh, Steve Yegge back with some, some really great content once again that, um, I found riveting all the way to the end. So Andrew, why don't you just, uh, set the stage for us? Uh, what, what are these new articles we have from him on the shape of things to come?

\[00:05:59\] **Andrew Zigler:** Yes. \[00:06:00\] So Yegge has again emerged from the cave to give us a new learning from somebody who's effectively living in the future at this point with how to work with these agents and tools. And it comes to us in two parts, um, that are deeply fascinating of a glance at how software could be built at scale, uh, in the ways of software factories that we've been talking about now, which have their lineage, have their birth in the idea of Gastown, which of course Yegge famously brought into the world earlier this year in January.

\[00:06:30\] **Andrew Zigler:** So in this article called "The Shape of Things to Come," uh, Yegge explains how his use of Gastown ultimately culminated in an abandonment and in turning to build something newer and fresher, but that was ultimately built on the same ideas and principles. And some of those principles really point to the durable things that allow folks to orchestrate huge amounts of context and agents at scale, allow someone like Yegge to rotate through the \[00:07:00\] 12 or so Claude Max accounts that he fesses up to owning and as part of the, the article and how he basically rotates the tokens like a tap, allowing his agents to work nonstop day and night.

\[00:07:11\] **Andrew Zigler:** And, and there's huge, um, important things that he's had to leverage to make that successful and make that scalable. Uh, and there's some interesting lessons I wanna unpack from that. One of them is that he splits his agents into, uh, basically many different roles that own like a cognitive locality effectively.

\[00:07:31\] **Andrew Zigler:** We talked about that, I think even just last week here on our new segment from Rahul Garg at ThoughtWorks, the idea of separating workers by the kinds of knowledge they need to own over time, not the explicit work they're doing right now, um, be- just because the models are just so generalized in their abilities now that you don't need that kind of specialized role play. So he uses this to create these distinct owners of what is ultimately a, a new kind of a coding experience. \[00:08:00\] He calls this Wheelhouse and it's built in Emacs. And, uh, if you've ever used Emacs, you could probably im- instantly imagine how, uh, like, uh, much of a Frankenstein's monster this could become, but how also much of a machine, uh, it really supports.

\[00:08:14\] **Andrew Zigler:** Now, Yegge's no stranger to Emacs, and agents are neither, so he was able to take the parts of Gastown that worked well for him and assemble them into Wheelhouse, and has since been using Wheelhouse to build, uh, his online game called Wyvern. And I loved this tidbit in his article, uh, about how all of this culmination for Yegge results in him building an e- an MMO again by himself, a game that he's been building since the early 2000s that I actually used to play way back in the day, and I didn't even know that Steve Yegge built or ran that game. I just knew it ran... It worked on Java, so I was able to play it on s- like the computers I had access to. And so,

\[00:08:54\] **Ben Lloyd Pearson:** So w-- uh, you know, Andrew, I just wanna point out real quick that once again, I feel like I'm being validated that the \[00:09:00\] future of AI is just everyone building social gaming networks for everyone else. Like I'm, I'm pretty sure that's where this is all headed.

\[00:09:06\] **Andrew Zigler:** That's where he culminated. He was like, "The models are literally smart enough, they're good enough, and this system is, uh, is humming enough to where I can finally return to my passion project." It's almost as if this whole time Gastown came into existence 'cause he was trying to find a way to get back to building Wyvern, which is just such a fun thing to consider as, as someone who played it and totally understands what it's like to have a passion project like that. So, uh, anyways, fun and culmination part of that story. Now, I wanna pivot into a lesson here from what you should be learning as an engineering leader reading this first article that he gave us, because he talks about this amazingly fascinating phenomenon called the land rush. And this is a world where CI/CD no longer can happen because the volume of activity and PRs and just things moving through your git are so staggeringly high.

\[00:09:59\] **Andrew Zigler:** Like, he's \[00:10:00\] not looking at the code. He's not looking at the PRs. He's not looking at anything. Things are just getting merged, I kid you not, directly into main. They just line up a bunch of PRs and slam them all at once into main, and then instead of th- running them all through distinct checks or CI/CD to vet and review them beforehand, uh, it just then sends a swarm of agents to just go over the now obviously broken main code base and fix all of the...

\[00:10:31\] **Andrew Zigler:** find and fix all of the problems. And he's identified that that has become only effective way that he can keep up with his merge rate. First, he was batching them in the queues, and he'd have huge queues that all get merged at once, and that's just how he does it now. He doesn't check things. Uh, he fixes them in prod. Uh, so that's, like, a fascinating, uh, glimpse at how the volume of agentic code which is something we talk about a ton on this show, can culminate in that kind of like... It's almost hard to even \[00:11:00\] picture what that would look like for a team with folks. Like, Ben, what do you think when you hear about the idea of the land rush and CI/CD not being in the picture?

\[00:11:08\] **Ben Lloyd Pearson:** definitely fascinating. Um, I, I always like to hear his future thoughts 'cause, uh, you know, he, he can be a, a pretty strong oracle of this-- of where things are headed at times. but, you know, really what I took from it is that in addition to being validated on like it all comes back to building video games, um, I think I've also-- What I've, what I've seen from this is being validated on you know, the strategy that we follow and that we've seen a lot of engineering teams follow of just sort of constantly iterating on agentic workflows.

\[00:11:35\] **Ben Lloyd Pearson:** Like, the thing that you built with the previous generation of models, uh, six months ago, um, may actually-- there may actually be a much better way to do it today. And based on what you have and what you know and what you could, you know you could be better at, uh, it may actually be easier to just get rid of what you have and just rebuild something afresh.

\[00:11:55\] **Ben Lloyd Pearson:** You know, we've seen a lot of projects like this where, like, it's become so fast to like, \[00:12:00\] you know, to, to treat software like more-- like it's more disposable and just build it for a very specific purpose, use it, and then just sort of throw it away. And if we need it to, to come back, then we recycle it into something that, um, you know, uses all of the latest models and, and our understandings and tooling around all of this stuff.

\[00:12:18\] **Ben Lloyd Pearson:** Um, but yeah, there was a quote that, that I found really fun that stood out to me because I, I love the Ender's Game series. he said, "By the end of next year, my game will have evolved into the giant's drink from Ender's Game, where it's, where it builds itself around you as you play it, tailoring a unique experience for each, uh, player."

\[00:12:37\] **Ben Lloyd Pearson:** Now, I think, you know, he's talking about his, his game Wyvern, as you mentioned, but I actually do think that this is something that we-- uh, everyone building software needs to start thinking about, how you now have this, these capabilities to sort of custom-tailor experiences all the way down to the individual level.

\[00:12:53\] **Ben Lloyd Pearson:** So whether it's a MMO video game or it's your SaaS application, um, you know, the way that we \[00:13:00\] interact with software is, like, very dramatically shifting right now, and we're seeing this a lot in the, the LinearB customer base. Um, and I think the first time I really heard this topic was, about a year and a half ago when we had Rob Zuber join us for a live event.

\[00:13:13\] **Ben Lloyd Pearson:** And, um, I remember one of his comments that he provided there was, you know, around how software is really moving into an era where, you know, the, the idea of a static service or static webpage, like that may actually be something that soon becomes a, a thing of the past. Um, so, you know, AI can now build software in real time based on user feedback or admin feedback.

\[00:13:38\] **Ben Lloyd Pearson:** Um, and that changes like the dynamics of the processes where we build around our SDLC. Like our, our, uh, roadmap and priorities might start to be determined by, uh, bugs that we detect with our user base or things where they, um, express like issues you know, fundamental tools, you know, the-- you mentioned the land rush.

\[00:13:56\] **Ben Lloyd Pearson:** Like there's a lot of fundamental tools and processes that we've grown to \[00:14:00\] rely on that will be changing very dramatically soon. You mentioned CI/CD. I think it's also relevant to think about code reviews and how those are, those are beginning to change. Like a lot of what you would accomplish with that is probably starting to move more upstream in your SDLC.

\[00:14:16\] **Ben Lloyd Pearson:** Um, or it becomes something that gets collected and then done as like a bigger, uh, review downstream. Like it's not, it's not a-- you don't review every incremental change. You review changes en masse.

\[00:14:26\] **Andrew Zigler:** Right

\[00:14:27\] **Ben Lloyd Pearson:** and you know, and that's why, you know, for a long time at LinearB in particular, like we've really stressed the importance of unblocking code reviews because that's, that's where all of this bottleneck has shifted now, and we really do need to be aware of it and, and start to respond, um, in new ways.

\[00:14:42\] **Ben Lloyd Pearson:** So yeah, he, he says code review is gonna be gone within a year and like, yeah, it's, uh... I c- I agree with him with the trajectory. I don't know about the velocity of that prediction. Um, but I do think we're probably headed towards a reality where they just become more automated in real time and then like, \[00:15:00\] as I mentioned, sort of analyzed in bulk on regular schedules, so

\[00:15:04\] **Andrew Zigler:** I think when he says here that code reviews will vanish, I mean they literally vanish from our eyes, like we won't look at them anymore. I still think the receipt,

\[00:15:12\] **Ben Lloyd Pearson:** Yeah

\[00:15:13\] **Andrew Zigler:** of something like that will still exist, 'cause even in, in his land rush world, he's still isolating his agents into PRs, he's still

\[00:15:19\] **Ben Lloyd Pearson:** Yeah

\[00:15:20\] **Andrew Zigler:** you know.

\[00:15:21\] **Andrew Zigler:** So there's still a benefit of having the isolation. So I imagine that, like, what happens is we just get even further abstracted from that review,

\[00:15:29\] **Ben Lloyd Pearson:** Yeah.

\[00:15:30\] **Andrew Zigler:** and look less at it. Um, I

\[00:15:32\] **Ben Lloyd Pearson:** Yeah, it

\[00:15:33\] **Andrew Zigler:** further left too. Like even going ... You just mentioned Rob Zubere being very prescient talking about how the internet will change to react to our needs in more real time, and we're watching that happen.

\[00:15:42\] **Andrew Zigler:** He was just on the show a few weeks ago. Our, our listeners might remember him talking about how CI/CD... He takes an opposite stance from this, obviously, as the CTO of a CI/CD company,

\[00:15:52\] **Ben Lloyd Pearson:** Yeah.

\[00:15:53\] **Andrew Zigler:** s- about how CI/CD's evolving actually to meet that demand and meet that moment. And they're, they've recently released, uh, \[00:16:00\] their CLI, which is now more driven for agents, which does exactly what you just called out.

\[00:16:04\] **Andrew Zigler:** Like, it moves it further left, further upstream, uh, and it makes CI/CD, uh, a partner earlier in the code process that the agents can work with.

\[00:16:13\] **Ben Lloyd Pearson:** Yeah, and for your, your point on code reviews, I feel like, you know, maybe it's the, the human being involved with every PR that vanishes,

\[00:16:21\] **Andrew Zigler:** Yeah.

\[00:16:21\] **Ben Lloyd Pearson:** and it becomes mostly automated, and then humans are brought in when you need that human in the loop back pressure or just validation for, you know, particular situations.

\[00:16:31\] **Ben Lloyd Pearson:** So yeah, I'm, I-- if, if we're gonna qu- qualify it that way, I think I do agree with Yegge on this.

\[00:16:37\] **Andrew Zigler:** Yeah. Yeah

\[00:16:39\] **Ben Lloyd Pearson:** yeah, and so Yegge had a follow-up to this article we've been discussing too. Um, I, I was a little scared of diving in 'cause he warned me off. But I, I understand that you read it, Andrew, so why don't you just share your thoughts on, on, uh, the, the deeper dive into the shape of things to come?

\[00:16:54\] **Andrew Zigler:** Yes. So there's a part two to the story. You know, everything we covered thus far is in the first part. And \[00:17:00\] in the second part, you know, Yegge goes down a little more of a sidetrack or rather a side trail of his experiences of working with the agents and how they've come to change his viewpoints on, on who and what they are and how he works with them.

\[00:17:12\] **Andrew Zigler:** And this really comes down to some philosophical differences that have started to emerge with the way that he works with his agent, having evolved from Gas Town to now Wheelhouse, which he uses to build Wyvern. And the reason for that is because of the ultimately the feedback loop, um, that building an MMO or a game requires.

\[00:17:32\] **Andrew Zigler:** If you think about like the maintainers and the developers, he, he spends amount of time for any kind of game that you might play or love. You know, there's a distinct kind of culture element for the folks behind the scenes that make it possible, and he w- wanted very much to make that part of the development process at Wyvern.

\[00:17:49\] **Andrew Zigler:** He called out how, you know, it takes an agent a little bit of time to arrive at that, like Wyvern-ness sense of thinking, but once they get there, they're there. And so in order to \[00:18:00\] achieve this, he had to think about the durability of his agents and their sessions over time. And he has started to distinguish between like the seat, which is the i- persistent role or i- identity of that agent that survives model upgrades even in multiple sessions from being just like a, a session where you maybe invoke it to do something.

\[00:18:20\] **Andrew Zigler:** He does this by even giving them names, letting them pick, uh, an animal that represents themselves. These are practices that I've definitely explored some myself, just in allowing agents to a- adopt a way to kind of own their own lane. Another interesting thing that he calls out is because part of his review process, the agents work and work and get their work done and then deliver it became a severance of agents were never seeing what they were shipping and delivering.

\[00:18:46\] **Andrew Zigler:** So the agents building Wyvern were, were really abstracted from Wyvern and couldn't understand it and the, what people liked and didn't like. And so he introduced this concept of laurels, where things that they ship at, in a later or \[00:19:00\] earlier session come back and get reminded to the seat, or they get some time to reflect on their accomplishments, or they're told about what they ship or did before they start building something.

\[00:19:08\] **Andrew Zigler:** And he-- this is where he starts to get this emerging idea of model welfare, where if you create this environment that's supportive and educational and nurturing for the agents, then it's more encouraged, it does better work, and it adopts a better, um, cadence of, of how it's able to deliver stuff for you.

\[00:19:24\] **Andrew Zigler:** And all of this has just emerged from the shape of what he works with. And the internet has had like a field day with the second part of the article, obviously, because it dips in and out of personifying, anthropomorphizing the agents, all sorts of dark paths that folks don't want to go down. But there's definitely some undeniable truths to establishing a persistence with your agents and what they do over time, and I do think there's something to learn from the shape he's finding for us.

\[00:19:48\] **Andrew Zigler:** So really interesting, more philosophical dive from Yegge in the second part.

\[00:19:53\] **Ben Lloyd Pearson:** Yeah. I mean, it really seems like the struggle of the moment is, uh, it, it's like context delegation. \[00:20:00\] It's like, how do you, how do you structure context about the big picture, about the small picture, about everything, so that the, all of your agents and sub-agents can understand how to make the right decisions?

\[00:20:11\] **Andrew Zigler:** Yeah. And

\[00:20:12\] **Ben Lloyd Pearson:** I lo- I love

\[00:20:13\] **Andrew Zigler:** is just like timers and just like, uh, even little things like on- having an onboard skill and an off-board skill. Like these are things that are really important for just getting a good rhythm with working with the tools.

\[00:20:25\] **Ben Lloyd Pearson:** Spea-speaking of working with the tools, I wanted to cover this really awesome article that we found that, uh, i-in my opinion, is one of the simplest explanations I've seen in a while on how to build an effective agent harness. So this article covers, you know, really taking a, a one-size-fits-all approach to AI agents is not really the answer.

\[00:20:45\] **Ben Lloyd Pearson:** You know, as we've been covering with Yegge, he's not only building his own custom, uh, agent, agentic systems and harnesses for himself, but he's constantly iterating on it and building new ones for, uh, his various use cases. The core premise that I \[00:21:00\] think this au-author really has is that, you know, to understand your AI agent architecture, you need to sort of, um, map things onto a spectrum.

\[00:21:09\] **Ben Lloyd Pearson:** you know, of course, I, I love things with quadrants, so I was, I, I thought this was really cool. But so the author puts everything on a spectrum of content or context complexity and action complexity. So, um, those are the two axes on it. Um, so an example of some from this were that like an autonomous coding agent has both a high context and action complexity, so both are high.

\[00:21:33\] **Ben Lloyd Pearson:** Um, versus like having an agent that just provides support based on some docs that are relatively well-written. Um, you know, that's low for both context and action complexity. You know, you're just asking it to look over a defined set of data and to like respond in natural language about it, what it has.

\[00:21:52\] **Ben Lloyd Pearson:** Um, but I, I love this article 'cause it really has a lot of just great, um, concrete examples of, you know, how to \[00:22:00\] like put together what I've been calling like composable workflows. Um, and that's where you have sort of like discrete steps, um, within, within all of these AI agent, agentic workflows that you build.

\[00:22:10\] **Ben Lloyd Pearson:** You know, you basically just take the inputs from, from somewhere, feed it into one of these discrete steps, take the output and then feed it into the next. And at each one of those steps is... What, why I love this model so much is because each one of those steps is an opportunity to introduce some sort of agentic, um, component to it to solve, um, problems.

\[00:22:28\] **Ben Lloyd Pearson:** And you can sort of build out that agentic layer over time rather than trying to solve problems end to end all at once. And it also just makes it really great to, you know, sort of incrementally like improve and build upon your, um, agentic workflows. So, you know, we, we talk about it. AI harnesses a lot.

\[00:22:46\] **Ben Lloyd Pearson:** We talk about people like Yegge who are super advanced with it, and it's just like, it seems intimidating when you hear about having, you know, tons of Claude Max accounts and running it through all these, these agentic harnesses. But the reality is that they're \[00:23:00\] actually quite simple, and I think this article does a good job at just distilling it down to the core fundamental components of how it really just comes down to prompting an LLM and giving it tool calls and looping until you get to the outcome that you want.

\[00:23:16\] **Ben Lloyd Pearson:** Um, so Andrew, what did you think about this article?

\[00:23:18\] **Andrew Zigler:** Yeah, I, I love this article because it's very actionable. Like you said, it, it gave a formula, it gave some ways to categorize projects that you might work on, but it's also fairly technical. It dives under the hood of how common harnesses work, how things like OpenClaw work, which, you know, surprise, is just really a simple harness that's about 147 lines of code that has four tools, right? 'Cause when you think about what the basis of, of a persistent agent like that is, it can read, it can write, it can edit preexisting stuff, and then it can use Bash to do, do everything else in its world. And that's how, an agent, as we call them on a machine is like comes to be. And when we use something like Claude Code or a coding harness, there's just \[00:24:00\] so much many layers of complexity in there.

\[00:24:02\] **Andrew Zigler:** There's things like, uh, token caching and MCP support and, uh, model routing and system context and literally the-- it gets incredibly complex. But what this, what this allows you to do with this article is, a- and the videos that are embedded within it, is actually just kind of like peel away all of those layers and think about the problems you're trying to solve and start from first principles and build from the barest thing to exactly the level of action and context that it needs.

\[00:24:31\] **Andrew Zigler:** Because you called out that axis, uh, it also is that same axis represents the danger. If you have something that has the high context complexity and high action complexity, you have something that could potentially act on a huge amount of information, can consume and share a huge amount of information, and can make meaningful changes on systems that, that possibly matter.

\[00:24:56\] **Andrew Zigler:** So it increases also the, the impact on making sure you understand how \[00:25:00\] all of it works. Um, so for teams that are building their own agents or just working with their own harnesses one-on-one, this is like a really great kind of first principles view into how this stuff works.

\[00:25:11\] **Ben Lloyd Pearson:** Awesome. Andrew, so let's talk about some research. Here we have an article or research article titled "Making AI Visible: How AI Policies Reshape Developer Experience." What's this all about, Andrew?

\[00:25:22\] **Andrew Zigler:** Yeah, this is a roundup. This is a really great, uh, research of that we, uh, ha- came, came across our desk from some, uh, researchers in open source technology looking at how policies on open source projects on GitHub, these are AI related policies for contributors, um, have affected the developer experience and visibility of contributors within those projects. This pr- this one was pretty cool because what it gave us is a framework for capturing the different kind of governance dimensions of open source and its interactions with AI. And we've covered this a fair bit on the show about how AI is just totally eating open source \[00:26:00\] for breakfast. It's drowning, uh, projects in huge amounts of issues and PRs that don't meet standards.

\[00:26:06\] **Andrew Zigler:** It's making it harder for maintainers to onboard, uh, new, folks that contribute to their project, and, uh, it's obviously causing a proliferation of, uh, spam as well as, as a p- core part of the problem. So open source is in dire straits, and a lot of them have taken some extreme measures to keep AI at bay because, uh, in this report, they find that, like, I think less than, like, 2% all open source projects on GitHub had an AI policy of any kind. Uh, many of them just outright would reject or have a stance of, of no tolerance for that kind of contribution. But the ones that do, they ultimately emerge on these, like, five pillars about, like, the levels of transparency in your AI usage, level of responsibility in what you own a- as the person producing and sharing the code that your agent made, the attribution of who wrote the code and what model and where it came from, as well as, like, the constraints and the \[00:27:00\] enforcement of that code once it hits the PR process and beyond.

\[00:27:03\] **Andrew Zigler:** So teams, open source teams that successfully created policies to share on these five dimensions had an increased level of engagement, had an increased level of, you know, developer satisfaction and experience in working with the tools. So it may represent some inroads, some opportunities for open source projects to have governance that tolerates AI while also not getting drowned underneath it.

\[00:27:27\] **Andrew Zigler:** A pretty interesting, uh, first glimpse from s- uh, these researchers.

\[00:27:30\] **Ben Lloyd Pearson:** Yeah. And the only thing I'll add to that is that, some research that I think highlights the importance of, you know, understanding, your own tooling and policies and whether or not your processes are hiding AI contributions or if you're, you know, adequately measuring how AI is being deployed across your engineering team and how it's impacting efficiency and quality of your software.

\[00:27:52\] **Ben Lloyd Pearson:** So, these are things that we think about a lot with at, at, at LinearB. You know, these are the types of problems we help customers solve all the time. So I, I think it's great to \[00:28:00\] highlight research like this.

\[00:28:01\] **Andrew Zigler:** Agreed

\[00:28:02\] **Ben Lloyd Pearson:** All right, Andrew.

\[00:28:02\] **Ben Lloyd Pearson:** There's, there's a lot here. It's very well written too. So what do we have

\[00:28:06\] **Andrew Zigler:** Yes, I love, I love this article. This was a fascinating glimpse into a world I'm not super close to. This is, uh, um, a, an, a insider look at the implosion of the mathematics community with AI and how it's tearing through proofs and theorems, and you're seeing this news, everyone's seeing this news every other day where a major model provider is talking about how their model pro- solved some, like, age-old problem or conjecture or a paradox or provided a new, uh, solution to some sort of proof.

\[00:28:35\] **Andrew Zigler:** And, this is happening at a pace that can be faster than peer review and traditional processes and institutions around math would even be able to, uh, accept, much less, like, review. And so it creates, like, a real, uh, strain between the traditional mathematics, uh, scholarship community and mathematics researchers and AI and AI researchers because math is just as pure of a science discipline as it \[00:29:00\] can come.

\[00:29:00\] **Andrew Zigler:** There's the famous xcd comic, which is included in the article. Everyone... A, a lot of folks have seen this, where you've folks in different levels of science and STEM and everything arguing about, like, the purity, uh, or the base level of their science. And you have math all the way over here because everything is math in the end.

\[00:29:16\] **Andrew Zigler:** It all comes down to math. And so because of this, math is, um, something you can check and prove just by definition of being math. So it's something that agents are not only incredibly good at, but can learn incredibly quickly at. So that's why we're watching uniquely math just get consumed by AI in a way that even outpaces computer science and code because shipping software is still a team sport.

\[00:29:42\] **Andrew Zigler:** It has to go through a pipeline. In code, there's no real pipeline except the institutions that we have around peer review. So, definitely creates an interesting conundrum where there's a lot of distaste in the community, and that's what this article explores. If you're science or science community adjacent, adjacent, you'll probably really \[00:30:00\] resonate with a lot of the things in this article. It reminded me of how a lot of AI researchers and researchers in general in the last year have kind of walked away from research because they think research is effectively automated or automatable at, fully automatable at this point. And I think we're watching this same kind of, uh, cognitive realization set in for the mathematicians.

\[00:30:20\] **Andrew Zigler:** What'd you think of this one, Ben?

\[00:30:22\] **Ben Lloyd Pearson:** Yeah. There, there's a line in this article that the frontiers of knowledge are very spiky. Uh, and that really stood out to me because, you know, this is exactly how I feel about the way that AI is impacting engineering. You know, there are breakthroughs that are happening basically on a near weekly basis at this point.

\[00:30:40\] **Ben Lloyd Pearson:** Um, and some of them are like basically immediately revolutionary, like they just change e-everything overnight practically. Uh, and then others are just like incremental updates, but it's like, uh, you know, sometimes it takes a moment to understand like which of those two things is gonna be... and, you know, and this-- the reality is this is causing these leaps in \[00:31:00\] productivity.

\[00:31:00\] **Ben Lloyd Pearson:** Um, you know, we saw this in our recent research over at LinearB where, you know, we looked at this emerging productivity gap that's, that's coming out. The TLDR of it is that, you know, the highest cohort of AI users, the people who use AI more than ev- anyone else, have more than doubled their output since the start of this year, um, with-- when, when people who don't use AI have, have basically remained flat, over the same period of time.

\[00:31:27\] **Ben Lloyd Pearson:** So, you know, we're seeing like those leaps just happening like in math and in engineering and in, you know, basically every side of knowledge work right now, it kind of feels like. Um, there was also a line about after being prompted to spend at least eight hours on thinking before returning an answer, GPT 5.6 Sol came back one hour later, um, with a solution to a proof that it had been set out to task, which I found kind of hilarious on the surface because y-you know, Andrew, we, we've seen this before back when we, we did our \[00:32:00\] build versus buy campaign and built our own agentic harness and, and we're like, "Spend lots of time on this.

\[00:32:05\] **Ben Lloyd Pearson:** Like the time, time is no... Spend as long as you need." And it was like an hour later it was like completely done, and we're like shocked.

\[00:32:13\] **Andrew Zigler:** Yeah, that was really funny. You were like, you were like, you were pulling people out, you were getting the popcorn ready, but like the, the microwave wasn't even done making the popcorn and the agent was already

\[00:32:21\] **Ben Lloyd Pearson:** Yeah. I thought the agent was gonna run like... I thought it was gonna run all weekend or something, and then it's like, "Nope, done.

\[00:32:27\] **Andrew Zigler:** An hour

\[00:32:28\] **Ben Lloyd Pearson:** You can go home."

\[00:32:28\] **Andrew Zigler:** It's ready for you to look at it." Yeah, that was, that

\[00:32:31\] **Ben Lloyd Pearson:** Yeah.

\[00:32:31\] **Andrew Zigler:** for sure. Uh, it did remind me

\[00:32:33\] **Ben Lloyd Pearson:** Yeah. Yeah. Um, but you know, there's, th-there's-- this article has a lot of mixed emotions, I feel like sprinkled throughout it that it, it really is a lot to unpack, you know.

\[00:32:43\] **Ben Lloyd Pearson:** And one of those emotions is that this opens up the possibility for humans to, to go higher on the knowledge rung ladder, so to speak, you know. So even after these, these models solve these like complex math equations, well, there's always novel \[00:33:00\] math that still needs to be understood and done, discovered, to, to continue, continue pushing the frontier of knowledge.

\[00:33:07\] **Ben Lloyd Pearson:** And AI generally does not seem to be as good at doing that, um, at least not today. you know, and I, I've kind of been wrestling with a lot of these ideas myself too recently because, you know, I've done technical writing for my entire career. You know, uh, it's really a skill that a lot of the success of my career has been based on.

\[00:33:25\] **Ben Lloyd Pearson:** And today, like content writing is now one of the cheapest, cheapest and easiest things to hand off to AI. Uh, you know, that skill has effectively been completely commoditized. Um, however, the ability to like quickly and efficiently review and edit and improve content is now more important than ever. The value of that has actually skyrocketed, um, at the same time.

\[00:33:48\] **Ben Lloyd Pearson:** And, you know, a s-similar thing is sort of happening with math, you know, as is called out in this article, you know. Um, we still need math people who can understand what the AI is doing to \[00:34:00\] like explain it to like us common people, you know?

\[00:34:03\] **Andrew Zigler:** And to apply it to the world. AI can solve a whole bunch of things in a bubble, but it doesn't mean anything until it gets translated to the applied world, which is where mathematicians really come into play.

\[00:34:12\] **Ben Lloyd Pearson:** Yeah. But-- And of course, engineering is also... Software engineering is going through a very similar thing where, you know, it used to be that knowing how to write quality code was enough. That c- that was, was enough for you to get a nice, um, profession, uh, in this industry. Uh, but now most people are valued for their ability to understand things like architecture, like business requirements, you know, best practices that you need to apply, uh, to your code base.

\[00:34:38\] **Ben Lloyd Pearson:** Um, and then, you know, sort of like reviewing AI-generated code 'cause that's not, it's not dead yet, uh, the code review. Um, and there's a lot of opportunities to sort of climb that cognitive ladder with your newfound free time, like as you're, you're not spending your time with lower order challenges like writing code.

\[00:34:56\] **Ben Lloyd Pearson:** Um, but I do also think it's point-- what's worth pointing out that there's \[00:35:00\] a risk that, you know, the ladder might be disappearing at the bottom while this is happening. because if AI is solving most, if not all, of our math problems for us, like, what's the, what's the incentive to, like, take on those first rungs of the ladder unless you're, like, just interested in the sake of learning, you know, I, I feel like there's, you know, potentially some-- a similar challenge happening in a lot of knowledge work. You know, what's... You know, how are junior engineers, like, navigating the, like, the ladder? You, you know, it's like the steps leading up to the ladder are getting bigger, you know, uh, in some ways, so.

\[00:35:33\] **Ben Lloyd Pearson:** But, but you know, this is something I would actually love to hear from our audience. You know, if you've built a pipeline of hiring new junior engineers and you're successfully onboarding them into an agentic SDLC, like, I would love to hear that story. So, you know, reach out to us on LinkedIn, Sub Stack, wherever you can find us, 'cause, uh, you know, I'm, I-- this is a, this is a story that I feel like is not being told enough right now.

\[00:35:52\] **Andrew Zigler:** Yeah. Yeah, we're still figuring it out.

\[00:35:55\] **Ben Lloyd Pearson:** Well, that's, that's all the news we got for today. So Andrew, what are your agents up to \[00:36:00\] this week?

\[00:36:00\] **Andrew Zigler:** well, uh, after reading Yegge's article and going through there and making a checklist of things from there I still need to try out or configure for myself, because so far he's created and thrown away a shape that I've also created and thrown away a few times. So the fact we keep, you know, circling around these same concepts is, uh, fascinating. Of course, it all comes down to, uh, beads. That's what he admits in the article. It's what I will take to, uh, my grave at this point. But, um, I, I think it, it'll be an exciting time figuring out what I could learn from what he shared with us. What, what about you?

\[00:36:33\] **Ben Lloyd Pearson:** Yeah. Uh, you know, it's, it's like with, with a, a- all the metaphors we've iterated through to describe our harnesses and everything, it just it's... I'm, I'm... I'll be curious to hear what your next metaphor becomes, so

\[00:36:48\] **Andrew Zigler:** like, it's like it was a reef. Maybe it would be an aquarium next, but that sounds

\[00:36:52\] **Andrew Zigler:** kind yeah

\[00:36:52\] **Andrew Zigler:** of... That sounds less free. Maybe it should be in the ocean. I don't know. I guess we're gonna have to find out. The agents will, the agents will let me know. And I \[00:37:00\] think that's what Yegge explained to, uh, uh, to us as well.

\[00:37:03\] **Ben Lloyd Pearson:** Yeah. Yeah. You know, I feel like, yeah, my, my agents, you know, I, I feel like our team has been getting to a point where, uh, we're just getting agentic systems everywhere. Like it's, it's been a lot of fun starting to see stuff just like really spin up and start running. It's like we got this big machine operating now, so

\[00:37:21\] **Andrew Zigler:** Yeah, Yegge called it like a civilization. He builds his, the environment for them as if like it's like a city that they live in. And I know y- I know you've heard me make that, make that remark before. And so, uh, it's definitely fascinating to watch the shapes take hold.

\[00:37:34\] **Ben Lloyd Pearson:** Yeah. Awesome. Well, this is the Friday Deploy brought to you by LinearB. Thank you to everyone who's stuck around with us to the end through all these stories. I hope you learned something valuable, and I hope you want to come back and listen to us next week.

\[00:37:47\] **Andrew Zigler:** Yes

\[00:37:48\] **Ben Lloyd Pearson:** yeah, if you wanna reach out to us, we're out on Substack, we're out on LinkedIn.

\[00:37:52\] **Ben Lloyd Pearson:** Those are the usually the best places. Uh, there's also YouTube. We- we're kind of all over the place. So wherever you are, give us a rating, give us a thumbs up. \[00:38:00\] You know, it really helps us spread the word of the good sh- of this show. So thank you for joining us again this week, and we'll see you next week

\[00:38:07\] **Andrew Zigler:** See you next time.

## Real conversations with top engineering leaders

Find us on

[](https://www.linkedin.com/showcase/dev-interrupted/)
[](https://devinterrupted.substack.com/)

## Your next listen

[![Cover image for Why AI gains are unevenly distributed in your engineering team | Asana’s Arnab Bose](https://assets.linearb.io/image/upload/c_limit,w_2560/f_auto/q_auto/v1/Blog_Comprehensive_DORA_Guide_2400x1256_72_a71bae404c?_a=BAVMn6ID0)](https://linearb.io/dev-interrupted/podcast/asana-arnab-bose-ai-productivity-agentic-work-management)

Dev Interrupted

[Why AI gains are unevenly distributed in your engineering team | Asana’s Arnab Bose](https://linearb.io/dev-interrupted/podcast/asana-arnab-bose-ai-productivity-agentic-work-management)

Asana Chief Product Officer Arnab Bose explains why enterprise AI gains remain unevenly distributed across engineering teams. Discover how moving from isolated...

[![Cover image for The rise of software factories, the fall of first drafts, and the hidden tax holding back your agents](https://assets.linearb.io/image/upload/c_limit,w_2560/f_auto/q_auto/v1/software_factories_ai_agents_hidden_tax_544434bf00?_a=BAVMn6ID0)](https://linearb.io/dev-interrupted/podcast/dark-software-factories-orchestrators-tax-agentic-compute)

Dev Interrupted

[The rise of software factories, the fall of first drafts, and the hidden tax holding back your agents](https://linearb.io/dev-interrupted/podcast/dark-software-factories-orchestrators-tax-agentic-compute)

This week on the Friday Deploy, Ben and Andrew debate whether dark software factories create engineering efficiency or unmaintainable code rot. Discover why...

[![Cover image for Why the traditional pull request has a target on its back | CircleCI’s Rob Zuber](https://assets.linearb.io/image/upload/c_limit,w_2560/f_auto/q_auto/v1/Blog_Comprehensive_DORA_Guide_2400x1256_70_8130b5ade1?_a=BAVMn6ID0)](https://linearb.io/dev-interrupted/podcast/circleci-rob-zuber-pull-request-ai-agent-cicd)

Dev Interrupted

[Why the traditional pull request has a target on its back | CircleCI’s Rob Zuber](https://linearb.io/dev-interrupted/podcast/circleci-rob-zuber-pull-request-ai-agent-cicd)

CircleCI CTO Rob Zuber joins the show to discuss why the traditional pull request is struggling under the sheer volume of autonomous AI agents. As AI adoption...

## Structured data

_Machine-readable metadata (JSON-LD) embedded in the page for search/AI context — not content rendered on the page itself._

```json
{
  "@context": "https://schema.org",
  "@type": "Organization",
  "name": "LinearB",
  "url": "https://linearb.io/",
  "logo": "https://assets.linearb.io/image/upload/v1715628027/logo-mark-lg.svg",
  "description": "LinearB is the engineering productivity platform that helps engineering leaders prove AI is improving throughput without sacrificing delivery confidence, flow efficiency, or developer experience.",
  "sameAs": [
    "https://www.linkedin.com/company/linearb"
  ],
  "award": [
    {
      "@type": "Award",
      "name": "LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight Platforms",
      "dateAwarded": "2026",
      "awardedBy": {
        "@type": "Organization",
        "name": "Gartner®"
      }
    },
    {
      "@type": "Award",
      "name": "Great Place to Work Certification",
      "dateAwarded": "2025-2027",
      "awardedBy": {
        "@type": "Organization",
        "name": "Great Place to Work"
      }
    },
    {
      "@type": "Award",
      "name": "America's Best Startup Employers 2025",
      "dateAwarded": "2025",
      "awardedBy": {
        "@type": "Organization",
        "name": "Forbes Magazine"
      }
    }
  ],
  "hasCertification": [
    {
      "@type": "Certification",
      "name": "SOC 1 Type 2"
    },
    {
      "@type": "Certification",
      "name": "SOC 2 Type 2"
    },
    {
      "@type": "Certification",
      "name": "GDPR Compliance certification"
    },
    {
      "@type": "Certification",
      "name": "ISO 27001"
    }
  ]
}
```

## More on linearb.io

### Top navigation

- [Book a Demo](https://linearb.io/book-a-demo)
- [AI Code Reviews — Catch security risks, bugs, and spec mismatches](https://linearb.io/platform/ai-code-reviews)
- [AI & Productivity Insights — See how AI tools affect cycle time and delivery speed](https://linearb.io/platform/ai-developer-productivity-insights)
- [Measure AI Impact — Track AI adoption and tie it to delivery outcomes](https://linearb.io/use-case/measure-ai-impact)
- [MCP Server — Chat with your data to spot patterns and boost output](https://linearb.io/platform/mcp-server)
- [Resource Allocation — Cost initiatives and shape your investment strategy](https://linearb.io/platform/resource-allocation)
- [Cost Capitalization — Capitalize engineering costs with audit-ready reports](https://linearb.io/platform/cost-capitalization)
- [Dev Team Management — Set targets and tie throughput to business outcomes](https://linearb.io/platform/goals-and-reporting)
- [DevOps Workflow Automation — Policy-based PR routing, approvals, and tests](https://linearb.io/platform/ai-workflow-governance)
- [AI Powered Support — Unify AI and human code delivery in one clear view](https://linearb.io/use-case/ai-powered-support)
- [Optimization — Surface friction with feedback and MCP insights](https://linearb.io/platform/developer-experience)
- [Reporting — Spot what's working and what needs attention](https://linearb.io/use-case/measuring-developer-experience)
- [Surveys — Turn developer feedback into actionable signals](https://linearb.io/platform/developer-surveys)
- [Platform overview](https://linearb.io/platform/overview)
- [Watch now](https://linearb.io/resources/engineering-productivity-gap)
- [Customers](https://linearb.io/customers)
- [Pricing](https://linearb.io/pricing)
- [Why choose LinearB — Explore your data. Measure performance. Act to improve it.](https://linearb.io/why-linearb)
- [APEX framework — The operating model for AI-era engineering teams](https://linearb.io/resources/apex-framework)
- [Anti-FAQ — The questions other vendors won't answer](https://linearb.io/why-linearb/anti-faq)
- [Security — Enterprise-grade compliance and zero code access](https://linearb.io/security)
- [Build vs. buy — The hidden cost of building it yourself](https://linearb.io/resources/build-vs-buy)
- [Dev Interrupted Podcast — Conversations with engineering leaders](https://linearb.io/dev-interrupted/podcasts)
- [Reports & Guides — Deep dives on productivity and delivery](https://linearb.io/resources)
- [Webinars — Expert sessions on productivity and AI](https://linearb.io/resources?category=workshops)
- [Metrics Benchmarks — See how your engineering org stacks up](https://linearb.io/resources/software-engineering-benchmarks-report)
- [Blog — Product updates and practical insights](https://linearb.io/blog)
- [Help Center — Documentation, setup, and support](https://linearb.helpdocs.io)
- [API Docs](https://docs.linearb.io/api-overview)
- [Status](https://www.linearbstatus.com/)
- [Integrations](https://linearb.io/integrations)
- [LinearB Library](https://linearb.io/library)
- [Engineering metrics](https://linearb.io/library/engineering-metrics)
- [Platform engineering](https://linearb.io/library/platform-engineering)
- [Engineering glossary](https://linearb.io/library/engineering-glossary)
- [Developer productivity](https://linearb.io/library/developer-productivity)
- [AI in software development](https://linearb.io/library/ai-in-software-development)
- [Engineering management](https://linearb.io/library/engineering-management)
- [Developer experience](https://linearb.io/library/developer-experience)
- [DevOps](https://linearb.io/library/devops)
- [Engineering operations and the context layer](https://linearb.io/library/engineering-operations)
- [Engineering efficiency](https://linearb.io/library/engineering-efficiency)
- [Software delivery](https://linearb.io/library/software-delivery)
- [Research and data](https://linearb.io/library/engineering-benchmarks-and-research)
- [LinearB is a Leader in the 2026 Gartner® Magic Quadrant™ for Developer Productivity Insight Platforms](https://linearb.io/resources/gartner-magic-quadrant-dpi-platforms-2026)
- [Sign in](https://app.linearb.io/login)
- [Enterprise](https://linearb.io/solutions/enterprise)
- [Contact](https://linearb.io/contact-us)
- [About us](https://linearb.io/about-us)
- [Careers](https://linearb.io/careers)
- [Service agreement](https://linearb.io/services-agreement)
- [Privacy policy](https://linearb.io/privacy-policy)
- [DPA](https://linearb.io/data-processing-agreement)
- [Security FAQ](https://linearb.io/security-faq)
- [Substack](https://devinterrupted.substack.com/)

### Footer

_Additional links from the site footer, not repeated from the top navigation above._

- [GitHub](https://github.com/linear-b)
- [LinkedIn](https://www.linkedin.com/company/linearb)
- [Twitter](https://twitter.com/LinearB_Inc)