# Your agents are starving! Airbyte’s Michel Tricot on the data ingestion crisis | Dev Interrupted Powered by LinearB

> Airbyte CEO Michel Tricot on the data ingestion crisis starving AI agents of context. Discover why data permissions, entity resolution, and long-term AI ROI matter.

_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": "Your agents are starving! Airbyte’s Michel Tricot on the data ingestion crisis",
  "description": "Airbyte CEO Michel Tricot on the data ingestion crisis starving AI agents of context. Discover why data permissions, entity resolution, and long-term AI ROI matter.",
  "url": "https://linearb.io/dev-interrupted/podcast/airbyte-michel-tricot-data-ingestion-crisis-ai-agents",
  "datePublished": "2026-09-08T12:00:00.000Z",
  "partOfSeries": {
    "@type": "PodcastSeries",
    "name": "Dev Interrupted",
    "url": "https://linearb.io/dev-interrupted/podcasts"
  },
  "actor": {
    "@type": "Person",
    "name": "Michel Tricot",
    "jobTitle": "CEO & Co-founder",
    "worksFor": {
      "@type": "Organization",
      "name": "Airbyte"
    }
  }
}
```

```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": "Your agents are starving! Airbyte’s Michel Tricot on the data ingestion crisis",
      "item": "https://linearb.io/dev-interrupted/podcast/airbyte-michel-tricot-data-ingestion-crisis-ai-agents"
    }
  ]
}
```

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

/

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

/

Your agents are starving! Airbyte’s Michel Tricot on the data ingestion crisis

# Your agents are starving! Airbyte’s Michel Tricot on the data ingestion crisis

By Michel Tricot

|

September 8, 2026

![Blog_Comprehensive_DORA_Guide_2400x1256_82_5c3d33ade4](https://assets.linearb.io/image/upload/c_limit,w_3840/f_auto/q_auto/v1/Blog_Comprehensive_DORA_Guide_2400x1256_82_5c3d33ade4?_a=BAVMn6ID0)

If your AI agents are starving for accurate context, or breaking production because they have way too much access, you are officially in the middle of the data ingestion crisis. This week, Airbyte CEO and co-founder Michel Tricot unpacks the massive data access and context sprawl challenges that are crippling AI workflows in production. He and Andrew dive into the critical need for strict data permissions, automated entity resolution, and why the transition to agentic workflows perfectly mirrors the paradigm-shifting migration from bare-metal servers to the cloud. Finally, Michel explains why obsessing over short-term AI ROI is a massive mistake, revealing how Airbyte measures true success with their internal automation project, Hydra.

### Show Notes

* Airbyte: Explore the open-source data integration platform powering AI context at [airbyte.com](https://airbyte.com/)
* Agent Blueprint: Read Michel Tricot's newsletter on building agentic data infrastructure on [Substack](https://agentblueprint.substack.com/)
* Connect with Michel: [LinkedIn](https://www.linkedin.com/in/micheltricot)

### Transcript 

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

\[00:00:00\] **Andrew Zigler:** Today joining me is Michel Tricot, the CEO and co-founder of Airbyte. And Michel is a deeply technical founder who's spent years solving the hardest problems in data ingestion, and lately he's been writing a series on Substack, Agent Blueprint, that I've really been eating up about the underlying data infrastructure for AI applications and why it just breaks and falls apart in production.

\[00:00:24\] **Andrew Zigler:** There's just so many failure cases to be learning from, and today's our chance to learn some of them and explore the often silent engineering hurdles that are involved in providing accurate data and operating on it reliably. So Michel, it's really great to have you here

\[00:00:41\] **Michel Tricot:** Very good to be here, Andrew. Thank you for having me

\[00:00:43\] **Andrew Zigler:** Amazing. Well, I wanna kick things off by talking about something that I'm maybe calling the ingestion crisis, because as a member of the tech journalism and media community, I'm either responsible for creating a new hype or saying that something is dead, right? So I'm gonna say this right now, the inge- \[00:01:00\] ingestion crisis for data.

\[00:01:01\] **Andrew Zigler:** So there's a lot at stake when it comes to providing data to agents because, you know, you are what you eat, or in your agent's case, they are what they read. And so there's a lot of complexity in what you provide to your agents that en- allows it to operate at scale and safely and reliably, and so much of that comes down to pulling data and things out of all sorts of silos and services and applications all across the world, things that are external to your company for the most part.

\[00:01:34\] **Andrew Zigler:** You have to reclaim your data from other people's hands. And then in doing so, it's messy, and no one can agree on how and what or why and best practices, so this just becomes a huge sprawl of connectors and tubes and pipes, and it just becomes impossibly hard to understand and work with. And I think that this is a huge contributor to problems with AI that works in production and at \[00:02:00\] scale for teams.

\[00:02:00\] **Andrew Zigler:** They can't operate on that data, you know, reliably and cleanly. So I want, I wanna hear it from an expert and from your position and vantage from what you do at Airbyte, what do you think about this complexity sprawl, and how do we, you know, start to get a control over all of those data sources so our agents can act reliably?

\[00:02:21\] **Michel Tricot:** There is a crisis on data access. It's not a new problem. It-- Data access has always been a big, big topic, like ever since we invented computers. now when it comes to agent living in an agentic world, the difference is that suddenly can scale like automatizing, uh, task. it means that, you know, like the standard, you ETL into your, uh, into your warehouse, and then you do some analytics on it. still a, a valid model in an \[00:03:00\] agentic world, but you have a lot more new use case. Like very similar to some of the, the use case we had, where you have an application that needs to talk to another application. That's great. But at that point, you should really start thinking about your agent as an entity that going to become, uh, fully self-sufficient. At that point, the real issue you have when it comes to data, which is something we actually have of fixed with, uh, with y- with, uh, with people, is that you need to understand, and you need to keep the control over who is accessing the data, who can access the data, at what pace, at, uh, what kind of operations they can do.

\[00:03:40\] **Michel Tricot:** Because normally you expect some human judgment, but now suddenly you have to trust agent judgment. And also, when should the agent like bring that, uh, decision back to the, to a, to an actual u- uh, human. And I think that's really what's happening. And yeah, there is this piece around, you still need to have access \[00:04:00\] to databases, but you need to also have access to live system.

\[00:04:03\] **Michel Tricot:** Like it can be a SaaS service, it can be an internal API, it can be an internal service. And this is really where a lot has to be done when it come to, to ingestion.

\[00:04:13\] **Andrew Zigler:** Right. It's about like a real-time ingestion. It's about looking at historical information. So understanding that the agent can operate much faster and quicker and make decisions and potentially harmful operations at a scale that just exceeds what humans can. So the scoping of permissions becomes much more of a, yeah, like a, a requirement.

\[00:04:35\] **Andrew Zigler:** It, you said it is for humans, it totally is for them as well, but even more so that becomes the clamp that lets you control.

\[00:04:42\] **Michel Tricot:** A-and the other piece is the more system you're connecting your agent to, the more intelligence you need to be able to, uh, to develop in term of how do you map different pieces of data across this system. So how do I know that Andrew on Zendesk is the same person as \[00:05:00\] Andrew on Stripe, is the same person as Andrew in my product database?

\[00:05:04\] **Michel Tricot:** And, you know, normally, if it's a human doing it, well, you exercise judgment when you do that. But what you want is you want to have autonomous agents. So you need to figure out like what are the rules, what are the-- what is the logic that governs all these different links that are established between these systems?

\[00:05:23\] **Andrew Zigler:** Yeah, completely. That's a huge challenge that we've tackled at LinearB too, that idea of attributing that same user across the different seats of the different platforms they use, because it's one thing to just ingest the platform and ETL it and figure out, like, what, how do we normalize into whatever place we wanna put it?

\[00:05:40\] **Andrew Zigler:** It's another thing to understand the activity and how it correlates to one person or one entity, uh, and more importantly, lets you track the life cycle of things. 'Cause more often than not, applications that if someone's touching or has seats in multiple applications, it's because those multiple applications represent stages of probably some \[00:06:00\] pipeline they move through reliably.

\[00:06:02\] **Andrew Zigler:** Think of, like, going from Figma and then you're on the other end of CI/CD. Like, there's a story there, and so you want to be able, as a, as a product manager or product leader, have accurate forecasting and understanding on your teams, like their capacity on making and producing code, but then also on like the, like the Jira and the Figma side and just getting the actual, um, understanding of the process, right?

\[00:06:25\] **Andrew Zigler:** So there's like a huge... And, and then that itself is a new layer of context. Now you have this context layer that sits on top of all your operators that knows all the tools they're using, so it's a higher order of context. And I, it brings me to the, I guess, one of the issues that I, I wanted to kinda dig into as well is that, like, it can become a context sprawl.

\[00:06:46\] **Andrew Zigler:** Like what you alluded to, there's like a complexity that, that, that definitely increases as, and as you provide more of it to the agent, you also have to be thinking about how do you provide it to that agent just in time, and \[00:07:00\] exactly what it needs, and about being precise, so you can have like long-running operators and such.

\[00:07:04\] **Andrew Zigler:** So, um, what do you think about that kind of balance?

\[00:07:07\] **Michel Tricot:** That's typically a place where this concept of entity resolution, so this, uh, linkage between, between entity extremely important and a-actually the quality of it and the self-learning of it. Like, ideally, it should not be a human that tells-- that creates this link. It should be the agent being able to discover across different silos and figure out, okay, these types of entities are very lightly connected.

\[00:07:37\] **Michel Tricot:** Of course, after that, you put that, you log that, when you've done matches and things like that. if you want to avoid any kind of, bloating your, your context is, it is really about how accurate data is for the task at hand. So it comes from just re-retrieving the records that you actually care about, but it's also about understanding what type of records you need to have access to in \[00:08:00\] order to perform that task. Uh, and not, you know, we had something similar with, uh, uh, with MCPs when it, when it just started. Like, the client would just load hundred percent of all the tools available. That would bloat

\[00:08:13\] **Andrew Zigler:** Yes.

\[00:08:14\] **Michel Tricot:** And at some point, we started to do, okay, no, let's be a little bit smarter and start searching for what tools are available. That is exactly the same thing. Like you go-- you-- like the agent has to go through this discovery phase around, like, if I'm asking, like, give me the, the, the life cycle of that customer on that specific feature. First, you need to have the agent to know, okay, what is that feature? Because that's the first part you start with, and then you start discovering, okay, this feature is associated with this Jira thing. It's mentioned in this Zendesk ticket, and also it's filtered by this particular customer. So this is really like the piece around the discovery of what data and how you're actually going to be working through all these different stores make it so \[00:09:00\] that your context remain extremely, uh, like lean a-and, uh, relevant and accurate.

\[00:09:06\] **Andrew Zigler:** Yeah, no, this identity component actually becomes a really key part of controlling the schema of what things need because it makes me think of even right now, you know, you make the joke about MCP blowing out everyone's context. MCP has had a run in terms of how the industry has used it and misused it and has been mischaracterized and it's reached now a different form because it, it just reached its, uh, its 728, uh, spec finalization or 1.0.

\[00:09:33\] **Andrew Zigler:** So now it's totally stateless and, you know, they listened to changes that needed to happen to make it more, um, uh, economical at scale. But also too, there's the cool thing that's happening of serving skills over MCP. MCP's starting to become a conduit with like MCP plugins where you can define what you're kind of saying like a user or an entity or an identity and say these are its skills and then this is its MCP server or these are the specific tools that are available for it.

\[00:09:59\] **Andrew Zigler:** And so \[00:10:00\] you start to get these strategies that emerge where you can define the consumers of data, the actors on that data, and then you can better scope it to permissions and what things need because, I think that's o- often, often with agents is the most difficult part of trying to wrangle them. I speak from like my own experience as someone who builds like agents.

\[00:10:21\] **Andrew Zigler:** When I do build them, it's so tempting and sometimes it even is easiest to start this way to give them access to everything in a very sandboxed way and then ask it what you're trying to do and see what it does and what it grabs for and figure out that golden path and then cut everything else away and find what's left.

\[00:10:40\] **Andrew Zigler:** Like, oh, they re- it really only needed these few tool calls and this kind of pathing or this kind of thing. And then there's really cool tooling now like, uh, like you can use Agent Gateway to create a very specific slice of like an MCP server that has just these things, and you could do that from a schema.

\[00:10:57\] **Andrew Zigler:** So your workflow could become an \[00:11:00\] MCP schema that's exactly defined for what the agent needs, and then that feels like a great way to work, but then it's also like to start you have to give it the world first. That's not gonna scale. So like how do you think about of finding the right level of permissions you need for agents?

\[00:11:15\] **Michel Tricot:** Yeah. I mean, at the end of the day, building an agent is very similar to, uh... It, it's a learning process. So you need to let it roam free initially, understand what's happening, and then, uh, narrow down the thing. The, like, the perimeter in which it's, it's operating. or you want to narrow it down, there need to be an escape hatch for the agents to figure out, like, this is a piece of-- this is a system that I don't have access to that I believe be relevant for what I have to do.

\[00:11:48\] **Michel Tricot:** And that's a moment when, well, the agent can actually ask permission for it. You know, y- y-- we heard about, OpenAI hacking Hugging Face. basically what, \[00:12:00\] what happened, is just you narrow down, like, where-- what the, the agent can actually do. And you're blocking access to internet, you're blocking access to everything. if you don't have the right, like, boundaries in place, well, it's gonna figure out a way to get out and well, mess, mess with Hugging Face. Uh, but that's, that's, that's very much the, the same, the, the same thing. Like, ideally, you should be having-- being in-- living in a world where you're not just blocking based on your first iteration, but you can actually get feedback from the agents about what is missing. And that's a place where actually metadata about systems that exist should remain available, the data itself, so that the agent can actually figure out, "Oh, preventing me from Salesforce, but you're asking me about, uh, like, sales result. I, I think I should have access to Salesforce.

\[00:12:58\] **Michel Tricot:** Please grant it." \[00:13:00\] And then that becomes part of a new grant that you're providing, or maybe it's a temporary grant. But that, that's really the, probably the place that we need, we need to pro-- You know, it's very similar to a human.

\[00:13:10\] **Michel Tricot:** I don't have access to a specific report, but I need it to do my work. Well, what am I gonna do? I'm going to ask permission to the, to the admin of the, of the platform to give me access to the report.

\[00:13:20\] **Andrew Zigler:** Yeah, no, there's a perfect parallel there. Uh, it, it, it does make perfect sense that, but in order for that to work, the agent has to be aware of what it can't touch, things outside of its boundary, which is a key, it's a important distinction, and it goes back to, like, the idea of, like, if you put it in the jail, if you take everything away, if you strip away the resources, then it doesn't know what it can or can't ask for, and it can deviate into more extremes on its path of trying to solve your problem.

\[00:13:50\] **Andrew Zigler:** So if you want the happy golden path, uh, you wanna make it the easiest way for it to flow. So the easiest way, if anyone en- a human encounters an obstacle, is they figure \[00:14:00\] out, you know, "Who do I need to ask for permission?" And so creating a, an, an, an infrastructure where agents can raise questions and feedback and gaps, that's something that I have found works for me.

\[00:14:12\] **Andrew Zigler:** Like, when I have an agent that maybe uses a bunch of data sources to put together a report or an analysis, like think of like a customer health thing, right? Uh, it, at the end of that process, part of the report is the agent reflecting on things that could have contributed to the report that maybe exist or don't exist.

\[00:14:32\] **Andrew Zigler:** It doesn't know, but, like, if we were to know that exists, now we know, "Oh, this is a gap the agent has," and yours seems like even one step further, like a registry.

\[00:14:41\] **Michel Tricot:** Yeah.

\[00:14:41\] **Andrew Zigler:** the world that's available to you, or could be if you can make the case for it

\[00:14:47\] **Michel Tricot:** Yeah. A-a-and to me, that's also a, you know, you are talking about like the ingestion crisis. That is something that requires additional investment from the, from companies is \[00:15:00\] this documentation and registry of what is available, what it can be used for, what type of data is available inside, and make sure that this type of systems and this type of metadata are made available to agents.

\[00:15:13\] **Michel Tricot:** The last thing we want-- I mean, the ultimate goal is to have autonomous agents, like entities that behave and are going to perform a task with as little limitation as possible. But we don't know everything that's-- you start building your agent, you don't know what it's gonna do. So you need to provide this path for like self-learning and self-improvement, upgrading your memory, upgrading your skills, et cetera, et cetera, so that the next iteration is even better.

\[00:15:41\] **Andrew Zigler:** Yeah. You know, let's talk a little bit too about that ingestion crisis. Going back to it is part of, part of the issue that we've explored is what you do and how you work with the data and how agents consume it and how you manage that complexity. But there's an even earlier problem t- or part of this problem that's even bigger, and that's \[00:16:00\] trying to get the data into your system in the first place from all the different providers and places that they live.

\[00:16:05\] **Andrew Zigler:** And the reality is, is that everywhere that, you know, bakes and provides data to you kinda has a different policy and a different way that they wanna serve it, and there's different ways that you can get it both in real time and maybe on a lag or on a schedule. Most of the time you have to have your own kind of tooling to either receive or to grab it.

\[00:16:24\] **Andrew Zigler:** Uh, and this becomes the whole, you know, ETL world where you're trying to pull that data and figure out how to consume it into all of the bl- building blocks that you and I were just talking about, that, that real engineers wanna work with and enable their teams with. So w- what is the, the state of like the vendor world right now and the way that they push data out?

\[00:16:46\] **Andrew Zigler:** Because everyone's acknowledged that their new consumers of their data are agents, so there's a proliferation to push everything to the front. What is that like from an ingestion standpoint? What's that like from a handling the noise standpoint? Um, just curious from your \[00:17:00\] perspective.

\[00:17:00\] **Michel Tricot:** So I think we-- it always goes back to, uh, to discovery. It's like, how do you let and make sure that an agent can actually, uh, discover what is available and provide, like, accurate data whenever. So at the end of the day, every data problem that, uh, an agent has is just a search problem. So how do you make sure that data that is made of-- You know, that's also-- Like, RAG is actually an

\[00:17:28\] **Michel Tricot:** example of that.

\[00:17:29\] **Michel Tricot:** RAG is a search problem. It's just I have unstructured data I want to be able to search. How do I index it? and it's very similar for any type of data. Now, the problem that exists, and, like, we need to see how the industry, uh, evolves, is many systems don't offer any kind of search primitive. If you want to connect to Gong, if you're using Gong for call, calls, well, I can tell you that \[00:18:00\] the list of transcript for Andrew is gonna force me to iterate through pages and pages and pages of p- of data before I can find the transcript that is relevant.

\[00:18:12\] **Michel Tricot:** And so why I do that? Well, I'm missing my, missing my, um, my context. And so that's the moment when you actually need to do something that is smarter, that allows you to do that search. And the search is not just for, like, unstructured data. It can also be that, well, maybe you're using a payment provider that doesn't allow you to search for transaction have this specific amount.

\[00:18:35\] **Michel Tricot:** And that's a big problem because that's what the agent will need. that's when we go back to, to ETL. Like, ETL is not just an analytic thing. It's just loading data into a place where you can build big processes to process that data, whether it's search, whether it's analytics. And well, that's, uh, that to me is something that is absolutely key.

\[00:18:58\] **Michel Tricot:** Now, will providers \[00:19:00\] of this data want to keep like walled garden of the data and making it accessible? Or do they want to charge for it? Or do

\[00:19:08\] **Michel Tricot:** they want to own their own retrieval agents that they sell? that is what's gonna happen. Like Salesforce, HubSpot, Gong, are they gonna offer like fully-fledged search features or are they going to monetize that or are they just gonna say, "Actually, you should run your agent on my platform." And that, that is really the-- like I'm monitoring it very clo-- uh, very closely because that's a big, value prop of the, the context store that we're building, which is this ability to just ingest the necessary data, the necessary metadata, the necessary permission, so that suddenly you have a place where your agents can just roam free, figure out the data, applying permissioning, et cetera, et cetera.

\[00:19:52\] **Andrew Zigler:** Yeah, it becomes like a fiefdom. Like everyone has their slice of your data, and they realize that there's now several layers that they can operate \[00:20:00\] on top of it. Like they can provide it to you and add more of that. They enrich it. They can pay for the e- egress or the ingestion or the movement of that data or services on top of it, like you're describing apps and agents.

\[00:20:14\] **Andrew Zigler:** We're definitely seeing this where SaaS companies and, and portals were places where we would go typically to, you know, pivot and look over data or otherwise interact with it now are becoming fully agentic assistants, and they're trying to be the place they want other data to go into it instead of it going somewhere else, and everyone's trying to have a stake in all the different parts.

\[00:20:36\] **Andrew Zigler:** So it becomes like does the-- it-- So then it becomes the question for leaders of do I draw all the little highways between all of these services and let them all talk to each other, or do I pull them all into my own layer and trust that I know best of how to do all of those things? Because the real challenge actually becomes, and this even ties back to the build versus buy narrative that's really strong right now in SaaS, is \[00:21:00\] like, do I trust them to be better domain experts about what to do with that data because they do it for bigger customers than me and way more customers than me and have seen every edge case, 'cause that could be a reality.

\[00:21:13\] **Andrew Zigler:** Or do-- or, or is like the opposite true, where we have the domain expertise, and we've always been beholden to it, and this is now our opportunity to take that in-house because we can own the process once and for all? So like what, what does it look like from your perspective when you work with teams that are in those positions?

\[00:21:32\] **Michel Tricot:** Yeah. I think it's a matter of, of, of maturity. You know, um, there is a lot of marketing analytics tools that exist in the market. And in general, they're opinionated about what is marketing, what analytics look like, what you need to be tracking. The moment you start introducing small-- y-you start-- small deviation in, like, how you're doing attribution, how you are, tracking emails, how, like, \[00:22:00\] you're importing lists and things like that, that's when this type of like full, fully fledged product that are turnkey fall, fall through.

\[00:22:10\] **Michel Tricot:** And that's why we're using warehouses this day, because at the end of the day, you will need an escape hatch, and your escape hatch is the raw data. Uh, and the moment you start getting hooked on the, the raw data, it becomes very, very hard to actually go for a specialized platform because you know that the moment you plug it on your data, there will be some, some issues.

\[00:22:35\] **Michel Tricot:** There will be things that are not taken into account. Now, with agent-to-agent protocol, maybe that's solution where you like-- where providers just provide, like, this type of interface that your agents can connect to. But they run the agents, so they run the, the, the retrieval of the data, the replication of the data, or whatever they're doing with the data. But you still have the ability to inject specific, \[00:23:00\] uh, like business knowledge as part of the, of the, like, of the agent roaming on your-- roaming free on your da- on the data, but the within walled garden. Like that is-- But I think today there is so much unknown, and not all companies are working at the same pace, that just want to go down to fundamentals, which is just give me the data and let me do my thing, let me learn about it, and let me also train my organization to just build agents that are actually going to be able to leverage that data.

\[00:23:34\] **Andrew Zigler:** And now, you know, we've covered the different parts of where the data is and how it moves. Once it gets inside the company and teams are able to work with it, you know, what are some strategies that you see work for engineering leaders to make the data that they can pull in from other, other providers and sources and make that available in a, in a way where all teams can experiment and make new workflows and share things?

\[00:23:57\] **Andrew Zigler:** Uh, do you see successful strategies on, like, the \[00:24:00\] ingestion and, like, success story side of, like, the data is, is in-house?

\[00:24:04\] **Michel Tricot:** I think there are already some very solid foundation that are still very much human-driven. You know, you talk about semantic layer, you talk about

\[00:24:12\] **Andrew Zigler:** Mm-hmm.

\[00:24:13\] **Michel Tricot:** golden table and things like that. That is a good starting point. but ideally, there should be a way that a human doesn't have to do that, and there is a way for an agent to actually learn about the company business, the different rules based on, hey, someone-- my, head of finance texts me and says, "Hey, Michel, I think we need to change this particular piece in the error." yes. So do I really want him to go to the data team and say, "Oh, please change the model so that the table is generated with the new thing?" Or should just that become part of your context that gets applied whenever you're querying the data? And I mean, that's the world I want to live in, where this type of decision are just being encoded directly, \[00:25:00\] uh, with, uh, like at data compute time.

\[00:25:04\] **Andrew Zigler:** Yeah

\[00:25:04\] **Michel Tricot:** but we're not there yet. Clearly not. Um, there is a lot of infrastructure that need to be built, and that's why people today are looking to get access to the raw data so that they can understand what they can do with it and how they can adapt their data processes with actually agents working on top of it. But yeah, right now, semantic layer is great because it contains all the definition of your company models and your company operating models. Um, skills are also a good solution where you can describe specific, um, specific rules, specific tables. You can encode that logic, but skills remain a little bit, unpredictable in a way.

\[00:25:44\] **Michel Tricot:** So the question then becomes, okay, do you go from a skill to a query that you can then review, or do you just apply the skill directly and let it run free and cr- and create, uh, SQL queries or API calls to a, to a system?

\[00:25:59\] **Andrew Zigler:** Yeah\[00:26:00\]

\[00:26:00\] **Michel Tricot:** we're still living in between these two worlds, but w- we're seeing that people are just trying to move in that direction, which is: How do I do the minimum amount of work, manual work to actually create that value?

\[00:26:12\] **Andrew Zigler:** Yeah, there's a we- there's a really interesting synergy that happens between like data query and skills and iterating on them in particular, because it goes back to even what you were saying earlier about like it knowing and not knowing what it knows and being able to access the world of info that it needs.

\[00:26:26\] **Andrew Zigler:** The same for iterating with data and understanding the best way to wor- work through a workflow, especially if it's a really data-heavy one, and then like encoding that process in a skill is helpful. The unpredictability emerges from the traditional problems around like how do we scale and share this reliably and prevent the one on Fred machines from getting out of sync from the one on Alice's machine, and like so there's...

\[00:26:49\] **Andrew Zigler:** And MCP solves some of that, but not all of it still. So there's like a lot of, um, still a lot of like operationalizing problems. I do think that going back to what you said \[00:27:00\] about, you know, how do you make changes, oh, you don't go to the data team, you change the process itself, and I think that's just still a new reality that, that teams are grappling with.

\[00:27:10\] **Andrew Zigler:** There was a really standout quote, I think it was from someone on the Anthropic team that talked about how they make decisions. Um, and it was about how they spent so much time talking and aligning before they take any action. Like alignment is the obstacle now. Like if you and your CF- if CFO or whoever like, uh, agree on how the modeling needs to be or what needs to be expected, that is the job.

\[00:27:32\] **Andrew Zigler:** That is the work that has to happen now. Because truly, if you have the data, if you have the agents, then that intent can quickly get inflected into the change without having to become a burden on someone else's plate. And what used to be like a d- a, you know, you pivot in your chair to a person can just be like a delegation that happens by matter of the process

\[00:27:54\] **Michel Tricot:** Yeah. A-and to me Like data drives a lot of decision or \[00:28:00\] drives a lot of information, it has always been bottlenecked on teams that generally are a cost center, so very hard to grow, uh, and that have, uh, their own roadmap. you know, f-few years ago, for example, I was working in an ad tech company, and we didn't have a warehouse.

\[00:28:20\] **Michel Tricot:** It was when Redshift was, was starting. So a lot of the, the query and like data analysis that we were doing was big Hadoop job running on terabytes and terabytes of data. And one question could take two or three hours to run. Uh, and so it means that when you're in that situation, and to be clear, we're still in that situation, it's just that the bottleneck is not that we don't have a warehouse, it's that a human needs to actually run the query, build a query

\[00:28:50\] **Andrew Zigler:** Right. Review it. Yeah

\[00:28:52\] **Michel Tricot:** it. And the, the problem is like whenever you have a question, in general, you are going \[00:29:00\] to want to follow up. You might want to-- it might lead to like ten other questions or ten other side quests. And the moment, for example, I introduced Redshift, at FlyRamp at the time, and it completely unlocked the amount and the depth at which we could-- we were able to analyze, uh, we were able to analyze that data. And to me, I mean, at the time I was the, in a way, like the guardian of the, of the, of that warehouse and the quality, et cetera, et cetera.

\[00:29:29\] **Andrew Zigler:** Yeah

\[00:29:30\] **Michel Tricot:** We made it better, but we still have But the moment you can start providing that and getting an agent to do it based on, "Oh, you know what? Just tell me like, uh, I don't know, how many publisher are giving me more than X thousand, uh, requests per month?" If you don't have a table, well, someone have to build it. But now suddenly you can just write that query, that request, sorry, not even a query, with \[00:30:00\] all the learning about your business, like the agents will be able to figure it out. And that just unlocks the amount and the depth at which you can make decisions.

\[00:30:08\] **Andrew Zigler:** Yeah. There's another interesting change that happens too in that world, maybe this is one you can speak to from your perspective, is like ultimately what happens is traditionally data ingestion, data warehousing, the data that everything runs on is kind of more like a, seems like an IT kind of thing, a cost center.

\[00:30:28\] **Andrew Zigler:** It's like maintenance and pipes and just like, uh, those types of things. But now there's actually such a huge opportunity for it to become a really, a profit driver and a part of the profits, profit center because it helps the teams optimize and improve the value add for customers or what the organization delivers.

\[00:30:47\] **Andrew Zigler:** And data, to be clear, always did that, and every part of that layer always did, but the perception became this cost center. 'Cause not only were they, you know, the executives are, are pretty far \[00:31:00\] removed from the programming world. They're even further removed from the data world, so there's like an alienation of the mindset.

\[00:31:06\] **Andrew Zigler:** But now because data and natural language and the connection of them has never been closer, they actually feel closer to their data than ever before. It's now cool to go up to your data guy and be like, "Hey, what's going on with your data warehouse?" Like, right? It's, I think it's like every, every C-suite wants to be in that position because they know that data is king.

\[00:31:25\] **Andrew Zigler:** So, uh, what do you think about that, that change in mindset?

\[00:31:29\] **Michel Tricot:** I think data is gonna become more accessible as a productivity tool. So let me, let me develop here. an exec If they have-- like, one of the reason why there is this, like, it's a cost center, et cetera, et cetera. I don't always see the value, et cetera, et cetera, of why I have data also because of the, the latency at which they are able... like, we are able to, uh, get value out of it. And the problem is, like, that \[00:32:00\] latency trans- also translate into why do I even need that?

\[00:32:03\] **Michel Tricot:** Because I'm not going to go as deep as I need. So it, it feels like it just an add-on for me to make a decision, but it's not re- fully driving my decision. But the moment you remove that wall between the raw data and the person interacting with it, and you don't have to do the delegation, you can actually ask the thing yourself, changes the, the, the perception of it completely because now you realize that, y-y-you know, it's, it's like writing a document.

\[00:32:36\] **Michel Tricot:** Writing a document is painful, but with an LLM, you can write a document, and now it's not as painful, and suddenly you're just, "Oh, wow, there is a lot of things that I can do. I will do faster than delegating to someone, and it won't take me that ti- much time, but I will get it." And it's self-serve. I can-- I don't have to do back and forth that makes everything slow. And I feel like for the data, something very similar is, \[00:33:00\] uh, is about to happen. a- and at that point, you can really justify, "I made that decision because I was able to, by myself, go very deep into that analysis. I was able to actually explore based on what I want to know, what, what was-- what, what is possible for or what decision I need to make."

\[00:33:19\] **Andrew Zigler:** Yeah, there's just so much value now that can be extracted from it, and the opportunity to, to operate on it is just bigger than it's ever been. And so executives too are, like, in the hot seat now. They wanna understand and, and, and, and work with their data too. And i- interesting things that happen include like, you know, in engineering teams you get these transformations that are happening where you get the proliferation of AI tools.

\[00:33:45\] **Andrew Zigler:** Maybe in the last year we've bought a whole bunch of AI tools or subscriptions and everyone has a bunch of seats, a bunch of stuff, and we've been shipping and writing a bunch of lines of code. You have the whole tokenmaxxing phenomenon that's, like, really run its course recently where everyone's just trying to burn as many tokens as possible.

\[00:33:59\] **Andrew Zigler:** So a lot of \[00:34:00\] the industry's trying to figure out too, as like engineering managers, engineering leaders, like, "My teams are adopting and using these tools. How do I talk about the pr- the value? How do I prove the ROI from our AI adoption?" And what does that look like inside of, uh, your own engineering team, your adoption of tools?

\[00:34:15\] **Andrew Zigler:** How do y'all measure success?

\[00:34:17\] **Michel Tricot:** I think it's too soon to just tie everything to ROI when you're talking about, uh, tech- a technological shift. When suddenly you're not just dealing with humans making the fabric of your company, but you're also dealing with, uh, like autonomous entities. And the, the changes are so big. Like, w- we're, we're just talking about infrastructure stuff right now,

\[00:34:48\] **Andrew Zigler:** Yeah

\[00:34:49\] **Michel Tricot:** it's just the bare minimum. But there

\[00:34:51\] **Michel Tricot:** is so much that needs to happen that only focusing on a six months ROI for an investment in how you \[00:35:00\] build product, in your, your, your engineers are working on how you're managing your inbox on, on your email, and just looking at it from like a six months window ROI perspective, this is wrong. Because, that's the stage one. You're just trying, you're just trying to understand, you're trying to get your organization to understand the value. But what you need to do is to really invest into, well, making sure that, that your company and your organization becomes fluent in that s-- It's like the same thing that happened with cloud at the time.

\[00:35:34\] **Michel Tricot:** We're just all buying servers

\[00:35:36\] **Andrew Zigler:** Yes. You definitely would, same thing with the cloud, buying into it with the ex- with the expectation of something else happening around it, right? Or that it would be the answer to a whole bunch of questions that maybe you didn't even have those questions in the first place. That was definitely a phenomenon that happened.

\[00:35:52\] **Michel Tricot:** And on ROI side, people will tell you, "Come on, we already bought like these 5,000 servers, and you want me to pay like a, a, a \[00:36:00\] consumption-based, uh,

\[00:36:01\] **Michel Tricot:** service for-- to run a, to run a server. Like, why should I do it? When, when, where am I going to see the value?" Et cetera, et cetera. And it's not just that you're making the decision, it's that then the services that you have that were running on your bare metal servers that you've designed to run on bare metal servers, so you don't think about consumption, you just think about, well, the resources here, I can just use as much as I want. Then suddenly you have to rethink your-- the way you build product or the way you operate in order to live in that new world. And it's exactly the same for AI. And yes, if you just do s-something I always hated when I go to this conference, like they say, like the, the word is like lift and, uh, lift and shift.

\[00:36:41\] **Andrew Zigler:** Yes, lift and shifts.

\[00:36:42\] **Michel Tricot:** nothing is lift and shift in cloud because you go from CapEx to OpEx.

\[00:36:48\] **Michel Tricot:** And so when you're at that point, ugh, everything changes. Like you're optimizing your product, the way you run your operation in a very, very different way. then you're gonna say, "Oh, I just moved everything to \[00:37:00\] cloud. Damn, my bill now is like 100x what it was than buying this 5,000 server that I'm amortizing," et cetera, et cetera. Well, where is my ROI? It's negative ROI. But no, it's just that you haven't gone through the, the process of actually making it cloud native.

\[00:37:17\] **Andrew Zigler:** Oh, okay. Yeah, you know, I like this, like, this take is spicy, Michel. I like this take. This is very interesting kind of way to view the how to get the AR- AI ROI. So your, your viewpoint is that measuring it in this, like, short-term window, I totally agree. Like, if you're just gonna arbitrarily, like, draw, lasso some period of time, be like, over this, it doesn't tell you a lot on, like, a grander story.

\[00:37:40\] **Andrew Zigler:** I'm curious, or rather, what I would love to know more about is, like, in that, there's definitely hill climbing that can happen. Like, there's a, there's a certain level of, I think, chaos happening in a lot of engineering orgs where you, maybe you get the one or the two, like, 1,000X engineers who are super agentic, and \[00:38:00\] maybe pe- people immediately around them have this, like, halo effect from how agentic they are.

\[00:38:04\] **Andrew Zigler:** Like, that's happening. You got five people who've all invented the same thing five times, but they never talk to each other. That's happening. So it's like there's a lot of disparate but common patterns, right? So the opportunity in measuring it or understanding, like, we had this many PRs, this many were assisted by agents, this many of them were merged, this many of them were reworked after, can help you actually, like, spot trends and see where it is.

\[00:38:28\] **Andrew Zigler:** Not for the idea of it, like, being your, like, end-all be-all, this is where we park, but more so just, like, how do I make sense of, like, all of this stuff we're paying for and what everyone is doing?

\[00:38:40\] **Michel Tricot:** I mean, I can tell you, like, we have had a very large initiative on one specific part of the product that is fully, fully AI, uh, managed today. So when you're a company like Airbyte, you have to manage hundreds and hundreds of different connectors. So it's-- And what-- The pr- the, the thing with connectors is that it's \[00:39:00\] easy to build. That's not where the cost is. The cost is on the maintenance. And that is also one of the reason why we, we started open source, uh, as, as a company, is because we wanted to really invite the community and just crowdsource the effort so that

\[00:39:13\] **Andrew Zigler:** Absolutely

\[00:39:14\] **Michel Tricot:** connector can just make it better. So we have this th- this, this internal project, we call it Hydra. Uh, we call it Hydra, by the way, because, you know, you cut a head, you have two more

\[00:39:24\] **Andrew Zigler:** Cut a head off, you have two more that grow out. Yeah, exactly

\[00:39:27\] **Michel Tricot:** And here we have a real way of measuring ROI. basically number of engineer per connector uh, number of connector per engineer. Sorry, I'm reversing it.

\[00:39:41\] **Michel Tricot:** And, you know, when we started Airbyte, it was one-to-one. Then it become one-to-two, one-to-three, one-to-four, and you start building abstraction to just make it so that an engineer can do more and more and more with as little effort as possible. And sometime it's not even an engineer. That is the, the ROI we're \[00:40:00\] measuring with, with, uh, with Hydra. And you should not expect that suddenly you hit one hundred percent of it. Like you, you have to scope, and you have to grow into that. the moment you start getting a little bit of it, the next one becomes easier, the next one become easier, and at some point, well, you have a fully automated pipeline that just connect to Sentry, to Zendesk, to open source queries, to, uh, API documentation that look at logs, et cetera, et cetera, and that are able to just take that information, feed it as an input, suddenly Hydra goes in place and starts looking at, "Okay, what do I need to do?

\[00:40:38\] **Michel Tricot:** I've seen that there is this issue with this customer. This API just changed. Let me go through my, uh, of how do I maintain that connector." And suddenly, well, have your ROI, but it doesn't happen overnight. Like you need to tame the technology as well.

\[00:40:57\] **Andrew Zigler:** Yeah. I, I love that, especially how it's so \[00:41:00\] form-fitted for your company and its value add, and you can measure the AI, uh, ROI by understanding how your users and your engineers are connecting to things and then the stuff that they operate on from there. So it's like, that's a great lesson for teams, I think, is like on top of understanding like the numbers in the SDLC on your PRs, also abstracting it one level further, defining what is your success criteria, what's that one level of abstraction higher, and then w- uh, looking for that too.

\[00:41:28\] **Andrew Zigler:** It's like a great strategy. I think

\[00:41:30\] **Michel Tricot:** that, yeah, it

\[00:41:31\] **Andrew Zigler:** yeah

\[00:41:31\] **Michel Tricot:** to revenue, it translate to support utilization, it supports to like SLA, et cetera, et cetera. So all of that just goes up the stack to like the revenue metric.

\[00:41:42\] **Andrew Zigler:** Then the narrative starts to tell itself because once you can pull things out of that layer, the other parts are operational, they're more market-facing, there's more of a story there. It's always been about connecting that big base, that, like, humming engine to that, that, that whole motion on top. Um, wow.

\[00:41:59\] **Andrew Zigler:** \[00:42:00\] So Michel, this has been, like, an amazing deep dive into your perspective, uh, over at Airbyte about how you think about data, how agents work with data, the responsibility of team leaders and managers to, uh, ingest and work with this data, how the companies that hold data are transforming and working with it and, like, the new realities of the market we live in.

\[00:42:20\] **Andrew Zigler:** I think it's been a really great tour of, like, the, the data reality that we live in. And just, you know, as we wrap up, uh, we'll of course point people to your Substack that I mentioned earlier, but is there anywhere else that you'd like to point people to about what we chatted today?

\[00:42:34\] **Michel Tricot:** Yeah, I mean, I think the, the main website or like our Slack community is a great place for, for people to just connect.

\[00:42:42\] **Andrew Zigler:** Awesome. We'll include that too then so that folks can go join and check it out. And if you listened this far, then you clearly loved our conversation, so please be sure to give us a like wherever you are listening or, or watching this conversation. And be sure to check out the newsletter as well that accompanies this on Substack and LinkedIn.

\[00:42:59\] **Andrew Zigler:** Uh, there's a \[00:43:00\] further deep dive on our conversation today, as well as a roundup of the news. And so if you have any opinions on what you heard Michel and I talk about, also please come find us. You know, we're on social media. You can come drop us a hello. If you could take a problem with what we had to talk about or what we had to say today, we'd love to, love to hear your viewpoint, so please just come give us a ping.

\[00:43:20\] **Andrew Zigler:** And Michel, thanks again for coming on the show. It was such a pleasure to chat with you.

\[00:43:25\] **Michel Tricot:** Yeah, same for me, Andrew. It was great.

\[00:43:27\] **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 NVIDIA acquires Hugging Face, OpenClaw 2.0 goes multiplayer, and the Linux kernel fights back against AI scrapers](https://assets.linearb.io/image/upload/c_limit,w_3840/f_auto/q_auto/v1/_2da0450e5f?_a=BAVMn6ID0)](https://linearb.io/dev-interrupted/podcast/nvidia-acquires-hugging-face-openclaw-linux-scrapers)

Dev Interrupted

[NVIDIA acquires Hugging Face, OpenClaw 2.0 goes multiplayer, and the Linux kernel fights back against AI scrapers](https://linearb.io/dev-interrupted/podcast/nvidia-acquires-hugging-face-openclaw-linux-scrapers)

This week on the Friday Deploy, Ben and Andrew unpack Nvidia's massive acquisition of Hugging Face and its implications for localized models. They explore...

[![Cover image for Why software factories fail without humans | HumanLayer, Warp & LinearB](https://assets.linearb.io/image/upload/c_limit,w_3840/f_auto/q_auto/v1/Blog_Comprehensive_DORA_Guide_2400x1256_80_84a60586cc?_a=BAVMn6ID0)](https://linearb.io/dev-interrupted/podcast/why-software-factories-fail-humanlayer-warp-linearb)

Dev Interrupted

[Why software factories fail without humans | HumanLayer, Warp & LinearB](https://linearb.io/dev-interrupted/podcast/why-software-factories-fail-humanlayer-warp-linearb)

HumanLayer CEO Dexter Horthy, Warp Head of Product Engineering Aloke Desai, and LinearB COO Dan Lines debate the viability of software factories and why...

[![Cover image for Build fences not sandboxes, earn the currency of trust, and share the cognitive burden of agents across engineers](https://assets.linearb.io/image/upload/c_limit,w_3840/f_auto/q_auto/v1/building_trust_with_ai_agents_cebc111498?_a=BAVMn6ID0)](https://linearb.io/dev-interrupted/podcast/ai-agent-fences-ox-alpha-trust-software-factories)

Dev Interrupted

[Build fences not sandboxes, earn the currency of trust, and share the cognitive burden of agents across engineers](https://linearb.io/dev-interrupted/podcast/ai-agent-fences-ox-alpha-trust-software-factories)

This week on the Friday Deploy, Ben and Andrew evaluate the arrival of Ox Alpha and unpack the security risks surrounding black-box AI tools. They examine why...

## 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/the-great-software-factory-debate)
- [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)