# Coding Agents Don't Scale Themselves. Neither Do Your Teams. — Patrick Debois, Tessl AI Engineer · 2026-08-22 Patrick Debois of Tessl argues that the 'dark factory' of autonomous coding agents won't work in most organizations because teams and platforms aren't set up for it, not because the technology fails. Developers who rebelled at 'writing better prompts' re-engaged once tooling opened a technical path; skeptics are ideal for context authoring, and retros target repeated agent failures, not code. Planning splits into well-scoped agent tasks and conversational human work; Debois tracks two metrics: human touches per result (down) and shared fixes that help everyone, not one 10x person. Platform teams must own paved roads, registries, eval systems, and spend visibility; that's the shift from solo developer to multiplayer system, and hiring tests AI leverage, engineering taste, and collaboration. ## Questions this episode answers ### Should developers fix the code an AI agent produces or improve the system? Patrick Debois advises teams to stop fixing the code the agent produced and improve the system instead—the context, harness, and loops around it. He echoes the idea of building the thing that builds the thing, and says developers still tightly in the loop with auto-completion and prompting need to elevate to system thinking. [5:21](https://aiengineer.podhood.com/f8e705fb-25d6-42ca-900b-596a5f8e2498?t=321000) ### What two metrics does Patrick Debois use to measure whether coding agents are getting more effective? Patrick Debois tracks two metrics: the number of human touches needed to get the right result, which should fall as the harness and context improve, and how much of each fix is shared, because improving a common system multiplies the benefit for everybody rather than making a single person 10x. That shift from solo to shared systems is the multiplier. [9:24](https://aiengineer.podhood.com/f8e705fb-25d6-42ca-900b-596a5f8e2498?t=564000) ### What new problems should platform teams expect when scaling coding agents across an organization? Patrick Debois says platform teams need to think about skill registries, eval systems for context, guardrails specifically for coding agents, and identities. These are new areas they may not own, so a named owner must drive the centralized program and provide paved roads—reusable context and harnesses—while making spend visible so teams can optimize rather than just limit costs. [10:47](https://aiengineer.podhood.com/f8e705fb-25d6-42ca-900b-596a5f8e2498?t=647000) ### What does "it will not work here" signal about an organization adopting AI coding agents? Patrick Debois compares today's skepticism about the dark factory to 2009, when people told him continuous delivery was crazy. When he hears "it will not work here," he reads it as a signal that the organization is not set up yet, not that the technology cannot work. He believes harnesses and loops will become commodity, so readiness is the real differentiator. [0:47](https://aiengineer.podhood.com/f8e705fb-25d6-42ca-900b-596a5f8e2498?t=47000) ## Key moments - **[0:00] Intro** - **[0:32] Dark factory** - [0:32] Patrick Debois compares 2009's 'continuous delivery is crazy' to today's 'dark factory will not work here' — the real signal is the organization isn't ready. - [1:41] Patrick Debois predicts agent harnesses and loops will eventually commoditize into a frontier-lab service, so they won't differentiate any organization. - **[2:26] Enabling teams** - [2:47] Developers to Patrick Debois: 'We didn't sign up for this. We didn't sign up for better prompting, writing better specs. We're engineers. We're technical.' - **[3:06] Developer pushback** - [3:40] Patrick Debois: building tooling, harnesses, and loops for agents reopened a technical path and reignited engineers who'd rejected prompt-writing. - [4:38] Q: What should you do with developers who resist AI coding agents? A: Use skeptics to author better context and harnesses — their anger improves output. - **[5:21] System thinking** - [5:21] Patrick Debois: 'stop fixing the code that the agent kind of produced, but improve the system' — build the thing that builds the thing. - **[7:04] Retros & planning** - [7:04] Patrick Debois: retros now ask why the agent hit the same wall repeatedly; planning splits well-scoped agent work from conversational team decisions. - [8:29] Patrick Debois: team leads' directive is 'stop prompting, make the context reusable,' then move the team to harnesses and loops. - **[9:24] Two metrics** - [9:24] Patrick Debois's two agent metrics: human touches per right result must fall; shared fixes multiply because one harness improvement lands for everyone. - **[10:25] Platform team** - [10:25] Patrick Debois: platform teams must own skill registries, context eval systems, coding-agent guardrails, and identities — not just cloud infra. - **[11:38] Paved roads** - [12:06] Patrick Debois: agent skill/harness sprawl happens without owners; a catalog of 3–4 maintained, security-scanned paved roads beats a thousand flowers blooming. - [13:33] Patrick Debois: platform teams should visualize agent spend and iteration counts to optimize cost via better context and harnesses — not just cap spend. - **[14:26] Scaling org** - [14:26] Patrick Debois: VP-level agent transformation needs mandates for team leads and platform teams, not generic lunch-and-learns or 'let a thousand flowers bloom'. - **[15:15] Hiring & teams** - [15:15] Patrick Debois: AI job titles don't validate skills; interview by letting candidates go nuts with AI, then walk through why their solution is good. - [17:27] Patrick Debois: VPs can justify agent investment with agent-effectiveness metrics (turns, reuse), since faster delivery and quality gains are hard to prove. - [18:10] Patrick Debois: when vendor agent costs are 'completely nuts', optimize spend by choosing the right model and improving context/harnesses to cut iterations. - [18:55] Patrick Debois on team sizing: one AI-powerhouse dev needs complementary PM/design, a backup, production support, and juniors, so teams don't shrink to one. - [19:46] Patrick Debois: the dark factory is really a 'dim factory' — invest in auditing, provenance, verifiers, and situational awareness by feature risk. - **[20:02] Dim factory** - [21:07] Patrick Debois's closing takeaway: the solo player won't win the agent game — improvement happens at team, platform, and organization levels. ## Speakers - **Patrick Debois** (guest) ## Topics Coding Agents, Developer Productivity, AI Strategy ## Mentioned Tessl (company), Claude (product) ## Transcript ### Intro **Patrick Debois** [0:13] Well, welcome. Um, last day, I guess. That's what happens. I'm going to talk to you maybe not on the technical side, but more on the organizational side. So if you're here for any technology, you can still leave if you want to. So in 2009, a lot of people were telling me the idea of continuous delivery was crazy. And I feel we're in kind of the same era, or kind of the same thingright now, with a dark factory. It will not work here. ### Dark factory **Patrick Debois** [0:47] That's what I keep hearing over and over again. But what they're actually signaling to me: we're not ready yet. So it's not the technology that can't make it work. It's not something they won't be able to do eventually, but they're just not set up for this. And there's been a lot of conference talks here about optimizing agents, with loops and harnesses and all those pieces. And I think that's great, but eventually we'll all get there,right? It's not that this is the rocket science. And yes, we'll have to assemble this in a good way, but one day this will kind of become commodity. Somewhere, maybe even going into one of the, you know, frontier labs that just offers this as a service and will kind of make this work. And that's not going to be the differentiator for your organization. So I'm starting from there up. Assume we're heading towards a dark factory, some kind of form of autonomous working within an organization. What I've seen for the people adopting this within our organization, including here where I work at Tessl, it changes the dynamic of the way you collaborate around this. And for those familiar, there's like Conway's Law. Like, you know, the way you organize yourselves and the tools, there is a relationship on how they interact and kind of work together on this. But today I'm not talking about, like, how you become better with your agent, but it is about how we'll change your team dynamics, your platform, and your organization. So that's what I'll take you through. ### Enabling teams **Patrick Debois** [2:26] Enabling the team. I assume most of you somewhere work in a team, and that you're not somewhere a solopreneur working. So it kind of works different than just you with your Claude code and a team working together around that with Claude or any of the coding agents there as well. The narrative that I heard a lot is, well, the developer eventually becomes more of a conductor and an orchestrator of agents. And I think that's fair. That's been an evolution that we're on, on the path. We're more like becoming the managers of the agent and kind of dealing with the agents. ### Developer pushback **Patrick Debois** [3:06] Now, what I've seen is that if eventually a lot of developers told me, "We didn't sign up for this. We didn't sign up for better prompting, writing better specs. We're engineers. We're technical." And that creates friction. Like, is this the role that we really want to do? There was a thing that came around, which maybe is more context engineering, that put a first step around, like, hey, it's not just a prompt. We'll test the prompt. We'll kind of evaluate the prompt. We'll kind of distribute the prompt and kind of optimize the prompt. So yes, there's a little bit of engineering, but still, a lot of developers kind of felt empty just working kind of with a prompt and a specification as such. What I've seen is that when we started introducing harnesses and loops and eventually more autonomous work within the whole organization, a new technical path opened. All of a sudden, we were helping the agent with tooling, building tooling for the agent, and that kind of reignited some of the developers who kind of felt that it wasn't for them. Now, all of a sudden, they were like, yes, we can do this. We have that knowledge. We're like somehow helping this, even with a kind of programmatic way. So I think that's interesting that the identity where we say abstraction, abstraction, abstraction, technically, all of a sudden, the craft created some new location for more engineering stuff to go to. Now, when I get the question, can we please help people and they're skeptical people, what do they do? And I always say that these are really great people to engage in creating better context for the agent. Because you tell them, please improve. Please put all your knowledge to improve the result of the agent. And the same with a harness. So if you have those kind of more resistant people that, like, complain maybe about the quality that things were produced by just a vanilla kind of coding agent, use almost that anger, use kind of that skepticism to kind of make it better. And the big mentality shift, if I would advise a companyright now for their developers, is kind of stop fixing the code that the agent kind of produced, but improve the system. I'm not the only one saying this in this event, but kind of that is the difference. ### System thinking **Patrick Debois** [5:42] Like, you kind of improve the system. And I think it was Swix a couple of years ago who said it, like, stop building the thing, but build the thing that builds the thing,right? So we're going on that abstraction, whether that is with context, with harness, with loops. And that is kind of the change that a lot of people who are still very tightly in the loop, auto-completion, prompting, that they kind of need to think about elevating this to the system thinking. So what we're really trying to do is minimize the human touches, but still with good engineering practices. And some of the narrative that comes up more often in the beginning, we're like, oh, great, vibe coding, a prompt, and it gives a result, and we can keep going. Where we now see, well, we're kind of instructing it through prompts, but we're also instructing this, like, please do it with tests. Please update the documentation. Please do this. All the things that we're saying to good engineers, we're now asking the agents to do. So if you still have people who are kind of yoloing their way into this, I think you should tell them, no, stop doing this. Like, engineering practices still matter for you to maintain the system and also for the agent to keep getting better at this. ### Retros & planning **Patrick Debois** [7:04] What I started seeing in some of the more advanced kind of teams is that their rituals of, hey, we're doing a planning and we're doing a retro in a team, that they weren't about, like, hey, we had issues with the code, but we're seeing we had issues with the system. So on the retro part, it's like, hey, the agent went over and over and hit this problem. Can we fix the system? That's something you learn in the retro. And on the planning side, what I started seeing is that things that were sufficiently scoped enough were easy to pick up by agents because they were well-defined. And what still was left for the humans were the things that weren't scoped out well. So there were like a split in the planning where you said, these things can straight go into agents, well-defined, and the harness is getting better. And this is conversational things that we need to decide as a team. And what I find important is there's a certain kind of cycle that developers go through. Yes, they learn first about prompting. They get better specs, context, harness, loop. Also, the industry is learning like that. But there is the lead of the team can say, well, stop prompting, make the context reusable. Now we got that. Now we jump to the next. So part of the team lead is putting that pace and almost that constraint and that directive in the team where it doesn't work where you just say, go figure it out and do something on your own. And one of the impacts of that is that if you start producing as a team more, the people downstream, GTM, people like that, they have a hard time keeping up. Even users have a hard time keeping up. So you need to help them also with automation. So your harness doesn't stop at your coding. It also is extended to those people as well. And the same thing with kind of requiring, like gathering requirements. The input might not come fast enough for your team. So that's another kind of piece that you need to tap into that workflow as well. ### Two metrics **Patrick Debois** [9:24] There's a lot of metrics that people are saying, like, hey, is your, like, tokens spend and all that stuff? I started to believe in these two metrics to kind of see on how to be more productive. One is you start measuring how many human touches you still do to have the agent do theright thing. That's supposed to go down. The better your harness is, the better your context is, the better your guidelines are. And on the other hand, if you're going from solo to shared system, that becomes a multiplier. You fix something once, everybody gets the benefit. This is not the multiplier from the one person becoming the 10x person, but the one change that optimizes the agents has an impact on all the people. So that is kind of the part that we're all. You can start that in a team, working together within your repo, sharing the context, working on the harness. ### Platform team **Patrick Debois** [10:25] But what you basically want to do is you want to scale this out. So you come into the realm of the platform people,right? Because they're the typical shared organization working on this. Now, the platform people, they might not be paying close attention because they're like infrastructure and cloud and working on an MTP gateway and stuff like that. But there's new things like bubbling up there. They need to think about, like, maybe skill registries or eval systems for your context and guardrails specifically for coding agents and identities and stuff. So they need maybe a little bit of a hand kind of growing to that role. And that kind of central role, it's hard. You need an owner to drive that program. But is it the platform team? Is it the developer experience team? They don't typically own any of those pieces of the infrastructure. And the other people don't really do the development. So there's somewhere a blend. But you need to kind of make sure that there's an owner driving this centralized piece and not just within your team. Because you want to have paved roads. And that's how I see it. ### Paved roads **Patrick Debois** [11:38] Reusable context across teams. Why are we all inventing how we do the authentication system,right? This is a shared component. Let's put it in the registry. Why are you building all your harnesses? Well, if we're all using the same linters and the same security tools, that's a reusable component. So I think that will centralize, similar to the paved path for cloud, into that platform registry of reuse. But if everybody can put stuff like on the internet in a repo, it becomes a sprawl. And it becomes a thing like, well, he has a skill. He's maintaining it. That person also has a similar skill and forked it. Now what do I do? Like, which one do I pick? So there is a kind of thing that you say there's an owner for this area, and they also care about making it testable. They make sure that it's modular, that other people can extend kind of the context, for example, or the harness that is security scanned. So you build kind of a more centralized and the fact that it's secured and kind of maintained as something instead of just something I share around in my organization. Now, that consensus is hard. I'm not saying this is tap versus spaces, but at times it feels like that. If you have two developer teams having to have consensus on how the way they work, that requires a lot of communication and brokerage. So you probably don't end up with one thing, but a catalog of three, four paved roads where they can pick off. And they can still do their own, but that's on their own budget,right? The centralized pieces will be maintained, and that is supposed to be the easy way of adoption to go there. Now, if they do this blindly, we also want to make sure that they know what is costs. Because if they visualize the cost, they might be eager to do some optimization in there,right? And that kind of is part of the platform team is making that visible. How much is this spending? How much is that kind of like helping? If I can reduce the number of iterations the agent has to run through, that is an optimization that I can run. But if I don't visualize that and I just see the end result, then we don't know,right? So that is part of the platform team helping people. And so what I'm arguing is that we should somewhere move from the solo developer to the team shared kind of context and pieces to a multiplayer system in your organization. And I think that's where the multiplication effect will happen,right? Because you have this flywheel of improvements to go into multiple directions. Now, one layer higher, the VP engineering says, how do I enable the organization,right? And that is, you know, I can predict the story in your organization. Hack it on, a lunch and learn. Let's share the successes. Have a shared Slack channel. ### Scaling org **Patrick Debois** [14:42] Have a champions program. That's all generic transformation. It could have been Agile that transformed like that. It could have been DevOps. It doesn't matter. And on the other side, we know that the strategy of just, you know, give licensing and educate people, do something, let a thousand flowers bloom, it doesn't work. So what I'm advocating is that the kind of on the organizational is that you give the team leads and the platform that mandate to start doing that work. And it's not a solo developer piece. ### Hiring & teams **Patrick Debois** [15:15] Now, finding people that help you externally is a mess. Yes, we have all the titles, the new job titles, AI product engineer for deployed engineer. You know, there was a whole talk on this. Agentic engineer, AI engineer. It doesn't mean anything. You cannot judge what are what kind of the maturity of this because nobody's really that mature. But it's a signal when you put a job posting out there that people might, with the new intentional, they'll be looking there. But it's not a validation of the skills as such,right? So that is challenging for people, kind of hiring people. Now, they come to the interview, and I heard stories about people using AI to, like, in their ears be a response to the interview person and stuff like that. I think what I hear from most companies is they say, first step is we give them an exercise, and we want them to really go nuts on AI to solve this. You know, if they have help from AI, that's all good. That shows you kind of like how much they can kind of leverage the AI to do this. Now, after they pass this, you do a walkthrough, and you actually say, please explain to me what happened. Why is this a good idea? That's where you are testing the taste and the engineering skills on why they're doing this. First part AI, then engineering. And the third thing is, how do you collaborate? Are you willing to share? Are you open or are you a solo player? That's another signal that you tap into,right? But that fits into that whole thing of, like, making it shareable, making it reusable, making it engineering grade within an organization. Those are the people that you look for. Not people who've studied ML or AI, not people who are, like, experts per se at the coding. There's a blend on this. Now, you might not find a person who has all three, which is okay. But at least you know, like, hey, they're very savvy on this piece, but then for the other piece, they need mentoring and they need tutoring. But, like, don't put all the three pieces into one kind of saying, like, they're junior or they're senior. They have, like, different skills on there. Now, the VP engineering has to defend this, and they would have to make the case,right? Well, we have X amount of licenses that we sold. We have faster delivery, maybe that they can promise, but hard to prove. We have quality that improved. Again, hard to say. But similar to what I said with the metrics of how effective are your agents, you can show that how much turns and how much improvement that you're making on that journey. And same thing, how much there is reuse. So it's an easier way to kind of show metrics than comparing productivity with and without agentic coding that help you in kind of those discussions as well. And so when people say the vendors are charging completely nuts, so we're going to limit the spend, you shouldn't say, like, let's limit all the spends. Your reflex should be, let's optimize the spend and help them kind of reduce that in a good way, whether that's as simple as saying, pick theright model, educate them on the model, but also on, like, giving them better context and harnesses because that will make your cost go down there as well. The debate on smaller and bigger teams, yes, it's nice to have, like, one person who can do it all. That's the ultimate dream. They can do everything. Typically, they're paired with a complementary skill, maybe PM, design, and so on. Okay, then we need a backup if one of them is on holiday, so that amounts back to three. And then maybe somebody has to care about production and tickets coming in. Could be the same people if you're really productive, but yeah, you know, you lose speed of features if you're still doing bugs, and that depends a little bit on your quality. And then there's the junior you want to get on the road as well to kind of make sure they're still learning what good looks like in one of those three areas. So I think we're still limited in the way in an organization that we're not going to each team being a solo or one or two. Yes, a lot of experience, but I think that is the thing. Now, we keep investing in actually education for that piece as well. So one of the final things is the dark factory with probably a dim factory. You have to see what risk you're willing to take for what features. So not if all features will become autonomous, but you can invest more in auditing, like provenance, like who changed the code, verifiers that kind of check whether that code was useful. And when it fails, you invest in situational awareness as well. ### Dim factory **Patrick Debois** [20:17] So there's a whole spectrum from being a micro-manager to being on autonomous approval that everything kind of is correct, but you make the decision on what your risk level is. And I think your mode is capturing the knowledge,right? The knowledge you're putting now into skills, you're in your context, and maybe in your harness, the way you kind of restrain this, your business context. And for me, that kind of brings continuous delivery actually to continuous learning. And if you ask the question, how fast can we swap in, swap out something new? That's your reactive mode. And if you can improve that ultimately, it's not about making the whole system more reliable, but can I keep it reliable while changing more of the system? I'm working on a website that kind of where I tried to list some of the agent enablement patterns that I described. I couldn't list them all within this time. Tell me what you're missing. I'm trying to source social kind of stories. So if you have a story of how things are going in your organization, please tell me, and I am happy to put on a link in there as well. And if you're interested in kind of the slides, happy to share those. And I think if there's one takeaway, it's not the solo player that will win the game. It's kind of like at the different levels how we improve organizations. Thank you very much for listening, and I hope it was useful. --- This library is powered by PodHood (https://podhood.com), the podcast website platform.