Skip to content
PodSubs
ShowsPeopleGuestsJobsNewsEvents
More
BlogPodCred
Menu
ShowsPeopleGuestsJobsNewsEventsBlogPodCredNetworksSign in
Join nowSign in
  • Shows
  • People
  • Jobs
  • News
  • More
    • Guests
    • Events
    • Blog
    • PodCred
    • Networks
    Join nowSign in

The AI Native Dev - from Copilot today to AI Native Software Development tomorrow

The AI Native Dev - from Copilot today to AI Native Software Development tomorrow artwork

The Tessl Agent: Build Your Software Factory on Autopilot

Jun 30, 202653 minAudio
ShareXLinkedInFacebookWhatsAppEmail

What if the whole point of your AI agent was to eventually make itself redundant? Dru Knox, Head of Product at Tessl, introduces the Tessl agent - a new interface built not just for AI-assisted coding, but for building the software factory that keeps improving without constant human input. This is a conversation about loop engineering: how to set up automated feedback cycles so your agents get smarter, your code review gets tighter, and your team ships more without adding more toil. What we cover: - What the Tessl agent is and how it fits into the broader Tessl platform - Loop engineering: why building automated feedback loops is the right place to start - How the agent sets up and continuously improves agentic code review - Why optimising your AI agent costs is usually the wrong lever to pull - The case for open, modular software factories - and the risk of vendor lock-in - UX expectations in the AI era: why outcome-oriented interfaces are now the baseline 🌐 Tessl: https://tessl.io 🔔 Subscribe for weekly episodes on AI-native development What's your approach to building feedback loops into your agent workflows? Drop a comment - we'd love to hear how teams are thinking about this.

Audio and video play straight from the show's own hosting. PodSubs stores and serves no media.

Transcript

From the show. Tap a time to play from there.

SPEAKER_03But ultimately, your goal should be that agents are doing a lot of this work in the background. And so the Tesla agent is built to sort of almost get you to stop using it, right? So you work with it, and at the end it'll sort of say, hey, I could set some of these up as recurring actions, I could create a CI CD check for this. So in that regard, you might see that the Tesla agent is actually pushing you a little bit more towards this idea of loop engineering and automating its own work in addition to your coding agent work. And at some point you might say, like, wow, 40-50% of our PRs don't even have a human looking at it. We never had to do a big initiative to make that happen.

SPEAKER_03We got started, we focused on doing what we were doing, and over time it could just delegate more to the agent.

SPEAKER_02The AI Native Dev is a podcast with developers and engineering leads at the cutting edge of AI and agentic coding. Join your hosts, Guy Fajani, and meet Simon Maple every week as we chat with the most exciting voices in AI and tackle the biggest questions we're facing developers today. This is the AI Native Dev. We just wrapped up two amazing days at AI DevCon in London.

SPEAKER_00But the great thing is that we get to do it all over again in New York City this November.

SPEAKER_02You're absolutely right. We're gonna be back in the city that never sleeps on November 3rd and 4th for more amazing sessions, really engaging, hands-on workshops, and much more.

SPEAKER_00Yep, all that great networking, partying, eating and drinking that you've come to expect from AIDEVCON. We think we have one of the best hallway tracks in the business, and it's the perfect compliment to our incredible speakers and presenters.

SPEAKER_02We'll both be in person and virtual with live-streamed access to all mainstage keynotes and talks.

SPEAKER_00Sign up right now for our Super Blind Bird ticket for just$100, only available for a limited time.

SPEAKER_02We're really excited to be headed back to the Big Apple. We hope to see you all there.

SPEAKER_01Hello everyone, welcome back to the AI Native Dev. Today I am excited to announce that we're launching a new product from TESL, the TESL agent. We're gonna spend a good portion of this podcast talking about what this agent is and what it is, but don't worry, we're not just gonna sort of talk about our products over here. We'll also talk about loop engineering and what that is and why we think you know it's a thing that you should know about as well. Uh we'll talk about the the importance of ease of use and UX in DevTools, even in the AI era, uh, and maybe some learnings from a company perspective about building a product in this era.

SPEAKER_01Um so to do all of that, we have Drew, our head of product here from TESL. Thanks for joining us here, Andrew.

SPEAKER_03Glad to be here. Finally, my MOI onto the podcast. It's been only a year and a half.

SPEAKER_01Well, you know, don't take it personally.

SPEAKER_03See how long it is till the next one.

SPEAKER_01We'll see. We're uh we're inspecting.

SPEAKER_03Yeah, yeah, yeah.

SPEAKER_01Performance review. So Drew, uh tell us a little bit about what this Tesla agent is and you know, what is it that we've just launched?

SPEAKER_03Yeah. So there's sort of two pieces to it. First is that the Tesla agent is a new agentic interface to all of Tesla's tools. So everything Tesla does today, helping you scale skills, make them sort of work organization-wide. Tesla agent is just going to help you set that up, put it together in more flexible, intelligent workflows, sort of connecting the tools. The second, the Tesla agent is sort of a first step towards a broader vision of loop engineering or factory building. So the idea is that the Tesla agent is a factory-building agent.

SPEAKER_03So it helps you go from scaling skills across your org to building your software factory piece by piece, setting up these loops that will talk about how you engineer them to make agents more effective over time.

SPEAKER_01Aaron Powell Very cool. And this is um I guess you know you'd still run it with sort of the Tesla agent command in the terminal. It sort of has a little bit of a kind of you know clawed codex, you know, sort of similar to uh feel for it. But you know, while you can ask it to write code, we don't recommend you do, right? Like it is focused on sort of, I guess.

SPEAKER_03Pinning agents down these days is always so hard because at the end of the day, you know, you can ask the Tesla agent to write a poem for you, and it will, but I wouldn't recommend it. It's certainly not built for that.

SPEAKER_01It's not part of our evaluation.

SPEAKER_03No, it's not part of our evals. So ultimately, though, yeah, using the Tesla agent will feel quite familiar. It's uh terminal-based CLI agent. Uh you work with it just feels like clawed code in that sense, right? Like you just type some commands, it'll pick the right skills and actions to take uh on top of that. But in addition to that, we've also designed the Tesla agent to be very automation friendly. So, you know, as we'll get into with the idea of loop engineering, with much of the work that you put into making agents successful and building up a software factory, you kind of want to get out of these interactive sessions, right?

SPEAKER_03Those are sort of a transitionary period where you are figuring out what works, figuring out where you can delegate tasks and sort of what are the workflows you want. But ultimately your goal should be that agents are doing a lot of this work in the background. And so the Tesla agent is built to sort of almost get you to stop using it, right? So you you work with it, and at the end it'll sort of say, hey, I could set some of these up as recurring actions, I could create a CI CD check for this. Um in that regard, you might see that the Tesla agent is actually pushing you a little bit more towards this idea of loop engineering and automating its own work in addition to your coding agent work.

SPEAKER_01Right. Okay, so we're gonna dig a lot uh into that and we talk about sort of factory building, factory manager. Let's start though, just from a concrete use case. So, you know, I picked up the agent. You know, what are some examples of things you can do? Maybe walk us through a bit of a storyline here.

SPEAKER_03Yeah, yeah. I'll give a couple just of how it works. So probably the one I'm most excited about that we uh are using a lot here at TESL is using a TESIL agent to set up your agentic code review harness. So maybe what I'll do is quickly walk through how you can use the TESIL agent to create an agentic code review, uh, agree with your team on a risk policy for when humans need to review it, uh, and then ultimately set up a recurring loop that will optimize that code review over time so that you can just spend time reviewing code, shipping features, and know that everything's gonna get better as you go.

SPEAKER_03And so there's a few components of this that I think are pretty illustrative of uh how the Tesla agent works. So the first, you'd come in and just type something like setup agent at code review, or I want to spend less time reviewing code. Uh and the Tesla agent is gonna start by reviewing and creating evidence-backed findings. So the Tesla agent is trained or instructed to look through all of your PRs, look through all of your issues in your issue tracker, uh, and then also to look through coding agent session logs that it has access to.

SPEAKER_03Those can be either local, or if you've been using Tesla for a while and you've been sort of uploading those logs, we can look through those. Yep.

SPEAKER_01We'll try to find latent knowledge that already exists in your code.

SPEAKER_03Exactly, exactly. So it's the kinds of information that you might want to review against. So it's looking for things like what is your style guide, what are common failure cases that agents might have, what are comments that your team seems to provide frequently in code review. And then once it's gathered all this information, uh first it will tell you what it's found. That information is uh, as is often the case, what's useful for agents is also useful for humans. Yeah. So writing that down, it gives you a chance to correct anything that may be uh off base there.

SPEAKER_03And then what it will do is it will walk you through a few concrete components. So the first is that it will set up a general skill-based agentic PR code review. And skill-based here is kind of interesting because it's uh unlike a lot of tools that are just sort of one click, you put it in production, you forget about it. One of the core principles of TESL agent and of TESL generally is that we think people are going to want to own and build their own factories, right? That this is the kind of thing that will be part of your software engineering discipline, not something you buy off the rack and just take as given.

SPEAKER_03And so for code review, we give you, uh we'll help create a skill that we think maps to your code review best practices. But it's a skill that you own. So you can update it, you can augment it, you can share it with other people, put it in other parts of your workflow. So we'll set that up, and that kind of immediately gets you going. Now every PR that goes up, uh, you'll get a gentic review. So once it's created that skill, the next thing that it will do is set up an actual automated flow so that when a PR goes up, uh an agent with that skill will be run.

SPEAKER_03Uh so there's a few things that we, the Tesla agent and Tesla, can help you with there, which is we provide basic primitives for running an agent through CI, for having it leave inline comments on a GitHub flow, just the sort of niceties that every team ends up building to get a flow that actually works for them. But TESL is built to be modular by design. So if there's things you already have or things you already like, the Tesla agent is fine working with those as well. As part of setup, it will try to learn your preferences. Right. And we have defaults that we think are great, but it works with whatever you you want to bring in.

SPEAKER_01Yeah. So this already, like at this point, you've already used the Tesla agent to figure out what it should have in a review process to create a unit, a skill, a plugin to be able to uh to execute that code review. And it it is it kind of specializes a little bit in all these like repo automations or whatever other tools. Yeah. So let's say, for example, here it created a kind of a GitHub action to run that for you, or it uses our app, and we have a little app to sort of help you as I pointed out. So you're already just like with a relatively simple command set up automated code review right now that is based on your historical learnings.

SPEAKER_03Yes, yeah. And if you're using the Tesla default primitives, you will get a lot of nice things out of the box. So uh one will have helped you create that code review skill. We have a cloud sandbox that you can run the review from, uh, which will have log observability, so you can go in and look at the coding agent logs as it ran. Uh it's also agent and model agnostic, so you can switch easily between any number of coding agents like Codex, Cloud Code, Gemini, et cetera, uh, without having to configure all of them.

SPEAKER_03You just log into TESIL and then set which agent you'd like it to use. Includes open models and open agents as well, which is great for sort of minimizing costs, which is a big one for code review because it's running all the time. It's an area that's really valuable to optimize.

SPEAKER_01Aaron Powell That's probably a point uh worth emphasizing, which is the actual review in this setup isn't happening with uh TESEL uh itself or with a Tesla agent. As we said, that is not a coding agent. Yeah. It is running your agent of choice and sets you up so you can actually swap that agent of choice over time. Yeah. And we'll talk a little bit more about how e-vales can help you guide to pick the right ones.

SPEAKER_03Exactly, exactly. So we help you get it set up. So a lot of what Tesla agent does is actually just helping you orchestrate other coding agents. So sometimes the Tesla agent orchestrates itself, which is always getting a little bit meta. Um, but once you have that uh generic code review set up, the next thing that the Tesla agent will help you do is set up a PR review sort of human gate. And what this means is that we found a lot of companies when they adopt uh agentic code review, the next question they have is when do I have to review it now versus when can the agent review it?

SPEAKER_03Uh and they would like to, for simple PRs, for ones that they have deemed to be not risky, be able to just let a good agentic review handle it, and then they can sort of focus on the more complicated or riskier PRs with their human review time. This is a common practice. Uh basically what we found most teams get to is you want to agree on some sort of policy across your organization with your security team, with privacy team, anyone who might uh who might be involved. And then you want to set up an analysis of every PR to decide based on this policy, does it need a human or does it not?

SPEAKER_03Right. And so the TESL gives you uh, we call it the change risk verifier. You can configure it with your own policy, but it also comes with a relatively uh straightforward one out of the box that you can tune between either more permissive if you'd like to do as much as possible through a genetic code review or more strict. So you can say, I still want humans to review most of the PRs. So it'll again help you set that up as an action that will just run within your CI CD pipeline. Uh and then the last thing that we'll do is we'll go through all of your existing skills and context in your repository, and we will create what we call verifiers out of those.

SPEAKER_03So you can think of these as very small, targeted, and fast LLM linting rules that look at a change, look at the sort of code that's coming into your code base, specifically against different aspects that you've codified in your skills. So let's say that you have a uh design guidelines that says how uh accessibility traits should be handled on new elements. There will be a verifier that we can create for that that looks at specifically files that touch front end and looks just for do they apply those ARIA properties correctly.

SPEAKER_03And if you stack a bunch of those up and keep them very focused, you can keep them small, fast, cheap, and you basically run them like linting against every change that comes in. Catches a lot of the mistakes where agents just don't adhere to what you've codified in your skills.

SPEAKER_01Yeah, I love that. So we've now kind of without command set up three different types of reviews. You review uh the code itself, I guess, that you're sort of invoking a coding agent for. You're reviewing the risk of the change so you can make some smarter decisions about whether you merge them or auto-merge or like a little bit of a flag uh for people. So you kind of codify your policy. Uh and then you know we introduce this verifiers theory, which probably kind of you know is worthy of a podcast episode on its own. But really what that does is it reviews whether the agent has adhered to the uh context that you've given it.

SPEAKER_01Like the sort of the skills, the attempts you've already made within the repo to sort of define how it should behave. It checks whether it adheres to those.

SPEAKER_03The verifiers, in my opinion, are the thing that really closes the loop between skills and plugins and like the sort of instructions, the control plane you have over agents to the actual code that is generated. So it's a way of saying, I told an agent to do these things, but did it actually do them in a way that is fast and scalable and doesn't require uh a million tokens every time you wanna you wanna ask that question. Uh and then the last piece, uh you know, I mentioned the Tesla agent will always push you towards the loop.

SPEAKER_03We sort of believe in loop engineering. Yeah, exactly. Getting loopy. So the uh what the final thing that will be set up is a recurring daily or weekly, depending on what you'd like, automation where the Tesla agent will scan, again, all of your PRs, uh CI checks, PR comments, coding agent sessions, and try to find new mistakes that are slipping through. So for example, you might start with a more strict humans still must review most PRs. And as humans are leaving review feedback, the Tesla agent is basically observing those and creating new verifiers or updating your review skill to try and capture those issues.

SPEAKER_03And then it'll use the TESL platform to create evaluation scenarios to sort of run back and say, okay, I've seen this problem, I've created what I think is affixed to it, I've now sort of simulated this PR a few more times. Yes, now you wouldn't have had to provide that feedback. And so that's where you get into the automated loop of every day, every week, you're just getting a couple PRs from the Tesla agent that make you just a little more AI native, right? Like your skills are a little more robust, your uh PR review is catching a few more errors. Uh over time, you don't even realize you're necessarily investing in it this way, but you'll see just sooner code review completion, less time on code review.

SPEAKER_03Uh and at some point you might say, like, wow, 40, 50% of our PRs don't even have a human looking at it. We never had to do a big uh big push or initiative to make that happen. Just sort of we got started, we focused on doing what we were doing, and over time it could just delegate more to the agent.

SPEAKER_01Yeah, and and I I think a core principle that you're describing here is that you set it up to be a loop uh time. And so we've defined a thing that would run recurringly, the the skill over here, uh we're running it in some sort of recurring location in an automation that runs again and again, and now we're surveying it uh over and over again. And so because it's a loop, you can observe and you can kind of voice an opinion of saying, okay, has it gotten better, has it gotten worse? And you just figure out what is that sort of uh feedback loop that it uh that it gets.

SPEAKER_03Yeah, exactly. It's I'd say the loop is probably one thing if somebody was you know just waking up to agents today in 2026 and looking to get started. I think uh interestingly, the building these loops, doing the sort of loop engineering, it feels maybe like an advanced topic to start. But I think in our own experience, in our own um you know, working with customers or building our own sort of software factory, it actually is feels like the right place to start. Uh when you get going with these loops, they solve a major problem with agentic development.

SPEAKER_03In fact, this was like one of the main reasons we chose to build the Tesla agent, is that building your software factory, making agents more effective, uh, getting them to run more autonomously, delegating work to them, all of that is unplanned work. You have no way of anticipating where agents will fail, when they'll fail, how much work it's going to take to get them to stop failing. And so when most teams get started with like the traditional, you know, boot up an agent, you start interacting with it, uh, they basically find this place where the agent will have made a mistake and they have to choose between do I push through and ship the feature, or do I pause, roll back, and do some science to try and make the agent able to do this in the future.

SPEAKER_03Uh and so people fall into one or two categories. They either focus on shipping, in which case they just get stuck in this local maximum where they they never take the time to fix the agents and get them to a higher level of autonomy. Uh, or they fall into the second category, they are disciplined, they do focus on that autonomy, but you're left with this gulf of like several months or or longer, depending. It's forever to build that. Exactly. And it's like, all right, can you eat that sort of a velocity drop as you basically shift all your work into internal tooling?

SPEAKER_03And so moving to a loop early does two big things. The first is that these loops run in very legible ways. So instead of having a bunch of your insights into how agents are failing, locked away in pr local coding agent session logs, if it's running through a PR review. It extracts it out. Exactly, exactly. It's all of it's all available to you. So you can start making these improvements. And then the loop handles the that grunt work, right? Actually putting up the PR that says, I saw this mistake, I think this fixes it.

SPEAKER_03Yeah. And it allows you to focus just on, oh yeah, that makes sense, except, right? And so it gets the it matches the sort of investment and the time scale so that you just stay focused on shipping. Agents will get better naturally as you engage with them.

SPEAKER_01As you go. So I love this sort of uh loop interaction. And I guess the uh we we talked about the sort of the loop improvement when it comes to the the code review and the inspect of those things, but there's also a loop around the agentic process, right? And I I really like how in the process of that, you know, we you know we oftentimes sort of preach here the importance of evals and you know how you do that. Uh and so uh one of the challenges I guess is we've been encountering is that uh you know, like what do developers not like doing? They don't like you know, writing docs and writing tests, and lo and behold, you know you kind of need to do that.

SPEAKER_01So uh I I think uh what I also like about the the concept of of the loop is that it moves the at least the test authoring into something that is uh done through observation. So instead of uh you know having the the human write down you know, sort of the developer and review things, which you know again, sometimes you still need to do. You still need to define those tests up front. Uh but hidden behind the scenes, if you sort of use the Tesla flow, you know, we will have created some evals for that plugin that you have, because we've looked at issues. But as you do the loop, you know, you can now say, okay, let's extract an eval out of that uh out of that uh process of it.

SPEAKER_01Uh and you know, again, you can kind of debate about how much do you do you let you know, how much do you accept those, you know, uh autonomously or not, but you extract test cases based on real-world scenarios. So you still get yourself into a place in which you're not only modifying continuously, but you're also building more confidence in your changes because you're creating evals as you go. Yeah. But at the same time, you are uh you're not making an effort, like you're not really asking developers to do this thing. Uh and we can probably we should towards the end talk a little bit about ease of use and sort of its importance, but it's one of those things where eventually eventually it might be right, but if it's not easy, people won't do it.

SPEAKER_01Yeah. Uh so I like that. Yeah. Which I guess kind of maybe I'll ask one more question about the review thing and then we'll expand to some other use cases. But uh you mentioned cost uh in passing, and I guess I guess that comes down to that sort of eval process over here, right? So like what happens over time as I run these things? What do I need to do to be able to make it cheaper?

SPEAKER_03Yeah, yeah, yeah. Cost certainly uh a much hotter topic these days than it was. It used to be it's amazing.

SPEAKER_01Yeah. Like a month ago, if you were talking about cost, you were a Luddite, you know, you're like, yeah, you're not believing not an AI believer, you're not sufficiently ADI build on it. And now you're like a forerunner, you know, you're thinking about it. You like open models on it. So it's amazing how these things twist.

SPEAKER_03Aaron Powell It is. It's uh you know certainly makes it hard to build products that are forward-looking and meet people where they are today. But uh I'd say that there's maybe two big pieces to this. So again, to your point, we get a lot of questions from folks internally or externally working with customers on how do I think about cost, how do I make these things cheaper, but without sort of unnecessarily slowing my devs down. People are willing to pay if it has good ROI, but they also don't want to just pay because. So I think the first thing this is I'm sure going to become a broken record of like pulling it back to loop engineering.

SPEAKER_03But the first piece of advice I always give, and the Tesla agent really tries to especially. This philosophy is don't try to optimize your general cost, right? If you're thinking about how do I make it so that every time someone opens Claude Code, they're picking the right model, they're planning with Opus, and then delegating to haiku or things like that. That's going to be a bit of a losing game, I think, for two reasons. The first is humans. Nobody really wants to think about that kind of stuff as they're getting going. And they'll kind of always default to whatever their preference is.

SPEAKER_03But the second is that it's also very hard to anticipate up front when a job is going to become complicated. You might hit an unexpected issue, snag, part of the code base that you thought this was a haiku task or you thought this was a GPT-4.1 or something like that, but it actually is a 5.5 task. That is just hard. And I'd say for most people, you're going to get the best results in your daily interactive driver of just use the best model that you're comfortable using and let it be flexible.

SPEAKER_03But then alongside that, if you are good about identifying recurring tasks and structuring them into workflows and really relentlessly carving them off of that general purpose path into a dedicated skill or plugin that codifies this is how we add a new command to our CLI, or this is how we do version bumping, or anything like that. Those become great targets for optimization. And so what I generally say is the work of delegating and sort of caught putting a box around a certain task and setting it up to run automated is also the work of cost optimization.

SPEAKER_03Because then you can find where your bottlenecks are, say, like this is a workflow that runs, for example, code review. Every single PR. So it's 50, 60, 70 times a day, and it's really important to us. We really need to strike the right balance of cost versus quality. That's where you can bring in the rest of Tesla's tools to say, I have this skill. It codifies my workflow for code review, create a bunch of hypothetical PRs for it to review, run it through its paces, try it on a small model, try it on an open model, help me make that trade-off of, you know, maybe it's 5% worse, but 80% cheaper, I'm willing to pay that cost.

SPEAKER_03And so the Tesla agent basically is built to help you do that process. It watches you as you work with agents, it watches the PRs you put up, and it's going to try and sort of bit by bit move repetitive tasks into structured workflows. And then once that's in place, it can help you optimize them. Right.

SPEAKER_01Yeah. And I think we've always observed how our evals could help you know, for instance, that you can use whatever it is, Deep Seek, you know, instead of Sonnet or instead of GPT-5.5. And that's fine. But one of the struggles was like, how do I, again, from a kind of reasonable ease of use, you know, do you really expect people to every time you know spawn a subagent with that or change it and remember what they're doing it? Um and so uh I I think one of the sort of the hidden wiring that we do when you set up the agent is when you run that environment, we don't just set up the skill in the plugin, but we also run it uh under this command call tester launch, which again we'll probably sort of write more about, uh which is more of like an environment management uh uh setup, uh which allows you to then modify that sort of uh uh project or that plugin that it runs.

SPEAKER_01So once you've concluded that, you can also switch easily. And it's all about just sort of the the gradual path, right? And the evolution.

SPEAKER_03This is I'd say a big uh so in many ways the Tesla agent is an interface to uh and a driver of a lot of these workflows that without the agent, uh we found that just building up towards a factory was too hard, right? There's knowledge that you don't have that's changing every few weeks. People would try to build their own harnesses and then update their harnesses and then update them again, and then you know, cobbling everything together. So a lot of what we're doing to your point is just trying to bring into one place a vertical agent focused specifically on this task with good tools, the right sort of latest cutting-edge knowledge kept up to date on your behalf.

SPEAKER_03But you could probably take a bunch of this and use it elsewhere if you want it, right? We we like to work with any agent that you bring, but we also want to make it easy for users. But there's a second component that you alluded to with uh one of the new commands we're launching, Tesla launch, which is basically allowing you to create an environment for agents to run in. When you get into this task of, okay, I have my sort of skills platform in place, I have the governance, the security, the standardization that I want, I'm ready to start scaling and building these loops.

SPEAKER_03Teams immediately start building the same few primitives over and over again. Like you need a way to wire your issue tracker up to some kind of agent environment to kick off tasks. You need a whole suite of agentic code review. Uh, you have things like when a task finishes, I want to post back to the issue tracker. And so alongside the Tesla agent, we're releasing a whole bunch of building blocks that make those parts easy. So the big one that you mentioned, Tesla launch, is just a sort of dead simple drop-it in coding agent environment, runs in the cloud, gathers all the logs for you to review, and do that sort of optimization loop against.

SPEAKER_03Uh but it also just has good defaults. It can run for longer than 60 minutes. It doesn't have to refresh its GitHub action token all the time. Easy to switch between agents. There's a few others that I'm sure will detail in the in the launch blog post. But all these things come together to your point to make it really easy to just start building your factory one piece at a time. You don't have to pause and do a foundational investment to build a linear app and a GitHub app that can talk to each other and then think about the polling semantics. You can just find a task, put it in automation, and then find the next task, find the next task.

SPEAKER_03And it's never going to feel like you're stopping to do this big initiative. You're just slowly working towards automation.

SPEAKER_01Yeah, so I I love I love that definition. And I guess also probably as people think about sort of Tesla as a whole, you know, we increasingly think about Tesla as this sort of composable factory, right? And you run the agent and you can use the TESL tools, and clearly, you know, we're sort of quite familiar. We built the tools for a reason, you know, we have those. Uh whether those are the existing tools like our ability to eval and gather logs and uh and analyze them, uh, but also, you know, or these sort of newer capabilities that we're that we're introducing. Uh but the idea of the agent is you know it can help pull that together and provide you these different services to help you.

SPEAKER_01So we said a lot about code review uh in the process of it. Can you just sort of quickly name a few other examples of loops or use cases that the agent can help you with?

SPEAKER_03So there's sort of infinite, which is what always makes it hard to talk about these products, but I will I will control myself. Yeah, just a few. Uh so after setting up code review, I think my next few favorite uh first is you can just ask the agent, what could I delegate to agents? And it will go and look through recurring tasks that seem to succeed with a high rate for you, uh, and suggest creating automated uh CI CD actions around that. Another thing that you can do is if there is a certain component or type of feature that agents have been struggling with, you can just ask the Tesla agent, you know, help agents work in my front end, or make agents more effective at designing layouts.

SPEAKER_03And it will go and it will analyze fine failures, pull them in. Uh another great one to get started is just make my repo agent ready. Uh this will do a bunch of things, but one of the main things is we have a bunch of default repo maintenance tasks like uh daily architecture review, uh test quality checks, things like that that we'll just set up for you. It's a great way to get going of just immediately hand off a bunch of work to agents in a sort of general purpose way. So I'd say those are probably the ones that get started, just set up code review, fix a thorny issue where agents have just been messing up in your code base, set up repo maintenance tasks, or just ask the Tesla agent to help you delegate more work to AI, and then it'll go from there.

SPEAKER_01Yeah, I love those. I also uh I like uh recurring things around all of those activities. And so like each of those things, once you get them loopy, uh you you start saying, okay, run a kind of recurring architecture review. You know, fix my flaky tests uh on a recurring fashion. Yeah.

SPEAKER_03Uh and once you have one set of loops, then you can make loops around those loops. So you set up your daily architecture review, but then eventually you can set up a loop that monitors your daily architecture review and makes it more effective every single day or week. And all of this, I know it can seem a bit overwhelming, just you know, loops on loops on loops. Tesla agent is designed to handle all of this. So you just give it the task, give it the problem you're seeing. And uh one of the main things that the Tesla Agent does is think about how to break it down into a loop and suggest an automation so that you never have to do the same task more than once or twice.

SPEAKER_01Yeah. And maybe I'll also highlight that many of these automations and these loops, they will uh oftentimes be focused on the repo itself. So like the other flexible aspect of it is do you uh like oftentimes you will set up those uh optimizations and they will land uh as let's say a GitHub action, right, that runs on a schedule or things like that if you're sort of doing something that's in the repo. And then of course you can kind of set up uh automations that are that are a bit more broadly. So lots and lots to do.

SPEAKER_03So much to do.

SPEAKER_01So a common question that that we kind of get and sort of discuss with customers around this notion of like building a factory versus buying one, right? I think uh today it's sort of a non-controversial statement to say that everybody needs to kind of work towards a factory. I've read it when you're gonna do it. Yeah. Maybe you can say a few words about sort of our philosophy when it comes to kind of factory building and kind of you know, own it versus buy it.

SPEAKER_03Yeah, of course. So uh I'll I'll bligh some of my roots here. I started my career working on open web platform, uh web standards, so certainly have a bit of a bleeding heart for this as well. But I also think it's it makes good sound business sense. Uh at TESL, we think that the factory that you build is gonna be a piece of technology. It's gonna be a differentiator that your team owns. It's part of your software discipline is building and maintaining this factory, and that there will be repeating components to a factory, but that everyone's factory will look slightly different based on your preferences and the services that you use.

SPEAKER_03So factory uh platforms will be much more like platforms, less like frameworks or like end-to-end solutions that you just buy off-the-shelf black box. Uh, and we think that for a few reasons. I think the most important one is that when you think about the grand total of building software products, right? There's a lot that goes into it. It just seems hard to imagine how a single provider, a single company could be best in breed at every single component that goes into that, right?

SPEAKER_03Design, mock-ups, code review, actually generating code, uh working with your legal team, sales, like all those things need to be brought into the factory over time. And buying into a single solution, somewhere in that stack, you're gonna be buying into not the best version of that component. And so we think that being open, modular, like Tesla wants to provide good defaults, so you don't have to think about it if you don't care about it. But for the parts that you care about, you need to be able to plug in either your own built solution or the best of breed so that you can uh be getting the results that you need.

SPEAKER_03Yeah. That's a that's an important one. I think the other is that when you think of how critical this factory is going to be to your company, I mean, in effect, it is the thing that produces your product.

SPEAKER_01But you're developing that.

SPEAKER_03Exactly. And so it's a very sensitive place to be bought into a fully integrated solution that now has complete pricing leverage over you, right? If you think about just the sorts of processes and workflows that you bake in, right, they're very specific, and that's part of what becomes your IP, your moat against competitors. But imagine if then all of that work you've built to differentiate yourself is now owned by someone else. And so they say, hey, everything that makes your company you is in our ecosystem, and so we're going to crank up the token cost, the token spend, et cetera.

SPEAKER_03And so we think that your factory needs to be built on an open modular framework that you can sort of trust to assess its own work, right? Fact optimizing the factory is like an important component of the factory, and so you need to trust it when it says, hey, this time you really do need to use the biggest model and you do need to spend 50% more on tokens. You don't want to be questioning those kinds of suggestions. Uh and then finally, it's like a big part of TESIL is we like to think of there's the rails that your factory runs on, and then there are the artifacts and knowledge, the context basically that powers those rails in the factory.

SPEAKER_03And for that, we believe that you should own those artifacts so that you can always pick up and move to another provider. Uh you basically own the secret sauce, right? So a great example of this with code review. We think that there is a general harness that should provide code review, but you don't want the brain of your code review to be locked inside that harness. You want to be able to say, look, we found a better tool, we're going to move to it. All of the work we've put into finely crafting our workflow, our style guide, the things that we've worked for.

SPEAKER_03That's just a skill checked into our repo. So we can go plug that into any brain.

SPEAKER_01Aaron Powell And I think so. This is very consistent with how we've generally been thinking about sort of context and skills and building those out, which is, you know, we we believe in the future you will have many agents because agents will specialize in different things. Uh we think you will need to sort of share context with them. Uh and similarly, we think you'll actually have multiple factories. You know, you'll have different factory lines or different sort of uh aspects that optimize for uh different different parts and different sort of you know stages of uh of development. And and really we're talking a lot about software factories over here, uh, but we expect very much that this sort of expands into uh agentic factories.

SPEAKER_01Yeah. Um and also like maybe it's worth pointing out that uh you know what while like all of this stuff it it could sound a little bit like a like a change from what we have been discussing uh all this time, right? Like we uh we've been talking about sort of scaling skills and governing them and uh and securing them, uh, and a lot about you know context and context is the new code, you know, and how do we think about that? Um so I guess it's uh it's worth maybe taking a moment a little bit to say, like this is we don't perceive this as a pivot, we see it as an expansion.

SPEAKER_01I guess how how does all of this conversation around scaling context, scaling skills, uh that you know, again, customers have a real pain around it? Yeah. How does that relate to the agent? You know, like over here we're starting saying loop engineering, you kind of alluded to harness engineering on it, which again probably needs like its own kind of conversation on the podcast. Um how uh how do you see the two interacting? Yeah.

SPEAKER_03Uh on the product team, there's always have this question of sort of what is our field to play on or not. And so you're always asking the question for a new feature. Like, does it make sense for us to solve this problem? And this is actually one of the easier choices or easier decisions. Uh, when we think of TESL's mission of agent enablement, we want to help you actually bring coding agents and you know all agents in the future to do real productive work for you. This just feels like a very natural extension of that. So in that regard, I think it's all part of the same goal, which is help you actually deploy and delegate work to agents effectively and get real productive work done.

SPEAKER_03Maybe from a more mechanical perspective, I think all of these are aspects of the same solution. So it really just sort of depends on where you're starting. So most companies uh that have gotten started with agents, they're starting to feel skill sprawl, they have hundreds, thousands of skills, they don't know which ones are good, they don't know where the duplicates are. Right. Those folks want to get started on the governance end of the spectrum. They're gonna say, help me inventory all of my skills, uh, use TESL to do a security review, find any vulnerabilities, then create policies to make sure that we never have this issue again.

SPEAKER_03They're gonna start doing review, quality review on skills, codifying their best practices. You can think of this as taking charge of a sort of grounds up upswell that you want to now make sure scales effectively across your company. Right.

SPEAKER_01And it's worth noting that that's also the the whole world of non-dev skills is where we've seen a lot of pickup and adoption, which is uh we help a lot of customers deal with kind of that world of they have their sales skills, their marketing skills, their product skills on it. Uh those worlds are generally not ready for words like factory. There are sort of a lot more around just I just want to sort of share best practices, basically usage packaged up in the form of skills and rules.

SPEAKER_03I think of this as the very sort of bottoms-up form of factory building. I increasingly I think of all of this as factory building. Uh the question is do you build a factory by focusing on the components first, right? Like finding your workflows, putting them into skills, getting uh your team trained up on how to work with agents, how to review their work? Or are you a bit more on the leading edge of things? You want to start factory first, and then as you get automated workflows running, you're gonna go in and decompose the components that matter that you then want to add in, things like governance or standardization.

SPEAKER_03So coming from this other direction, you might come in immediately with setup agentic code review, or agents can't work with our front-end layout, make it better, and then make sure they never get worse at it again, right? And so you're starting with these loops. And I think it's a great way to get started if you are introducing your team for the first time to agents, because this is very focused on making agents effective and delegating work to them. It's a quick path to value. Exactly.

SPEAKER_01And you're actually setting yourself up in a good spot.

SPEAKER_03Yeah. And it helps you also uh isolate the change as you work, right? You can have one team just get started with agents, make themselves a bit more effective. Uh you don't have to worry about the governance and the security parts at this point, because it's just a one team working on it. But at some point you're gonna want to start scaling that out, right? Like you'll have proven it with one team, they're effective, they've automated a lot of their work. They want to start interfacing with other teams in this automated fashion, and that's where these governance and standardization primitives come in. We say, okay, now I'm gonna start hat letting everyone in the company throw skills into this registry.

SPEAKER_03We see again and again is all of these things run at the pace of agents. And so the first week you'll say, Oh, I'm just getting started with skills. And then the second week, you're like, I have 15,000 skills. What happened? Right. So you kind of have to get these primitives in earlier than you probably would normally, but it really just depends on what are you trying to do first. Are you trying to bring agents across your organization, or are you trying to sort of go deep on some agentic flows and get them automated? Yep.

SPEAKER_01Cool, cool. Yep. So I I think um, you know, for for us, we try to build all of that in that type of kind of composable approach uh to uh to you know, kind of helping you build kind of that factory, that estate. So it's always in your control. It's your context, it's your plugins, it's your kind of workflows, and now it is sort of your loops and your uh your set of harnesses that we help you optimize. Um and I guess just as a side comment, you know, we focus very much here on sort of the agent's um uh uh advantages and the sort of new competency from terms of like Tesla helping you with engineering and uh uh harness engineering.

SPEAKER_01But you know the agent is also an interface for many other things, and we you know we love sort of seeing you know customers use it for customizing and defining their policy, for handling that inventory processes, for sort of building those out. So excited about the agent. And it's interesting how you know we we kind of grew to to accept and get used to uh in the web interface having a little agent chat uh on the side. And to say, fine, yeah, you have you know all of these things that you can invoke, but then you can have the agent to just perform a bunch of actions for me, whether it's on my sort of slide deck or in my analytics portal or whatever it is.

SPEAKER_01Yeah. Um but we we still think it's a slightly kind of bigger deal or change when it's on the command line interface. So in that sense, like it is also just a command line interface, and it will eventually make its way to the uh to the uh to the web interface as well.

SPEAKER_03Starting with the local CLI, it just kind of gives you the most flexibility. And so given TESL's overall approach to factory building, it just it seemed like a no-brainer. Let's start with the thing that gives people the most power, and then exactly to your point, coming very soon we'll have much more streamlined interfaces for folks who aren't comfortable with a command line or who just want something in a simpler, GUI interface, things like that.

SPEAKER_02Hey everyone, hope you're enjoying the episode so far. Our team is working really hard behind the scenes to bring you the best guests so we can have the most informative conversations about agentic development. Whether that's talking about the latest tools, the most efficient workflows, or defining best practices. But for whatever reason, many of you have yet to subscribe to the channel. If you're enjoying the podcast and want us to continue to bring you the very best content, please do us a favor and hit that subscribe button. It really does make a difference and lets us continue to improve the quality of our guests and build an even better product for you.

SPEAKER_01Alright, back to the episode. So uh we're kind of running uh running up on time here. Uh I want to maybe share kind of one learning uh from uh from the product building side of this, which I think is sort of useful and it's interesting. Uh or maybe even two, you know, one is it's just sort of reiterating the importance of ease of use, right? We're we're seeing this like in uh I I I I like talking about how you know even like in SNCC days, I would talk about uh ease of use for security and you know how uh for everything in life, there's how much you care about something and and how hard it is.

SPEAKER_01And you need to care more than it is hard. Uh and then and then you act. Um and so it's interesting to see the action over here. And I I I think one of the things we're trying to address in terms of ease of use. Is uh is is just by the ease of use of getting into this business. It it has kind of a newer problem, and it it's not a new problem that you can't keep up, but it's a much bigger problem right now on it. So the agent kind of embodies a bunch of that knowledge. So, you know, yes, technically you can run it with whatever, you know, with your codex, with your cloud, with your sort of Gemini, but it's uh it's uh it's you need to know what you're doing and it's a lot of work, and then whatever it is you thought you knew, you know, like loop engineering is like a few weeks old and my best you know, in terms of a uh a term.

SPEAKER_01And so capture that knowledge, it's about ease of use of uh of the of the UX, being able to run a bunch of these things. It's about ease of use with sort of a Tesla providing a bunch of these tools around it, so you don't need to say, okay, you can do this, but now you need to equip yourself with seven different sort of foundations on it, which again over time you might modify, you might switch, you know, you sort of push us to sort of build better tools. Uh and and I guess it's about the ease of use feedback loop, right? Because what we've seen is we we created tools, we gave them to users, we wanted to make it easy, so we gave them skills as well, and they ran, but as they would run them in their sort of coding agent of choice, uh it was it was hard for us to fix problems like we've seen.

SPEAKER_01It's hard to see visibility, like as a product developer, you want to be able to see what's going on so that you can improve. Uh, it was hard to fix issues, you know, if the agents went sideways or a new whatever uh anthropic model sort of uh you know suddenly became less obedient, which we've had many uh uh many uh many cases of that, uh, or tuning it. And so the harness gives us that. So I guess as I as I think about uh uh and that this kind of spills a bit into my sort of second view, is that increasingly I think that the the shape of a product in the AI era is sort of these like four components, which is a set of tools that you build, which we used to call in like the pre-AI era products.

SPEAKER_01Those are kind of the capabilities, but now we think about them as tools, a set of skills, a kind of embodied expertise, uh, a harness to be able to provide a UX and a bundle, all of those things. You know, this is our harness, we also help you build your harness and the likes. Uh, and then some form of control center or like central repository for collaboration, especially as you go across time and across people to do that, uh, which we offer with a platform. So it was an interesting kind of learning process here.

SPEAKER_03The way that I've sort of brought it together when thinking about designing new products and maybe like a very concrete way is that like you said, ease of use has always mattered, but agents have added a few new layers, especially if you're thinking about DevTool products, which is that historically I think DevTools have focused a lot more on providing expressive power. Like make sure that you have really modular, composable primitives to do high-value tasks. And there was just sort of an expectation that the value is going to be enough that as a developer, you will learn my new vocabulary, you will stitch them together, you will do a lot of building on your own.

SPEAKER_03And I think the first thing to really internalize about agents is that they've really made all of us insatiable, like outcome-oriented machines, right? Gone are the days where you say, oh yeah, to do this, just call this m-call this command, then this command, then this command, and you know, they're all like you got to learn a bit, but no, it's worth it. And then now it's like, I'm gonna tell you what I want and I expect everything to happen. And so that sort of end-to-end, I want to speak in outcomes, I don't want to speak in the language of your product is has never been more extreme in this moment.

SPEAKER_03I think the the second is the usability of knowledge become is like supercharged, right? Agents are changing so fast, they're changing the industry so fast that not only is there just a lot to learn because there's all these new concepts coming out, but learning is no longer a one-time event. I mean, we've always had continual learning, but now it's continual learning means like daily or weekly. And so I think a significant portion of usability that you can provide is handling that on behalf of your users, keeping things up to date for them.

SPEAKER_03Uh and then maybe an outshoot of that, as you yourself become more agent-enabled as a product company, one thing that we have found is quickly your rate of shipping features will start to outstrip your GTM motions, eventually just your user's ability to ingest the changes. And so you sort of end up getting back into this place where you have to provide an agentic interface that is keeping up with the change of your product so that users can stay focused on the thing that is stable, which is their business and what they want to be doing.

SPEAKER_03And then the agent is constantly updating and translating that into the latest and greatest in your product.

SPEAKER_01Yeah. Yeah, it's agents all the way down. Yeah, yeah, yeah.

SPEAKER_03The answer is always more agents.

SPEAKER_01Yeah, yeah, indeed. So, you know, lots of exciting things. And it's worth in the talking about learning and talking about sort of knowledge on it, uh, worth noting that we're actually also launching uh just now uh TESL.io slash learn, which has some interesting agentic patterns and has sort of education capabilities. Uh so hopefully people check that out. This episode was dedicated to the TESL agent, but you know, there's sort of uh more uh more that you know we've been uh we've been chipping as the as the pace picks up. Um so before we close off, uh Drew, just uh a couple of words about what what happens next.

SPEAKER_01Now we're so we launched the agent, you know what uh what happens next. And then how can people get started?

SPEAKER_03Yeah, uh so number one, we've just launched, we're really excited to get feedback from folks. Uh sort of always the name of the game is you can expect the Tesla agent to get faster, cheaper, smarter at everything we've talked about here. Uh and then from there, I think we're really just focused on how do we make it easier, more seamless to go from any starting point you may be at with scaling skills or exploring a few automations to how can we get you towards that factory vision faster with less effort, less uncertainty, lack of confidence as you go.

SPEAKER_03Uh but really focused on that incremental path. I think that's the main thing to expect from Tesla is we're the we want to be the tool that helps you go from where you are today to factory. We're not just the, hey, if you can throw everything out and build a greenfield code base, you can do the cutting edge. So expect to see more there.

SPEAKER_01Yeah, indeed. And this this notion of uh you know, we talked about sort of the the catchphrase, right, from scaling skills to uh to a full-on factory. Yeah. You know, maybe there's loops somewhere sort of in the in the process of it, but it's uh it's okay. Everybody's behind. Yes, yeah.

SPEAKER_03So let's sort of uh gradually let's no one feels comfortable, everyone wants to go faster, but we're here to help you move sort of through that process. Uh in terms of how to get started, it's pretty easy. Just go to the website, download the Tesla CLI, uh, and then ask it to do something for you. So TESL agent, hit enter, just like every other agent. It'll open a session, ask it to set up code review, ask it to delegate some work to AI for you. All of those things will work just fine. It's an agent, so you can ask it to do other things as well. Uh and then over time, more and more of it will be put into automation just as you as you work with the agent.

SPEAKER_01Yeah. And I think if you want to do the experiment, you can also try out uh having different team members run the Tesla agent because it does look a little bit at their logs. And so there's a little bit of an element of if you heard that someone is having a problem, uh having them try the Tesla agent, that might be an interesting experiment.

SPEAKER_03Yes, yeah, yeah. It's a great way uh the Tesla agent both can look at your local logs, it can also help you get your logs into a communal space. And as a point of getting started, sometimes just sitting down with the last month's worth of coding agent sessions and just asking what's broken, what's taking a lot of our time, will yield some really interesting results. Yeah.

SPEAKER_01So I think that's it for us. Hopefully you find the TESL agent interesting. We'd love to have you try it out and share feedback. You know, this is very much about iterating. Hopefully, you're well familiar that we're all about the community uh at uh TESL. So join the AI Native Dev Discord, share comments uh and feedback that you have around the product, you know, things you love, things you uh want to see us change. Uh, we're super, super excited about the TESL agent over here. Probably the most important thing. We're getting a little bit told off uh a little bit about uh uh the the you know just sort of how much we talk about it.

SPEAKER_01Uh but very, very keen to see it come to life. You know, early users, thanks a lot for all the great feedback and evolutions uh for it. Uh and yeah, try it out and tell us uh what you think. Yeah, can't wait. And with that, thanks for tuning in to uh this episode and hope you join us for the next one.

SPEAKER_02The AI Native Dev is brought to you by Tesla, the package manager for skills and context. Your hosts are Guy Pajani and me, Simon Maple. Our producer is Tom Dowler. The AI Native Dev is not just a podcast, it's a community. And we host monthly meetups at the TESL offices in central London. Visit Tesla.io forward slash community to learn more, and I hope to see you there.

Open the transcript file

Hosts and Guests

Nobody is credited on this episode yet.

Credit the people on this episode

Be the first to rate this episode

More episodes

All episodes
  1. Your Software Factory Needs a Bill of Materials | Daniel Meppiel

    Nov 19, 20261 hr 1 minAudio

    Developers are about to write skills instead of code, and Microsoft's Daniel Meppiel argues the software factory that runs them needs versioning, a bill of materials and signed receipts before enterprises will trust it....

    Credit the people on this episode

  2. Paul Stack: I'll Never Write Infrastructure as Code Again

    Nov 17, 20261 hr 2 minAudio

    Paul Stack helped build Terraform. Now he says he'll never write another line of infrastructure as code, because an agent harness runs his team's production infrastructure instead. Watch all the AI DevCon NYC 2026...

    Credit the people on this episode

  3. Edith Harbaugh: Code Is Cheap. The Last Mile Isn't.

    Nov 10, 202649 minAudio

    Automated software delivery is moving faster than the people who used to approve every release. LaunchDarkly co-founder and CEO Edith Harbaugh tells Guy Podjarny why rollback should be autonomous, why one-shot coding...

    Credit the people on this episode

  4. Maggie Appleton: Agentic Coding Has Outgrown the Text Box

    Nov 3, 202652 minAudio

    Agentic coding has outgrown the text box. Maggie Appleton, staff research engineer at GitHub Next, argues that walls of CLI output and AGENTS.md files serve coding agents far better than the humans steering them. She...

    Credit the people on this episode

  5. Caleb Sima: AI Attackers Move at Machine Speed

    Oct 27, 202655 minAudio

    AI attackers now move at machine speed, while most security teams still move at meeting speed. Former Robinhood CSO Caleb Sima has seen an AI attacker up close, and he argues the only way to keep up is to take humans...

    Credit the people on this episode