How Claude Code Works

Talk transcript

1. 0:00

   [upbeat electronic music] So welcome to the last workshop.

2. 0:22

   Um, you made it. Congrats. [laughs] Yay. [audience clapping] Out of, like, 800, uh, people, you're the, you're the last standing, uh, so the very, very dedicated engineers. Uh, yeah, so this one's a weird one.

3. 0:36

   I got in trouble with Anthropic, with Anthropic on this one, uh, obviously because of the title. [laughs] I actually also gave him the title, and I was like, "Do you wanna change it?"

4. 0:43

   And he was like, "No, I just roll with it." [laughs] It's kind of funny. [laughs]

5. 0:47

   Uh, uh, so, so yeah, this is not officially endorsed by Anthropic, but we're hackers, right? And Jared is, like, super dedicated. He's, um... Uh, and the other thing I also, like, really enjoy is featuring, like, notable New York AI people, right?

6. 1:01

   Like, so don't take this as, like, this was the only thing that Jared does. He has a whole startup that you should definitely ask him about. Um, but, like, you know, I'm just really excited to feature more content from local people.

7. 1:13

   So yeah, Jared, take it away.

8. 1:15

   Thank you very much. Thank you very much, and what an amazing conference. Very sad we're ending it, but hopefully it'll be a good ending here. Um, and yeah, uh, my name is Jared.

9. 1:26

   Uh, this'll be a talk on how Claude Code works. Again, not affiliated with Anthropic. Uh, they don't pay me. I would take money, but they don't. Um, but we're gonna talk about a few other coding agents as well, and kind of the high level goal that I'll go into is, me personally, I, I'm a big user of

10. 1:47

    all the coding agents, as is everyone here, and they kind of exploded recently. And as a developer, I was curious what changed, what made it finally... What made coding agents finally be good.

11. 2:00

    So let's get started. I'll start about me. I'm Jared. You can find me, I'm [REDACTED:username] on X, on Twitter, whatever. Um, I'm building the workbench for AI engineering, so, uh, my company's called PromptLayer.

12. 2:13

    We're based in New York. You can kind of see our office here. It's like a little building, so it's blocked by a few of the other buildings. So we're, we're a small team.

13. 2:21

    We launched the product three years ago, so, uh, long for AI, but small for everything else. And, uh, yeah, what, kind of our core thesis is that we believe in rigorous prompt engineering, rigorous agent developing, development, and we believe that the product team should be involved, the engineering team should be v- involved.

14. 2:40

    We believe if you're building AI lawyers, you should have lawyers involved, as well as engineers. Um, so that's kinda what we do, uh, processing millions of LLM requests a day, and a lot of the insights in this talk come from just conversations we have with our customers on how to build coding agents and stuff like that.

15. 2:56

    And al- also feel free throughout the talk, we can make this casual, so if there's anything I say, if you have a question, feel free to just throw it in.

16. 3:04

    Uh, and I spend a lot of my time kind of dogfooding the product. It's kinda weird, the job of, of a founder these days, because it's half, like, kicking off agents and then half just using my own product to build agents.

17. 3:15

    And it feels weird, but it's kinda fun. And, uh, yeah, the last thing I'll add here is I'm a big enthusiast. We literally rebuilt our engineering org around Claude Code.

18. 3:26

    I think the hard part about building a platform is that you have to deal with all these edge cases and, oh, uh, we're uploading data sets here, it doesn't work, and you could die a death by a thousand cuts.

19. 3:38

    So we made a rule for our engineering organization, if you can complete something in less than an hour using Claude Code, just do it. Don't prioritize it. And we're a small team on purpose, but, uh, it's helped us a lot, and I think it's really taken us to the next level.

20. 3:54

    So I'm a big fan, and let's dive into how these things work. So this is what I, as I was saying, the goal of this talk. First, why have these things exploded?

21. 4:03

    What is the... What was the innovation? What was the invention that made coding agents finally work? If you've been around this field for a little bit, you know that, uh, a lot of these autonomous coding agents sucked at the beginning.

22. 4:17

    And, uh, we all tried to use them, uh, but it's, it's night and day. Uh, we'll dive into the internals. And, and lastly, we'll, like, everything in this talk is oriented around how do you build your own agents and how do you use this to do AI engineering for yourself.

23. 4:36

    So let's just go, uh, talk about history for a second here. How did we get here? Uh, everybody knows, started with, uh, you remember the workflow of you just copy and paste your code back from ChatGPT back and forth, and that was great, and that was kind of revolutionary when it happened.

24. 4:53

    Uh, step two, when Cursor came out, if we all remember, it was not, not great software at the beginning. It [laughs] was just the VS Code fork with the Command+K, and we all loved it.

25. 5:06

    But, uh, now, now we'll no- we're not gonna be doing Command+K anymore. Then we got the Cursor assistant, so that little agent back and forth, and then Claude Code.

26. 5:15

    And honestly, in the last few days since I made this slide, maybe there's a new version we could talk about here. And, uh, at the end I'll talk about, like, kind of what's next.

27. 5:23

    But this is how we got here, and this is really, I think the Claude Code is kind of this headless, uh, not even, this, this new workflow of not even touching code.

28. 5:33

    And it has to be really good. So why is it so good? What, what was, uh, what was the big breakthrough here? Let's try to figure that out. And again, throw this in one more time, these are all my opinions, uh, and what I think is the breakthrough.

29. 5:47

    Maybe there's other things, but simple architecture, I think a lot of things were simplified with how the agent was designed. And then better models, better models, and better models.

30. 5:58

    Uh, I think the- A lot of the breakthrough is kind of boring in that it's just Anthropic releasing a better model that works better for th- these type of tooling calls and these type of things.

31. 6:10

    But the simple architecture relates to that. So we could di- dive into that. The architecture, and, and this is our little... You'll see, uh, prompt wrangler is our little mascot for our company, so we made a lot of graphics for these slides.

32. 6:24

    But, uh, basically, give it tools and then get out of the way is what a one-liner of the architecture is today. I think

33. 6:35

    if you've been building on top of LMS for a little bit, this has not always been true. Obviously, tool calls haven't always existed, and tool calls is kind of this new abstraction for JSON formatting, and if you remember the GitHub libraries like JSON Former and stuff like that in the olden days.

34. 6:51

    But give it tools, get out of the way. Uh, the models are built for these things and being trained to get better at tool calling and better at this.

35. 7:01

    So the more you wanna over-optimize, and every engineer, uh, including my- especially myself, loves to over-optimize. And when you first have an idea of how to build the agent, you're gonna sit down and say, "Oh, and then I'm gonna prevent this hallucination by doing this prompt, and then this prompt, and then this prompt."

36. 7:17

    Don't do that. Just a simple loop and get out of the way, and just delete scaffolding, and less, less scaffolding, more model is kind of the tagline here. And, you know, this is, uh, the leaderboard from this week.

37. 7:34

    Obviously, these models are getting better and better. Uh, we could have a whole conversation, and I'm sure there's been many conversations about, is it slowing down, is it plateauing?

38. 7:43

    It doesn't really matter for th- [laughs] this talk. It-- we know it's getting better, and they're getting better at tool calling, and they're getting better optimized for running autonomously. And don't...

39. 7:54

    This is... I, I think Anthropic calls this, like, the AGI pill to-- way to think about it, is don't try to over-engineer around model flaws today, because a lot of the things will just get better, and you'll be wasting your time.

40. 8:09

    So here's the philosophy the way I see it of Claude Code. Ignoring embeddings, ignoring classifiers, ignoring pattern matching. The-- we had this whole RAG thing. Actually, Cursor's bringing back a little bit of RAG in how they're doing it, and they're mixing and matching, but I think the genius with Claude Code is th- they, they scratched all this

41. 8:29

    and they said, "We don't need all these fancy, uh, paradigms to get a- around how the model's bad. Let's just make a better model and then let it, let it cook." [laughs]

42. 8:39

    And, uh, just leaning, uh, uh, on these tool calls and

43. 8:46

    simplifying the tool calls, which is a very important part, part. Instead of having a workflow where the master prompt can break into three different branches and then go into four different branches, there, there's really just a few simple tool calls, uh, including Grep instead of RAG, and, uh...

44. 9:06

    Yeah, and that's kinda what it's trained on. So, uh, these are very optimized tool-calling models. So this is,

45. 9:15

    uh, [laughs] the zen of Python if, if you guys are familiar, if you do import this in Python. This is... I love this philosophy when it comes to building systems, and I think it's really

46. 9:26

    apt for how Claude Code was built. So really just simple is better than complex. Complex is better than complicated. Flat is better than nested. This is, this is all you need to...

47. 9:36

    This is the whole talk. [laughs] This is all you need to know about how Claude Code works and why it works specifically. That just, in eng-- We're going back to engineering principles such that simple design is better design.

48. 9:49

    Uh, I think this is true whether you're building a,

49. 9:55

    uh, database schema, uh, but this is also true when you're building these auten- au- autonomous coding agents. So let's... I'm gonna now kinda break down all the specific parts of this coding agent and, uh, why I think they're interesting.

50. 10:12

    So the first is the constitution. Now, a lot of this stuff we kinda take for granted, even though they started doing it a month or two ago, or maybe three or four months ago.

51. 10:20

    So this is the Claude MD, Codex or others use Agents MD. The interesting thing, uh, I think, I assume most of you know what it is. Uh, it's, again, it's where you put the instructions for your library, but the interesting thing about this is

52. 10:36

    it's basically the team saying, we don't need to over-engineer a system where the model f- first researches the repo and Cursor, uh, like Cursor 1.0, a- as you know, makes a vector DB locally to understand the repo and kind of does all this research.

53. 10:55

    They're just saying, "Eh, just put a markdown file. Let the user change stuff when they need. Let the agent change stuff when they need." Very simple and kind of goes back to prompt engineering, which I'm a little biased towards because Prompt Layer is a prompt engineering platform, but, uh, everything's prompt engineering at the end of the day,

54. 11:13

    or context engineering. Everything is how do you, uh, how do you adapt these general purpose models for your usage? And the simplest answer is the best one here, I think.

55. 11:24

    So this, this is the core of the system. It's just a simple master loop. Uh, and, and this is actually kind of revolutionary considering how we used to build agents.

56. 11:38

    Everything in Claude Code and, and all the coding agents today, Codex and, and, and, uh, the new Cursor and AMP and all that, it's just one while loop with tool calls just running the master while loop, calling the tools, and going back to the master while loop.

57. 11:52

    This is [laughs] basically four lines of what it's called. I think they call it N0 internally, uh, at least based on my research. But while there are tool calls, run the tool, give the tool results to the model, and do it again until there's no tool calls, and then Ask the user what to do.

58. 12:11

    The first time I did this, uh, the first time I used tool calls, it was very shocking to me that the models are so good at just knowing when to keep calling the tool and knowing when to fix their mistake.

59. 12:22

    And I think that's one of the most interesting thing about LLMs, just they're really good at fixing mistakes and being flexible. And the more, just going back, the more you lean on the model to explore and, uh, figure it out, the better and more robust your system is gonna be when it comes to better models.

60. 12:45

    So, so these are the core tools, uh, we have in Claude Code today, and to be honest, these change every day. You know, they're doing new releases every few days, but these are the core ones that I found most interesting to talk about.

61. 13:01

    Uh, there could be 15 tomorrow. There could be down to five tomorrow, but this is what I find interesting. So first of all, read. Uh, yeah, they could just do a cat, uh, but what's interesting is read is we have token limits.

62. 13:16

    So y- if you've used Claude Code a lot, you've seen that sometimes it'll say, "This file's too big," or something like that. That's why it's worth building this read tool.

63. 13:25

    Grep glob. Uh, this one's very interesting too because it goes against a lot of the wisdom at the time of using RAG and using vectors. And I'm not saying RAG has no place by the way either, but in these general purpose agents, Grep is good and, and, and Grep is, uh, how users would do it.

64. 13:44

    And I think that's actually a high level point here. As y- as you're, a- as I'm talking about these tools, remember, these are all human tasks. They're not... We're not making up a brand-new tool for the model to use.

65. 13:56

    We're kind of just mimicking the human actions and what you and I would do if we were at a terminal trying to fix a problem. Edit. Edit makes sense.

66. 14:04

    I think the interesting thing to note in edit is it's using diffs, and it's not rewriting files most of the time. Uh, way faster, way m- way, uh, less context used, but also way less,

67. 14:17

    uh, issues. Uh, if, if I asked you to... If I, if I gave you these slides and asked you to review the slides, and you read it and had to write down all the slides for me in your new revisions versus if you could just cross out things in the paper, the crossing out is way easier.

68. 14:33

    Diff is kind of a natural thing to prevent mistakes. Bash. Bash is, uh, Bash is the core thing here, I think. You could probably get rid of all these tools and only have Bash, and the first time I saw this, when, when you run something in Claude Code and Claude Code creates a Python file and then runs

69. 14:53

    the Python file, then deletes the Python file, that's, that's the beauty of why this thing works. So Bash is the most important, I'd say. Web search, web fetch. Uh, the interesting thing about these is they mo- move it to a cheaper and faster model.

70. 15:08

    So for example, if you're building a, some sort of agent maybe on your platform, and you're building an agent, and it needs to connect to some endpoints, some list of endpoints, might be worth to bring that into a kind of sub tier as opposed to that master while loop.

71. 15:24

    That's why this is its own tool. To-dos. Uh, we've all seen, seen to-dos. I'll talk about it a little bit more later, but keeping the model on track, steerability, and then tasks.

72. 15:34

    Tasks is very interesting. It's context management. It's how do we, how do we run this long process, read this whole file without cluttering the context? Because the biggest enemy here is when your context is full, the model gets stupid [laughs] for lack of better word.

73. 15:50

    So basically, Bash is all you need. Uh, I think this is the one thing I wanna drill down. The amazing thing about... There's two amazing things about Bash for coding agents.

74. 15:59

    The first is that it's simple, uh, and it does everything. It's, it's very robust, but the second thing that's equally important is there's so much training data on it because that's what we use.

75. 16:11

    It's not... It's the reason that models are not as good at Rust or less common programming languages, just because there's less people doing it.

76. 16:22

    So it's really the universal adapter. Um, you've thousands of tools. You could do anything. Uh, this is that Python example I gave. I, I, I always find it so cool when it does the Python script thing or creates tests, and I always have to tell it not to.

77. 16:35

    But it... All these shell tools are in it, and this is... I mean, I find myself using Claude Code to spin up local environments where normally I'd have like five commands written down on some file somewhere, and then they get out of date.

78. 16:49

    It's really good at figuring this stuff out and running the stuff you'd wanna do. Uh, and it specifically lets the model try things.

79. 16:58

    So, uh, yeah, the other suggestions here and the tool usage, uh, I think

80. 17:06

    there's a little bit of a system prompt, uh, that tells it which to use and when to use which tool over which, and this changes a lot, but the, these are kind of like the edge cases and the corners you find the model getting stuck in.

81. 17:17

    So reading before editing, uh, they actually mas- make you do that using Grep, the tool, instead of the Bash. So if you look at the tool list here, there's a special Grep tool.

82. 17:30

    Uh, there could be a lot of reasons for that. I think security is a big one, uh, and sandboxing, but then also just that token limit thing. Running independent operations in parallel, uh, so kind of pushing the model to do that more, and then also, like, these trivial things like quoting paths with spaces.

83. 17:47

    It's just the common, common things I'm sure they're just dogfooding a lot at Anthropic, and they find it, and they're like, "All right, we'll throw it in the system prompt."

84. 17:55

    Okay, so let's talk about to-do lists. Uh, now again, a very common thing, but was not a common thing before. The, the [laughs]... So this is actually, uh, I think a to-do list for, from some of my research for this slide deck.

85. 18:09

    Um, but- The really interesting thing about to-do lists is that they're structured, but not structurally enforced. So here are the rules, one task at a time, uh, mark them completed.

86. 18:24

    This is kind of stuff you would expect, uh, keep working on the in progress if there's block, uh, blocks or errors, and kind of break up the tasks into different instructions.

87. 18:36

    But the most interesting thing to me is it's not enforced deterministically. It's purely prompt-based. It's purely in the system prompt. It's purely because our models are just good at instruction following now, and this would not have worked a year ago.

88. 18:51

    This would not have worked two years ago. Um, there's tool descriptions at the top of the system prompt. We're kind of, uh, injecting the to-dos into the system prompt.

89. 19:02

    Uh, there's... They're not, uh, but it, but it's not enforced in actual code. And again, uh, maybe there's other agents that take an opposite path. Uh, I just found this pretty interesting that this, at least as a user, makes a big difference, and it doesn't even see...

90. 19:18

    It seems, it was, it seems like it was very simple to implement, almost a, [chuckles] a weekend project someone did and seemed to work. Could be wrong about that, about that as well.

91. 19:27

    But, uh, um, so yeah, it, it's literally a function call. Uh, it, it's the first time you ask something, the reasoning exports this to-do block, and I'll show you what the structure is on the next slide.

92. 19:40

    Uh, there's IDs. There, there's some kind of structured schema and determinism, but

93. 19:47

    it, it's just injected there. So here's a example of what it could look like. You get a version, you get your ID, uh, a title of the to-do, and then it could actually inject evidence.

94. 19:59

    So this is, uh, seemingly arbitrary blobs of data it could use, and the IDs are hashes that it could then refer to, title something human readable. But this is, uh, just another way to structure the data.

95. 20:14

    And in the same way that you're gonna organize your desk when you work, this is how we're trying to organize the model.

96. 20:21

    So I think there's, uh, these are kind of the four benefits we're getting. We're forcing it to plan. Uh, we get to resume after crashes, uh, Claude Code fails.

97. 20:33

    I think UX is a big part of this. As a user, you know how it's going. It's not just running off in a loop for forty minutes without any, uh, signal to you.

98. 20:42

    So UX is non-negligible, even though UX might not make it a better coding agent, it might make it better for us all to use, and, uh, the steerability one.

99. 20:52

    So here's two other parts that were under the hood. AsyncBuffer, so they called it H2A. Uh, it's kind of, uh, the IO process and how to decouple it from reasoning, and, and how to manage context in a way that you're not just stuffing everything you're seeing in the terminal and everything back into the model, which again, context

100. 21:12

     is our biggest enemy here. It's gonna make the model stupider. So we need to, uh, be a little bit smart about that and, and how we do compact and how we do summarization.

101. 21:22

     So here you see when it reaches capacity, it kind of drops the middle, summarizes the head and tail. Um, then we have the, uh, uh, that's the context compressor there.

102. 21:32

     So what is the limit? Ninety-two percent it seems like something like that. Uh, and, and how does it, how does it save long-term storage? That's actually another kind of advantage of Bash, in my opinion, and having a sandbox.

103. 21:47

     I would even make a prediction here that all your, all ChatGPT windows, all Claude windows are gonna come with a sandbox in the near future. It's just so much better because you can store that long-term memory, and I do this all the time.

104. 22:00

     I have, I have Claude Code skills for deep research and stuff like that, and I'm always instructing it, "Save markdown files," because the shorter the context, the quicker it is and the smarter it is.

105. 22:12

     So this is what I'm most excited about. We don't need DAGs like this. We...

106. 22:18

     I'll give you, I'll give you a real example. Uh, so some users at Prompt Layer, uh, different agents like customer support agent, basically everybody was building DAGs like this for the last two, two and a half years.

107. 22:32

     Uh, and it was crazy. Hundreds of nodes of, okay, this, if this user wants a refund, route them to this prompt, if they want this, and a lot of, uh, classifying prompts.

108. 22:45

     The advantage of this is you can kind of guarantee there's not gonna be hallucinations or guarantee there's not gonna be

109. 22:52

     refunds to people who shouldn't be having refunds or kind of the, that pro... It, it solves the prompt injection problem because if you're in a prompt that purely classifies it as X or Y, injecting doesn't really matter, especially if you throw out the context.

110. 23:05

     Now, we kind of brought back, bring back that attack vector, but the, but the major benefit is we don't have to deal with this web of engineering, uh, madness. [chuckles]

111. 23:15

     And, uh, it just, it's 10X easier to develop these things, 10X more maintainable, and it actually works way better because our models are just good now.

112. 23:24

     So this is, this is kind of a takeaway is rely on the model. Uh, when in doubt, don't, don't try to think through every edge case and think through every if statement.

113. 23:36

     Just rely on the model to explore and figure it out. And I was actually, two days ago, I think, or yesterday, sometime this week, I was doing a, uh, a experiment on our dashboard to add like trying these browser agents, and I wanted to see if I could add little titles to all our buttons, and it would

114. 23:55

     help the agent navigate our website automatically. And it actually made it worse, surprisingly. Uh, and maybe I could run it again, and maybe I did something wrong with this test, but it made the agent navigate Prompt Layer worse because it was getting distracted because I was telling it, "You have to click this button, then you have to

115. 24:11

     click this button," and then- It's, it, it didn't know what to do. So it's better to rely on exploration. You have a question?

116. 24:19

     Yeah. I'll, I'll push back a little bit.

117. 24:22

     Please.

118. 24:23

     I'll admit any scaffolding we create today to resolve the idiosyncrasies of limitations will be, like, that'll be obsolete three to six months. Even if that's the case, they help a little bit today, I don't...

119. 24:40

     How do you balance that, like, wasted engineering to solve a problem we only have for three months?

120. 24:46

     It's a great question. So just to repeat, uh, the question is basically,

121. 24:51

     uh, what is the trade-off between solving the actual problems we have today, and if you're relying on the model that can't do it yet, but it'll be able to do it in three months, right?

122. 25:00

     Um, it's case by case. It depends what you're building. If you're building a chatbot for a bank, you probably [laughs] do wanna be a little bit more comp- be careful.

123. 25:09

     To me, the happy middle ground is to use this agent paradigm of a master while loop and tool calls, but make your tool calls very rigorous. So I think it's okay to have a tool call that looks like this or looks like half of this, uh, in the same way that Claude Code uses read as a tool

124. 25:29

     call or grep as a tool call. So for the edge cases,

125. 25:34

     throw it in a structured tool that you can then eval in version and stuff like that, and I could talk, I'm gonna talk a little bit more about that later.

126. 25:41

     But throw it in that structured tool, but for everything else, uh, for the exploration phase, leave it to the model or throw some system prompt. Uh, so it's a trade-off, and it's very use case dependent, but I think it's a good question.

127. 25:58

     Thank you. So yeah, uh, just back to Claude Code, uh, we're, we're getting rid of all this stuff. We're saying we don't want ML-based intent detection. We don't want regex.

128. 26:08

     We don't want the... I mean, it uses regex a little bit, but we don't want regex baked into it. We don't want classifiers. And, and there was a long time, we actually built a product for PromptLayer.

129. 26:17

     We never released it because it was only a prototype of using a ML-based, like a non-LLM-based classifier in your prompt pipeline instead of LLMs. And a lot of people have a lot of su- success with it, but it, it feels more and more like it's not gonna be that helpful unless cost is a huge concern for you.

130. 26:36

     And even then, cost is, the smaller models, is going less and less as, uh, kind of financial engineering between all these companies pays for our tokens. [laughs] Um, so Claude does also s- this smart thing, I think, with the trigger phases.

131. 26:52

     You know, you have think, think hard, think harder, and ultra think is my favorite. Uh, and this lets us use the reasoning budget, the reasoning token budget, as another parameter that the model can adjust.

132. 27:05

     And this is actually ... The model can adjust this, but this is how we force it to adjust. And as opposed to you could make a tool call for hard planning, and actually there's some coding agents that do this, or you can, uh, let the user specify it and then just on the fly change it.

133. 27:23

     So this is, this is one of the biggest topics here, sandboxing and permissions. I'm gonna be completely honest, it's the most boring part of this [laughs] to me because I just run it on YOLO mode half the time. [laughs]

134. 27:35

     Um, it's, uh, [laughs] some people on our team actually dropped all their local databases, so you do have to be careful. Uh, so, uh, you know, w- we don't YOLO mode with our enterprise customers, obviously.

135. 27:49

     But, uh, I, but, but I think this stuff is ... It feels like it's gonna be solved, but, but we do need to know how it works a little bit.

136. 27:57

     So there's a big issue of inj- prompt injection from the internet. If you're connecting this agent that has shell access and you're doing a web fetch, that's a pretty big attack vector.

137. 28:11

     Uh, so there's some containerization of that. There's s- blocking URLs. You could see Claude Code's pretty annoying about can I fetch from this URL? Can I do this? And it kind of puts it into a sub-agent.

138. 28:23

     And, uh, yeah, uh, most of the, most of the complex code here is in this sandboxing and permission set. I think there's this whole pipeline to gate batch commands, so

139. 28:36

     it, depending on the prefix, is how it goes through the sandboxing environment. And a lot of the other models work differently here, uh, but this is how Claude Code does it.

140. 28:46

     I'll explain the other ones later at the end.

141. 28:51

     The next topic, uh, of relevance here is sub-agents. Uh, so this is going back to context management and this, this problem we keep going back to of the longer context the, the stupider our agent is.

142. 29:02

     This is a, this is an answer to it. So using sub-agents for specific tasks, and the key with the sub-agent is it has its own context, and it feeds back only the results.

143. 29:12

     And this is how you don't clutter it. So we got the researcher. These are just four examples, researcher, docs reader, test runner, code reviewer. In that example I was talking about earlier when I added all the tags to our website to let the agent do it better, I, obviously, I used a coding agent to do that, and

144. 29:29

     I said, "Read our docs first and then do it." And it's gonna do this in a sub-agent. It's gonna feed back the information. And the, the key thing here is the forks of the agent and how we aggregate it back into our main context.

145. 29:44

     So here's an example. I think this is actually very interesting. I wanna call out a thing or two here. So task is what a sub-agent is. We're giving task two things, description and a prompt.

146. 29:56

     The description is what the user's gonna see, so you're gonna say, "Task, uh, find default chat context instantiation," or something. And then the prompt, you're gonna give a long string, which is really interesting because now we have the coding agent prompting its own agents.

147. 30:13

     And I've actually used this paradigm in agents I've built for our product. Uh, if you can- You can just have the agent stuff as much information as it wants in this string, and if we're going back to relying on the model, if this task returns an error, now it could stuff even more information, and let it solve

148. 30:33

     the problems. It's better to be flexible rather than rigid.

149. 30:37

     If I was building this, I would consider switching a string to maybe an object here, uh, depending on what you're building, and maybe let it give actually more structured data.

150. 30:46

     Yes.

151. 30:47

     So I can see this prompt has quite a couple sentences. Is that in the main agent? Is that taking the context of the main agent, or is there, like, you know, some sort of intermediate step where, um, the sub-agent double reads over, you know, like, what the main agent is doing, and then, you know, kind of generates

152. 31:04

     its own slightly longer prompt or something?

153. 31:06

     Right. So the question is: Does the task just get the prompt here, or does it also get your chat history? Is that the question?

154. 31:15

     Yeah.

155. 31:15

     No, the, the question is, is, are all of the... I have my main agent. Are, is all of this in the system prompt of the main agent to inform how that prompts the sub-agent?

156. 31:24

     No, no.

157. 31:25

     Okay.

158. 31:25

     Like, it's not in the system prompt. It's in the whole context. Is the, all of this the context of the main agent?

159. 31:33

     The task it calls, or, or the, you're saying the structure for the task.

160. 31:37

     This whole JSON array, like, or, or-

161. 31:39

     Yes

162. 31:40

     ...

163. 31:40

     So this is a tool call. So the tool call structure of what a task is, is in the main agent. Uh, and then these are generated on the fly.

164. 31:49

     Uh, so as you wanna write a task, it's generating the description and the prompt. Task is a tool call that could be run in parallel, and then they're returning the results of it.

165. 32:00

     Hopefully, that helps.

166. 32:02

     Thank you.

167. 32:03

     Um, so we could go back to the system prompt. So there's some leaks of the Claude Code system prompt, so that's what I'm basing this on. Uh, you can find it online.

168. 32:13

     Um, here are some things I, I noted from it. Uh, concise outputs, uh, obviously, don't give anything too long. No, "Here is" or "I will," just do the, do the task the user wants.

169. 32:28

     Uh, kind of pushing it to m- use tools more, more instead of text explanations, obviously. I think when we, we've all built coding agents, and when we do it, it usually says, "Hey, I wanna run this SQL."

170. 32:40

     No, push it to use the tool. Um, matching the existing code, not adding comments. This one does not work for me, but, uh- [laughs] ... running commands in parallel extensively, and then the to-dos and stuff like that.

171. 32:54

     There's a lot that you can nudge it to do with the system prompts, but as you see, I think there's a really interesting point to the earlier question you had about where, what's the trade-off between DAGs and loops.

172. 33:08

     A lot of these things, you could see are, feel like they came from someone using it, Claude Code, and saying, "Oh, if only it did this a little less," or, "If it did this a little bit more."

173. 33:19

     That's where prompting comes in, because it's so easy to iterate, and it's not, you're not, it's not a hard requirement, but if only it said, "Here is a little bit more."

174. 33:28

     It's okay to say it sometimes, but... All right, skills. Skills is great. It's, uh, slightly newer. I've, I honestly got convinced of it only recently. So good. I built these slides with skills.

175. 33:41

     Uh, it's basically, I think in the context of this talk about architecture, let's think of it as a extendable system prompt. So in the same way that we don't wanna clutter the context, there's a lot of different type of tasks you're gonna need to do where you want a lot more context.

176. 33:58

     So this is how we give Claude Code a few options of how it could tap into more information. Here are some examples. Uh, I use this for, I have a skill for docs updates to tell it my writing style and h- and my product.

177. 34:14

     So if I wanna do a docs update, I say use that skill, load in that skill. Uh, editing Microsoft Office, uh, uh, Microsoft Do- Microsoft Word and Excel, um, I, I don't use this, but I've seen a lot of people using it.

178. 34:27

     It kind of, like, decompiles the p- fi- it's really cool. Uh, but it lets Claude Co- Code do this. Design style guide, this is a common one, deep research.

179. 34:36

     I, the other day, I threw in a, like, article or GitHub, uh, repo on how deep research works, and I said, "Rebuild this as a Claude Code skill." Works so well.

180. 34:46

     It's amazing. So unified diffing, I think this is worth its own slide. Uh, it's very obvious, probably not too much we need to talk about here, but it makes this so much better, and it makes the token limit s- shorter, it makes it faster, it makes it less prone to mistakes, like I gave with that example, when

181. 35:07

     you rewrite an essay verse marking it with a red line. It's just better. I highly recommend using diffing in any agents you're doing. Unified diff is a standard. When I looked into a lot of these coding agents, some actually built their own kind of standard, uh, and, like, with slight variations on unified diff, because you don't always

182. 35:27

     need the line numbers, and... But unified diff works. You had a question?

183. 35:32

     To go back to skills, I are, uh... I don't know if anyone's seen the Claude, the Claude Code warns you in, in yellow text if your Claude MD gets, like, greater than 40K characters.

184. 35:44

     And so I was like, "Okay, I'm fucking up. Let me break this down into skills." So I be- spent some time, and then Claude ignored all of my skills, and, uh, so I put them somewhere else.

185. 35:54

     So what am I... I don't know. Skills feel globally, uh, misunderstood or, uh, like, not... I don't know. I'm missing something. Um, help me understand. [laughs]

186. 36:05

     Same.

187. 36:06

     Yeah, so the, the question was on... Okay, so Claude Code system, Claude MD, it tells you when it's too long, so, uh, you move it into skills, and then it's not recognizing the skills and not picking it up when it's needed.

188. 36:20

     It ignores.

189. 36:21

     Yeah. Take that up with the Anthropic team, I'd say. [laughs] Uh, but that's also a good example of maybe the system prompt-

190. 36:31

     You need to invoke them and, like, the agent itself shouldn't, like, just call them all the time or-

191. 36:39

     Right

192. 36:39

     ... do the other thing.

193. 36:39

     It does give a desc- description of each skill to the model, or it should, uh, tell it, "Okay, here's, like, a one-liner about each skill." So theoretically, in a perfect world, it would pick up all the skills all the time, but you're right, I generally have to call the skill myself manually.

194. 36:56

     I- but I think this is a good tie-back into when is prompting the right solution or when is the DAG the right solution, or maybe this is a model training problem.

195. 37:07

     Maybe they need to do a little bit more in post-training of getting the model to call the skills is almost like calling a tool call. Uh, you have to know when to call it.

196. 37:18

     So maybe this is just a, a functionality that's not that good yet, but I think the paradigm is very interesting. But it's not perfect [laughs] as we're learning.

197. 37:28

     So diffing, we just talked about. What's next? So this is more opinion based, but where I see these things going and where the next kind of innovations might likely be.

198. 37:39

     So I, I th- there's two schools of thoughts here. A lot of people think we're gonna have one master loop with hundreds of tool calls and just tool calling is gonna get much better.

199. 37:50

     That's highly likely. Uh, I take the alternate view, which I think we need to reduce r- the tool calls as much as possible and just go back to just bash and maybe even put scripts in the local directory.

200. 38:04

     I think I am on the proponent of one mega tool call instead of a lot of tool calls. Maybe not actually one. I actually think that slide I showed you before is probably a good list, but a lot of people think we need hundreds of tool calls.

201. 38:17

     I just don't think it's going there. Adaptive budgets, uh, adjusting reasoning. We do this a little bit, uh, the thinking and ultrathink and stuff like that, but I, I think reasoning models as a tool makes a lot of sense as a paradigm.

202. 38:32

     Can you use ... I think a lot of us would make a trade-off of a twenty times quicker model with slightly stupider results and being able to call a tool call for a very good model.

203. 38:44

     I think that's a trade-off we'd, we'd make in a lot of cases. Maybe not our planner. Maybe we go to the planner first with GPT 5.1 Codex or Opus or whatever if the, when the new Opus comes out.

204. 38:54

     Uh, but I think, I think there's a lot of, uh, mix and matching we can do, and that's, I think, the next frontier. And I think the last frontier, I think there's a lot we can learn from to-do lists and, and new first class paradigms we can build.

205. 39:08

     Skills is another example of a first class paradigm we can kind of try to build into it. Maybe it doesn't work perfectly, uh, but I think there's a, I think there's a lot of new discoveries to be made there, in my opinion.

206. 39:19

     Do I have them? I don't know. Uh, so now I, I wanna h- for the, for the l- latter part of this talk, I wanna talk about the other frontier agents and the other philosophies they've designed, phils- philosophies they've chosen.

207. 39:33

     And we all have the benefit, we can mix and match. When we're building our agent, we can do whatever we want and learn from the best. And the frontier labs are very good at this.

208. 39:43

     So, uh, something I like to go back to a lot, I call it the AI therapist problem. May- maybe there's a better name to give it. Uh, but I believe there's a lot of problems, the most interesting AI problems around, there isn't a global maximum.

209. 39:58

     Meaning, all right, we're in New York City. If I need to see a therapist, there's six on every block here. There's no global answer for what the best therapist is.

210. 40:09

     There's different strategies. There's a therapist that does meditation or CBT or maybe one that gives you ayahuasca. A- and these are just kind of, like, different strategies for the same goal, in the same way that if you're building an AI therapist, there isn't a global maxima.

211. 40:25

     This is kind of my anti-AGI take, but this is also the take to say that when you're building these applications, taste comes into it a lot and design architecture matters a lot.

212. 40:36

     You can have five different coding agents that are all amazing. Nobody knows which one ... Today, nobody knows which one's best, to be honest. I don't think Anthropic knows.

213. 40:44

     I don't think OpenAI knows. I don't think Sourcegraph knows. Nobody knows whose has the best, but some are better at some things. I personally like Claude Code for, I said, like, running my local dev environment or using Git or using these kind of, like, human actions that require back and forth.

214. 40:59

     But I go to Codex for the hard problems, or I go to Composer from Cursor because it's faster. And there's a lot ... Basically, all this to say there's value in having different philosophies here, and I don't think there's gonna be one winner to this.

215. 41:14

     I think there's gonna be different winners for different use cases. And, and this is not just coding agents, by the way. This is all AI products. This is, this is kind of why our whole company focuses on domain experts and bringing in the PM and the, the, the subject matter expert into it, because that's how you build

216. 41:30

     defensibility. So here are the perspectives the way I see it. This is not a complete list of coding agents, but these are the ones that I think are the most interesting.

217. 41:39

     Claude Code, I think, I think to me, it wins in user-friendliness and simplicity. Uh, like I said, if I'm doing something that requires a lot of applications that ...

218. 41:49

     Git. Git's just the best example. If I wanna make a PR, I'm going to Claude Code. Codex, uh, context. It's really good at context management. Uh, it feels powerful.

219. 41:59

     Do I have the evidence to show you that it's more powerful? Probably not. But, uh, it feels that way to me. And the market feel ... There's a whole another conversation here to say the market knows best and what people talk about knows best, but I don't know if they know either.

220. 42:14

     Cursor IDE is kind of that perspective, model agnostic. It's faster. Factory, uh, makes Droid. Uh, great team. They were here too. Uh, they have multiple ... They, they really specialize these Droid sub-agents they have.

221. 42:28

     So that's kind of their edge, and that's maybe a DAG conversation too, or maybe a model training. Uh, cognition, uh, so Devin, uh, kind of this end-to-end autonomy, self-reflection, AMP, which I'll talk about more in a second.

222. 42:42

     They have a lot of interesting perspectives, and actually I find them very exciting these days. Free, it's model agnostic, uh, and there's a lot of UX sugar for users.

223. 42:52

     And I- actually, I love their design. Their, their talks at this, this conference, they, they, they have very, very unique perspectives. So let's start with Codex because it's a popular one.

224. 43:03

     So it's pretty similar to Claude Code. Uh, same master while loop. Most of these do, because that's just the winning architecture. Uh, interestingly, Rust core, uh, the cool thing is it's open source, so you can actually use Codex to understand how Codex works, which is kind of what I did.

225. 43:20

     Um, it's a little more event-driven, a little more, uh, work went into concurrent threading here, uh, kind of submission queues, event outputs, kind of the, the thing I was talking about with the IO buffer in Claude Code, I think they do it a little bit differently.

226. 43:39

     Uh, sandboxing is very different, so theirs is more, y- I mean, you could see here macOS seatbelt and Linux Landa. Theirs is more kernel-based. Uh, and then

227. 43:50

     sta- kind of this, it's all under threading and, and permissions is how I'd say it's mostly different. And then the real difference is the model [laughs] to be honest. Uh, so this is a, this is actually me using Claude Code to understand how Codex works.

228. 44:08

     Uh, so you see we have a few Explore. I didn't talk about Explore, but, uh, it's, uh, it's a, it's another sub-agent type. As y- as I, as I mentioned, these go in and out.

229. 44:18

     Uh, but yeah, this is researching Codex with Claude Code. It's always a fun thing to do. So let's talk about AMP.

230. 44:25

     So this is Sourcegraph's coding agent. I, it has a free tier. That's just a cool perspective in my opinion. Uh, they leverage kind of these excess tokens, uh, from providers and they give ads.

231. 44:37

     So we actually have an ad on them. I think it's a cool... I'm pro-ad. A lot of people are anti-ad. I think it's one of my hot takes, but I like it.

232. 44:45

     They don't have a model selector. This is very interesting too. This is its own perspective. Uh, it actually helps them move faster because you're, you have less of an exact expectation of what the output is because you know they might be switching models here and there.

233. 45:00

     So that changes how they develop. And then, uh, I think their vision is pretty interesting. Uh, their vision is, how do we build not just the best agent, but how do we build the agent that works with the most agent-friendly environments?

234. 45:18

     And actually, Factory gave a talk similar to this as well. But how do, how do you build a hermetically sealed, uh, a, like, coding repo that the agent can run tests on?

235. 45:28

     How do you build the feedback loop? Because that's kind of the Holy Grail. That's how we build an autonomous agent. And how do we, uh, I'd love to see the front end version of this.

236. 45:35

     How do we let it look at its own design and make it better and go back and forth? And this is kind of their guiding philosophy, and you could boil it down to the agent perspective, as I've been calling it.

237. 45:48

     I think they do interesting stuff with context. So we're all familiar with Compact. It's the worst. You have to wait ten min- I don't know why it takes so long.

238. 45:56

     Uh, and if you're not familiar, it's summarizing your chat window when the context gets too high and giving the summary. So they have something called Handoff, which makes me think of, if you, if any was a, anyone was a Call of Duty player back in the day, switch weapons.

239. 46:09

     It's faster than reloading. And, uh, that's what Handoff is. It, you're, you're just starting a new thread and you're giving it the information it needs for a new thread.

240. 46:18

     That feels like the winning strategy to me. Could be wrong, but maybe you need both. That's where they're pushing it. And I, I kind of like that. I, they give, they give a very fresh perspective.

241. 46:28

     So the second thing is model choice. This is the reasoning knobs, uh, and their view on it. They have fast, smart, and oracle. So they lean even more heavily into, we have different models.

242. 46:41

     We're not telling you what oracle is. They tell you, but we're willing to switch what oracle is, but we're gonna use oracle when we have a very hard problem.

243. 46:50

     So yeah, so that's AMP. Let's go to Cursor's Agent. I think Cursor's Agent has a very interesting perspective here. First, obviously, it's UI. Uh, UI first, not CLI. I think they might have a CLI, not entirely sure, but the UI is the interesting part.

244. 47:06

     It's just so fast, their new model composer. It's distilled. They have, they have the data. They actually made, in my opinion, people interested in fine-tuning again. Fine-tuning, it was almost, uh, we'd never recommend it to our customers, but Composer shows you that you can actually build defensibility based on your data again, which [laughs], which is, uh, surprising.

245. 47:28

     But, uh, yeah, Cursor's Agent Composer, I've been almost switching completely to it since because it's just so fast. It's almost too fast. Accidentally pushed to master on one of my personal projects, uh, so you don't, you don't want that always.

246. 47:40

     Uh, but Cursor was just the crowd favorite. And, and I want to give a lot of, uh, props to their team. They built iteratively. The first version of Cursor was so bad and it was...

247. 47:52

     And we all used, I used it because it's a VS code for, for it, I have nothing to lose, and it's gotten so good. It's such a good piece of software and it's a great team.

248. 48:00

     And, uh, but I, I'll say the same thing can be said about OpenAI's Codex models. They're not quite as fast, but they are optimized for these coding agents and they are distilled.

249. 48:11

     And I could see OpenAI coming out with a really fast model here because they also have the data.

250. 48:18

     So h- here's a picture. Um, I think you could... This is a picture they put on their blog, and you could see what their perspective is on coding agents here, just based on the fact that they show you the three models they're running.

251. 48:30

     So they're offering Composer, but they're letting you use the state of the art because they know that maybe GPT 5.1 is better at planning, or here it's 5, but now we have 5.1

252. 48:42

     So here begs the big question, which one should we all use? Which architecture is best? What should we do? And, uh, my opinion here is that benchmarks are pretty useless.

253. 48:55

     Benchmarks have become marketing [chuckles] for a lot of these model providers. Every model beats the benchmarks. I don't know how that happens, but [chuckles]

254. 49:04

     I think there's a, there's world where evals matter here, and

255. 49:09

     the question is what you can eval. The question is how this whole simplis- so simple while loop architecture that I've been kind of trying to push based on my understanding of it actually makes it harder to eval because if we're relying more on model flexibility, how do you test it?

256. 49:26

     You could run an integration test, kind of this end-to-end test, and just say, "Does it fix the problem?" That's one way to do it. You could break it up.

257. 49:33

     You could kind of do point in time snapshots and say, "Hey, I'm gonna give a context to my chatbot from like a half-finished conversation where I know it should be running a specific tool call."

258. 49:43

     I could run those, uh, I c- or I could maybe just run a back test and say, how, how often does it change the tools? I think there's also another concept here that's starting to be developed called agent smell, or at least I'm calling it agent smell.

259. 49:57

     So run an agent and see how many times does it call a tool call, how many times does it retry, how long does it take? And these are all surface level metrics, but it's really good for sanity checking.

260. 50:06

     And these things are hard to eval. There's a lot that goes into it. I'll show you an example of what I did, uh, just to kind of dive into it.

261. 50:15

     But, but on that subject, maybe I'll just say one more thing. I would break it down ment- me- my mental model is you could do an end-to-end test, you can do a point in time test, or what I most often recommend is just do a back test.

262. 50:31

     Start with back test, start capturing historical data, and then just rerun it. So yeah, let me give you, uh, this example. So basically, what I have here... So this is a screenshot of PromptLayer.

263. 50:42

     This is our... Our evals product is also just a batch runner, so you could kind of just run a bunch of columns through a prompt. But in this case, I'm running it through not a prompt, but Claude Code.

264. 50:52

     So I just have like a headless Claude Code, and I'm taking all these providers, and I just, my headless Claude Code says, I think I have it on the next slide, "Search the web for the model provider."

265. 51:02

     It's given to you in a file variables. Find the most recent and largest model released and then return the name. So I don't know what it's doing. It's doing web search.

266. 51:10

     I'm not even caring about that. This is an end-to-end test. This is how we kind of try doing Claude Code, and I actually think there's a lot about putting Claude Code into your workflows and those type of headless SDKs.

267. 51:23

     I'll talk about that, I think, next slide. But

268. 51:27

     kind of main takeaway here is you can kind of start to do end-to-end tests. You can look at it from a high level, do a model smell, and then kind of look into the statistics on each row and see how many times it called a tool.

269. 51:41

     And going back, and we, we've talked about this a lot in this talk, rigorous tools. The tools can be rigorously tested. You can... This is how you offload the deter- this is how you offload the determinism to different parts of your model.

270. 51:55

     It's you test the tools. You, you test the shit out of your tools. Look at them like functions. It's an input and an output. If your tool is a sub-agent that runs, then we're in a kind of recursion here because then you have to go back and test the end-to-end thing.

271. 52:08

     But for your tools, I'll give you this example. If I... So the, in my coding agents, or my agents in general, my autonomous agents, if there's something very specific that I want to output, so in this case, if I have a very specific type of email format or type of blog post that I want to write, and

272. 52:30

     I really want it to get my voice right, I don't want to rely on the model exploration. I want to actually build a tool that I can rigorously test.

273. 52:38

     So in this case, this is also just a PromptLayer screenshot, but this is a, like a workflow I've built. It has an LLM assertion where it says, "Check if the email is good to my standards."

274. 52:48

     If it's good, it revises it. If it's not good, it adds the parts, so like the header that it missed, and it revises it with the same step. This is obviously a s- a very simple example, but

275. 53:00

     in, I, we have another version for some of our SEO blog posts that has like twenty different nodes and writes an outline from a deep research and then fixes a conclusion and adds links.

276. 53:12

     And for the stuff that you have a very specific vision, that's when testing it just gets so much easier. Because as you can see, obviously, testing this sort of workflow has less steps and less flexibility.

277. 53:26

     So this is an eval I made. I start with just a bunch of sample emails. I run the prompt, or actually, I run the, the agentic workflow here, and I'm just adding a bunch of heuristics.

278. 53:37

     So this is a very simple LLM-as-judge. Does it include three parts in it? So this is what I was testing for, like the, "Hi, Jared," email body and the signature.

279. 53:46

     You can get a lot more complicated. You could do a code execution. You can do... I don't know. LLM-as-judge is usually the easiest, but now obviously you could see, I could keep running this until it's correct on all of them and kind of, uh, see my eval over time.

280. 54:00

     This is just from this example. I got it to a hundred, so that was fun.

281. 54:04

     Uh, and then I wanna, I wanna add another future-looking thing. Keep an eye on headless, uh, Claude Code SDK. I know there was a talk about it this morning, um, so I don't wanna, I won't spend too much time on it, but

282. 54:19

     it's amazing. You just give a simple prompt, and it's just another part of your pipeline. I use it for... I think I have it on the next slide. I have a GitHub action that updates my docs every day and just reads all the commits we've pushed to our other repos.

283. 54:34

     And we have a lot of commits going, and it just runs Claude Code. Claude Code pulls down all the repos, checks what's updated, reads our Claude MD to see if it should even update the docs.

284. 54:46

     And then creates a PR. So I think this unlocks a lot of things, and there's a possibility that we're gonna start building agents at a higher order of abstraction and just rely on Claude Code and these other agents to do a lot of the harnesses and orchestration.

285. 55:02

     Are you reviewing those?

286. 55:03

     Yeah. [laughs] I- it creates a PR. It doesn't, uh, it doesn't merge the PR.

287. 55:12

     So here are my takeaways. Number one, trust in the model. Uh, when in doubt, rely on the model when you're building agents. Number two, simple design wins. Number one and number two kind of go together here.

288. 55:26

     Number three, Bash is all you need. Go simple with your tools. Don't have forty tools, have ten or five tools. Four, context management matters. This is the boogeyman we're running from all the time in agents at this point.

289. 55:43

     Maybe there'll be new models in the future that are just so much better at context, but there's always gonna be a limit because, ah, you're talking to a human.

290. 55:52

     I forget people's names if I meet too many in one day. That's context management [laughs], or my stupidity, I don't know. And number five, different perspectives matter in agents.

291. 56:02

     I think this is... The engineering brain doesn't always comprehend this as much as it should, especially in, and I'm an engineer, so I'm also talking about myself. But the- different perspectives matter such that there's different, uh, ways to solve a problem where there's not one is better than the other, and you kind of, m- you probably want

292. 56:23

     a mixture of experts agent. I, I would love to have mine run Claude Code and Codex and this and give me the output and consider it a team and maybe have them talk to each other in a Slack-based message channel.

293. 56:34

     I'm waiting for someone to build that. That would be great. But these are my takeaways. Uh, my bonus thing that I'll show you is how I built this slide deck using Claude Code.

294. 56:43

     So, uh, I built a slide dev skill. So I, I basically told Claude Code to research how slide dev works and how it can, uh, and that's kind of just a library that I made this in.

295. 56:54

     I built a deep research skill to research all these agents and how they work. I built a design skill because I, I know if a thing looks terrible or looks good, but I'm not a good designer to figure it out.

296. 57:05

     So these boxes even, I was just like, "Oh, ma- make the box a little nicer. Give it an accent color." Uh, so yeah, this is how I built it.

297. 57:13

     But again, thank you for listening. Uh, happy to answer any questions. I'm Jared, founder of PromptLayer. [clapping] Find me there.

298. 57:24

     Yes.

299. 57:25

     Thank you. Great talk. Um, so you mentioned, um, regarding DAGs, basically like let's get rid of them, right? But, um, DAG's gonna enforce this like sequential, uh, execution, right, of paths, I don't know, customer service, like agent asks the name, email, right, like in some sort of, um, uh, sequence.

300. 57:47

     Um, so are you saying just write this out, um, like th- this is now, th- this should be, uh, just written out as a plan for an agent to execute and just trust that the model is gonna be calling those tools in that sequence?

301. 58:04

     Like how do we enforce, uh, the order?

302. 58:07

     Right. So the question was, why do I keep talking about getting rid of DAGs? How else am, are you supposed to enforce a specific order for solving a problem?

303. 58:19

     So I think there are different types of problems. So the problem of building a general purpose coding agent that we can all use to do our work and even non-technical people can use, there's no specific step to solving that problem, which is why it's better to rely on the model.

304. 58:37

     If your problem was to build, let's say, a travel itinerary,

305. 58:46

     it's more of a specific step because you have a deliverable that's always the same. So there's a little bit more of a DAG that could matter, but in the research step of traveling, you probably don't want a DAG because every city is gonna be different.

306. 58:58

     So it really depends on the problem you're solving. I would, if I wanted to make an agent for a travel itinerary, I'd probably have my tool call,

307. 59:07

     w- one of my tool calls be a DAG of creating the output file because I want the output to look the same, or creating the plan. And then in the system prompt, I could say, "Always end with the output," for example.

308. 59:17

     But you need to mix and match. There's a, every use case is different, but if you wanna make something general purpose, my take is to rely more on the model, on simple loops, and less on a DAG.

309. 59:31

     Cool. Any other questions? Yes.

310. 59:34

     Yeah, building on that point, like do you think we're heading towards a world where most of, you're not actually gonna call the API through code and that most LLM calls are by triggering Claude Code and is write, just writing the files instead?

311. 59:50

     So the question is, are we gonna move away from calling models directly and just calls call, call like headless Claude Code? Right?

312. 59:58

     Yeah. Like if I had a, like I have a pipeline that does one LLM call per document, summarizes it at the end. You could make a while loop Claude Code that saves a file every time.

313. 1:00:10

     You never call the API besides using Claude Code in a, in a while loop.

314. 1:00:16

     Potentially. Uh, I'll give you the pro and the con there.

315. 1:00:20

     Yeah.

316. 1:00:21

     The pro is it's easier to develop, and we can kind of rely on the frontier mo-- I mean, if you think about it, a reasoning model is just that.

317. 1:00:30

     The reasoning models didn't always exist. We just had normal LLM model and then, oh, now we have O1 and reasoning models. All that is is a, I mean, it's a little more complicated than this, but it's basically just a while loop on OpenAI's server that keeps running the context and then eventually gives you the output.

318. 1:00:44

     In the same way that Claude Code SDK Is a while loop with a bunch of more things. So I could totally see m- a lot of builders only touching these agentic endpoints, maybe even seeing a model provider release a model as a agentic endpoint.

319. 1:01:01

     But for a lot of tasks, you're gonna want a little bit more control, and they're probab- and probably you'd still wanna go as close to metal as possible. Having said that, there's, there's a lotta people who still wanted completions models, and that never happened, and nobody really talks about that anymore.

320. 1:01:20

     So it's very likely that everything just g- becomes this SDK. But I don't have a crystal ball, but those are, that is how I, I would think about it.

321. 1:01:29

     Yes.

322. 1:01:30

     Thanks for your talk. Um, I know you said the simpler the better, but, um, what's your thoughts about test-driven development, uh, spec-driven development in AI? Have you tried it?

323. 1:01:40

     What do you think about it?

324. 1:01:42

     For building agents, or for getting work done?

325. 1:01:45

     For coding.

326. 1:01:46

     Okay. So the question on spec-driven development, test-driven development for coding with agents.

327. 1:01:55

     When in doubt, go back to good engineering practices is what I would say. So i- if you

328. 1:02:04

     ... [laughs] A- and there's, there's whole engineering debates on if test-driven development is the right way, and some people swear by it, and some people don't. So I don't think there's an answer.

329. 1:02:13

     I think coding agents, clearly test-driven development makes it easier. I think, as I was showing you, that's AMP's, Sourcegraph's, whole philosophy that if you can build good tests, and Factory I think thinks this as well, if you could build good tests, your coding agent can work much better.

330. 1:02:29

     So it makes sense to me. When I'm working personally, I rely pretty heavily on the planning phase and the spec-driven development phase, and I think the simpler tasks are pretty easy for the model, but if I'm doing a very simple edit, I'll skip that step.

331. 1:02:43

     So no one size fits all, but return to the engineering principles that you believe when in doubt, I'd say.

332. 1:02:52

     Yes.

333. 1:02:53

     So early, ear- early you talked about sy- about, uh, system prompt leaks. Um, is it not possible to just look at the, uh,

334. 1:03:02

     at the downloaded JavaScript bundle, or do they have a special endpoint that has some prompts behind the endpoint?

335. 1:03:08

     Yeah. Uh, I think, I think they hide it. I think they hide it. There was a, there was actually a interesting article of someone ... Because Codex is open source, they w- before OpenAI released the Codex model that it was using, they were able to hack together the open source Codex to give a custom prompt to the

336. 1:03:28

     model and be able to use the model without it. So yeah, you can dive into it, but, uh, generally it's tried to be hidden, and also laziness of someone posted it, so there you go.

337. 1:03:39

     That's the work. [laughs]

338. 1:03:40

     Yeah.

339. 1:03:40

     But someone had to have found it, right?

340. 1:03:41

     Yeah, but like, is the system prompt somewhere on your machine?

341. 1:03:46

     I actually don't know that answer. [laughs]

342. 1:03:49

     Just have it.

343. 1:03:49

     Do you know that answer? Yeah. Yes? Yeah, it's on your machine. It's on your machine. Nico says it's on your machine. So there we go. So maybe the prompt I was looking at is a little bit old, and I have to update it.

344. 1:03:59

     But the sy- but, uh, the question was does a,

345. 1:04:04

     is the prompt hidden on their servers, or can you find it if you are so determined, and the answer seems to be yes.

346. 1:04:13

     Any other questions? Yes.

347. 1:04:16

     Is this the last one? Is this the last question?

348. 1:04:19

     Can be.

349. 1:04:21

     Um, you talk about Prompt Layer. How can people help you?

350. 1:04:24

     Yes. [laughs] That's a good one. I forgot about that, thank you. [laughs] [laughs]

351. 1:04:29

     Um, so yeah. My ... One, we're hiring. Uh, so if you're looking for coding jobs at a very fun and fast-moving team in New York, you can reach out to me on X or email [REDACTED:email_address]

352. 1:04:45

     We're based in New York. We are, uh, yeah, we're, we're a platform for building and testing AI products for prompt management, auditability, governance, all that fun stuff, but also logging and evals, and those screenshots I showed you came from Prompt Layer.

353. 1:05:00

     So if you're building an AI application and you're building it with a team, you should probably try Prompt Layer. It'll make your life easier, uh, especially the bigger your team is, the more you wanna collaborate, the more you wanna collaborate with PMs and non-technical users, and, or if you're just technical users.

354. 1:05:14

     It's a great tool. It'll make your life better. Highly recommend it, promptlayer.com, and it's easy to do. And that was my shill. [laughs] [laughs]

355. 1:05:22

     Thank you for listening. [upbeat music]