An episode of the AI & I podcast (Every) in which Dan Shipper interviews Angela Jiang, head of product for the Claude platform at Anthropic, and Katelyn Lesse, head of engineering for the Claude platform. They discuss Anthropic's Managed Agents feature announced at the Code with Claude developer event — Claude wrapped in a cloud computer that can be spun up, scaled, and managed as needed — and what it takes to make agents reliable in production. Topics include how the Claude platform evolved from an API to agents, the primitives that make up Managed Agents, why the harness and the model are becoming a single unit, the infrastructure wall that kills most agent projects in production, how team agents differ from individual productivity tools, how Anthropic's legal team uses an agent to review marketing copy, multi-agent orchestration (advisor strategies, adversarial pairs, and swarms), measuring agent success with outcome and budget as the end state, and what the platform looks like a year from now when Claude writes its own harness. Timestamps: 00:01:48 - How the Claude platform evolved from API to agents 00:04:09 - The primitives that make up Claude Managed Agents 00:10:37 - Why the harness and the model are becoming a single unit 00:18:49 - The infrastructure wall that kills most agent projects in production 00:24:49 - Why team agents need a different shape than individual productivity tools 00:26:36 - How Anthropic's legal team uses an agent to review marketing copy 00:34:24 - Using multi-agent orchestration for advisor strategies, adversarial pairs, and swarms 00:35:50 - How to measure agent success with outcome and budget as the end state 00:39:11 - What the platform looks like a year from now, when Claude writes its own harness # Channel Identity Observations: "AI and I" ## Channel Self-Identification - **Explicit channel name and host:** The closing segment names the show and host directly: > "You absolutely, positively have to smash that like button and subscribe to **AI and I**... It's not just a show. It's a journey into the future with **Dan Shipper as the captain of the spaceship**." - **Explicit content claim:** The outro describes the show as delivering: > "pure, unadulterated knowledge bombs about Chat GPT. Every episode is a roller coaster of emotions, insights, and laughter." Note: this outro is comedic/hyperbolic in tone ("snorts" in transcript), suggesting parody or absurdist humor layered over a genuine subscribe request. ## Observable Presentation ### Format - **Long-form interview show** with industry guests. The host interviews two Anthropic employees introduced by role: > "Angela, you're the head of product for the Claude platform and Caitlin, you are the head of engineering for the Claude platform." - The host references an annual event context ("a year from now, we're back at **Code with Claude**"), suggesting recurring event tie-in coverage. ### Intended Audience - **Technical builders and AI-curious professionals**, evidenced by the depth of discussion: API primitives, the Messages API, agent SDK, harness engineering, model lock-in tradeoffs. - The host repeatedly frames questions from a **builder's perspective**, e.g., describing his team's setup: "we have a couple Mac minis with... Claude running in a loop... it's like a thousand line Python file." - Guests address a spectrum from technical to semi-technical users; the host notes even non-technical people might use agent tooling. ### Claimed Scope (per title and demonstrated content) - **Title claim:** "The Secrets of Claude's Agent Platform From the Team Who Built It" — an insider/behind-the-scenes framing, supported by the guests' self-identification as platform product and engineering leads. - **Demonstrated scope:** Deep-dive coverage of Anthropic's Claude managed agents, platform philosophy, multi-agent orchestration, and future direction — consistent with the title. ### Host Positioning - The host identifies as running a company building agent products ("We've got some people already using it in production inside of **Every**"), positioning the channel as practitioner-led rather than purely journalistic. - Recurring first-person framing: "I'm really excited to talk to you because A, you've been launching a bunch of stuff." ## Claims vs. Demonstrated Patterns | Type | Evidence | |---|---| | **Creator claim (explicit)** | Show is "the epitome of awesomeness"; delivers "knowledge bombs about Chat GPT" (comedic outro) | | **Creator claim (explicit)** | Host named as Dan Shipper | | **Demonstrated pattern** | Long-form technical interviews with AI industry insiders | | **Demonstrated pattern** | Audience assumed to understand APIs, agents, SDKs, and AI industry players (Cursor, Vercel, Stripe, Ramp) | # Delivery Observation: "The Secrets of Claude's Agent Platform From the Team Who Built It" ## Format Overview - **Interview/podcast format** with a host (Dan Shipper) and two guests from Anthropic (Angela, head of product; Caitlin, head of engineering). - Opening **cold-open tease** before the intro: "A year from now, where do you think the platform will be?" — a clip that recurs near the end of the conversation, a common podcast framing device. - Closing segment includes a **hyperbolic outro script** delivered to camera: "You absolutely, positively have to smash that like button and subscribe." ## Host Delivery Patterns ### Conversational, self-interrupting style The host frequently restarts and self-corrects mid-sentence: > "Um so, I'm just trying to I'd love to help I'd love for you to help me unpack that trajectory" > "And I I I love the anyone can open a PR to to do this cuz everyone's using Cloud Code." This is a **stable pattern** — repeated fillers and doubled words appear throughout ("it it it comes at this really interesting time," "for for for me and I think for a lot of people"). ### Playful, provocative framing of questions The host repeatedly escalates abstract questions into vivid, money-flavored hypotheticals: > "How close are we to Claude making a billion dollars? This is this is really what I'm asking." > "Claude, make me a billion dollars. Your budget is $10." ### Willingness to interject and push back The host cuts in with short clarifying challenges: > "or just file systems in general?" > "is your team responsible for approving the PR, or does it just like go in?" > "why is that not a skill?" ## Guest Delivery Patterns ### Filler-heavy, hedged speech Both guests (especially the first respondent) use dense "like" chains as a stable habit: > "I think like, you know, your your characterization is like very accurate. I think like as we've kind of like as a lot of these kind of like technologies have evolved..." This pattern is **highly repetitive** and appears across most answers. ### Explicit acknowledgment before disagreement Guests routinely validate the question before adding nuance — a repeated teaching/habits move: > "Yeah, I think, you know, this is this part of the the kind of platform business is actually somewhat similar to any other form of the platform business..." > "Yeah, and I think, you know, on your point around or your team's point around like, you know, having some kind of like model lock-in fear, I think that that's like valid." ### Comfortable admitting limits Both guests state uncertainty plainly rather than speculating: > "I'm not entirely sure. My uh intuition would be that like, I don't know about Cursor in particular..." > "Hm. Um probably. Um I can't I can't speak enough about that at the Anthropic level. I've only been here like a couple of months." ### Structural signposting in longer answers A recurring habit: enumerating "two pieces" or "a couple things": > "I think we have like two pieces of the philosophy here. One is..." > "Okay, so a couple things." ## Recurring Vocabulary and Phrases - **"Harness engineering" / "harness"** — used many times as the core technical term ("harness and the model get very paired," "there is a lot of alpha in that kind of construct"). - **"Hill climb"** — repeated metaphor: "you can actually hill climb a tremendous amount," "you can actually hill climb at um multiple layers of abstraction." - **"Thin layer"** — describing product built on managed agents: "it becomes actually like a pretty thin layer on top of managed agents." - **"Outcome and budget"** — a paired phrase repeated in the closing prediction: "two-parameter world of like outcome and budget." - **"AGI pilled" / "AI pilled"** — insider slang used by both host and guests. - **"Opinionated"** — design vocabulary: "we want to be opinionated about some pieces." ## Teaching Habits - **Concrete example anchoring**: abstract points are grounded in named cases — Stripe's "Minions," Ramp, the "legal reviews marketing copy" workflow, Mac minis running "a thousand line Python file." - **Concrete-anchor example (guest)**: the legal/marketing agent is walked through step by step: "I'm a marketer and I've written some copy... instead you submit it to this like, you know, a little app..." - **Metaphor use**: "LEGO-like" primitives; "it's just kind of like managed agents all the way down"; Vercel's "AI like software factory." ## Audience Interaction & Tone - Frequent **laughter markers** in the transcript, often following jokes about pain points: "And also infrastructure sucks. It's so it sucks so much to like spin up servers." - Mutual **back-channeling** ("Exactly," "Yeah, yeah, yeah," "Mhm") keeps the exchange conversational. - Guests occasionally flag their own punchiness: "Maybe this is I don't know, spicy, I'm not sure, but I think I think people think the harness engineering part is the hard part." ## Uncertainty Notes - Speaker attribution between Angela and Caitlin is **not marked in the transcript**; observations above distinguish "guests" collectively except where one is directly named. - Repeated verbal tics (fillers, restarts) are well-evidenced; whether they reflect the transcript's verbatim nature or editing artifacts cannot be determined from text alone. - The closing outro's tone shift ("I'm absolutely, hopelessly in love with you") is an **isolated moment** distinct from the interview's register; no pattern can be inferred from a single instance. # Observation Record: The Secrets of Claude's Agent Platform From the Team Who Built It ## Participants - **Dan Shipper** — host (per transcript) - **Angela** — introduced as head of product for the Claude platform (speaker attribution within overlapping dialogue is not always individually marked in the transcript; attributions below rely on explicit cues where available) - **Caitlin** — introduced as head of engineering for the Claude platform - Note: Transcript does not consistently tag which of the two guests speaks each line; gendered pronoun cues ("I've only been here like a couple of months", "Kito's given as an example") provide partial attribution. ## Evolution of the AI Platform - Platform trajectory characterized as moving from **completion endpoints** (GPT-3 era), to endpoints with **tool calling and chat sessions**, to today's **Claude managed agents** — "a Claude on a computer with memory." - Guest's framing: as Claude becomes more autonomous, the platform evolves toward "higher and higher order abstraction" in pursuit of best outcomes. - Early days were exploratory ("no idea what people were going to build"); use cases narrowed, and many customers now want capabilities "out of the box." - Stated end-state philosophy: the platform is "the set of primitives and infrastructure that enables you to basically get the outcome as fast as possible with actually as little of work as possible." ## Claude Managed Agents: Design and Philosophy - Built on the same primitives as the Messages API: built-in tools, code execution, sandboxes, web search. - Origin: Anthropic repeatedly built autonomous cloud agent infrastructure internally and decided "we're done building this for ourselves" — do it once, well. - **Modularity principle**: opinionated on pieces tightly married to Claude (file systems, skills), while leaving other endpoints open for customization. - Reference implementations and blog posts published so builders can replicate the construct directly on the Messages API. ## Harness–Model Pairing vs. Lock-In - Guest (identified only by dialogue context) responds to Dan's team's **lock-in fears** as "valid" but argues: - The old "super generic harness, hot-swap any model" pattern "worked like okay" for older models. - New-generation models differ enough per lab that abstraction shifts to hot-swapping **harness + model as a paired unit**, keeping redundancy at the agent layer. - Evidence cited: memory feature — different harnesses "performed drastically differently" on evals; "a lot of alpha" in harness engineering tied to specific models. - On generalizability: guest acknowledges harness choices "do tend to lock the model" and create **path dependency**; primitives must be chosen carefully. - Asked about undoing path dependencies: "probably," but the speaker (recently hired, "only been here a couple of months") says they can't speak to it at the Anthropic level. ## Who It's For; What's Actually Hard - Audiences: internal teams automating processes (end-to-end dev platforms, legal review of marketing copy) and builders embedding agents in customer-facing products. - Quick-start experience was launched for **education about primitives**, not specifically for non-technical users. - Dan shares he set one up via Codex driving the managed-agent setup; got a Slack bot working quickly. - **Key claim**: people think harness engineering is the hard part, but "everybody hits an infrastructure wall" — persistent servers, transcript storage, sandbox resilience, scaling. Second guest agrees: "productionizing is just a freaking nightmare," especially long-running async agents. - Dan: their internal agents run on Mac minis with a ~1000-line Python file (later clarified: actually `claude -p` in bash). ## Internal Agent Patterns - Examples: Stripe's **Minions**, Ramp's similar platform, internal Anthropic Slack-accessible agents. - Legal-review agent example: marketer submits copy → agent does first-pass review → either clears it or routes to legal inbox. Requires **human-in-the-loop** and separate sessions, so it's broader than a single skill. - **Ownership/anti-staleness**: users on consuming teams opened Claude Code and submitted PRs to tweak the agent; the owning team reviews PRs. Managed-agents-to-managed-agents layering ("managed agents all the way down") shields users from foot-guns. - Caveat stated: companies still need "AI-pilled people and technical people" to build excellent things on top; Stripe's large dev-productivity team cited. - Team layer claim: individual productivity is easy; team-level automation requires shared platform abstraction; Vercel's "AI software factory" framing (via "G from Vercel") endorsed. ## Multi-Agent Orchestration - Use patterns: separate **execution from advice** (advisor strategy), adversarial generator/critic pairs, split-and-recombine, best-of-N. - Different architectures suit different use cases (deep/wide research vs. bug hunting/swarm). - "LEGO-like primitives" enable hill climbing at multiple abstraction layers. ## Measuring Success & Agent Lifecycle - Preference for **verifiable outcomes** (e.g., PR merged) over generic evals; end-state principle: "everything should compress down to an outcome and a budget." - Dan's recurring joke: "Claude, make me a billion dollars. Your budget is $10. No mistakes." - **Agent staleness** (Dan's concern): agents decay without owners; he jokes about agent "funerals." - Guest response: skills exist to upgrade models; most "AGI-pilled" users run agents monitoring agents; migration is treated as a breaking change requiring energy, eased by evals and tools. ## One-Year Forecast - **First guest's vision**: users specify only outcome + budget; Claude "understands itself" enough to pick models, spin up sub-agents, and "write itself on the fly." Less prompt engineering, less harness architecture. Qualification: "I don't know that we'll get there in a year," but outcome-specification with error bars on budget may be achievable. - **Second guest's answer** ("more boring"): if agents are constantly running and recreating themselves, "the platform has to seriously scale" — long-running requests, varied shapes; never let platform scaling limit what users can accomplish. ## Unresolved Tensions Preserved - Dan's team's **fear of lock-in** and of features lagging Claude Code is acknowledged as valid but only partially addressed (promise of "less and less divergence" over time, no guarantee). - Guest uncertainty on whether generic harnesses (e.g., Cursor's approach) persist: "I'm not entirely sure," intuition-based only. - Path dependency locking models into "lanes" is acknowledged as real risk with no resolution offered. - Ownership/staleness problem: partially mitigated (PR workflow, upgrade skills) but no full lifecycle solution presented. # Speaker Attribution & Provenance Record ## Video Metadata - **Title:** The Secrets of Claude's Agent Platform From the Team Who Built It - **Video ID:** `01a0f15a-8719-7958-bd92-e399a467f774` - **No curated metadata supplied**; all role attributions below are inferred from transcript content and explicit in-transcript introductions. ## Speakers & Roles ### Host / Creator - **Dan Shipper** (identified by name in the closing promotional segment: *"Dan Shipper as the captain of the spaceship"*) - Acts as **interviewer/host** throughout; introduces guests: > "Angela, Caitlin, welcome to the show." - States his affiliation context: works at a company referred to as **"Every"** ("some people already using it in production inside of Every"), building internal agent products. ### Guests - **Angela** — **Head of Product for the Claude platform at Anthropic** (role stated by host). - **Caitlin** — **Head of Engineering for the Claude platform at Anthropic** (role stated by host). - One guest states tenure uncertainty explicitly: *"I've only been here like a couple of months."* - One guest mentions prior employment: *"We used to work at Stripe."* - **"Kito"** — mentioned by a guest as having "given as an example" an internal agent app; not a present speaker; role at Anthropic not specified beyond internal-team attribution. - Transcript does not consistently mark which guest (Angela vs. Caitlin) delivers each answer; individual attribution of specific statements between the two guests is **not verifiable** from the source. ## Referenced Third-Party Sources & Claims - **Stripe** — built "Minions," described as an end-to-end developer platform; has a large developer productivity team (per guests/host). - **Ramp** — "did something similar" (per guest). - **Vercel** — "G from Vercel" cited for an "AI software factory" perspective (per guest). - **Cursor** — host asks whether they use per-model harnesses; guest responds *"I'm not entirely sure"* — **unverified, explicitly uncertain**. - Products/features referenced: Claude managed agents, Messages API, agent SDK, Claude Code, code execution, web search, skills, vaults, memory, multi-agent orchestration, Codex (in-app browser), GPT/Gemini models, Open Claw (host's example). ## Promotional Segments - **Closing promotion (flagged):** Outro exhortation to "smash that like button and subscribe to AI and I," praising the show and host Dan Shipper, ending with a personal declaration to Dan. This is a channel promotion, not interview content. - Occasional **[music]** and **[laughter]** markers are present; no other sponsored or promotional segments identified. ## Availability Limits - **Comment availability:** Not indicated in the source material. - **No external citations, links, or documents** provided beyond in-conversation references. - Speaker-level attribution between Angela and Caitlin is unavailable due to transcript formatting. A year from now, where do you think the platform will be? We'd want to experiment with directions where Claude actually gets so good at understanding itself, it figures out what model you should be using, it figures out how to spin up all the sub agents. We don't have to think so much about what kind of architectures are there because Claude is actually able to understand itself enough that it can write itself on the fly. \>\> In that world, if Claude is on the fly or agents on the fly are becoming what they need to become in order for you to do what you're trying to do, the platform has to seriously scale. How close are we to Claude making a billion dollars? This is this is really what I'm asking. \>\> \[music\] \>\> Angela, Caitlin, welcome to the show. Thanks for having us. \>\> Yeah, thank you. So, for people who don't know, you both work on the platform at Anthropic. So, Angela, you're the head of product for the Claude platform and Caitlin, you are the head of engineering for the Claude platform. Um I'm I'm really excited to talk to you because A, you've been launching a bunch of stuff. You have Claude managed agents that came out recently, you've been launching new features for it. And I think that it it comes at this really interesting time where it makes me think about what actually is a platform in AI for a model company because in the GPT-3 days, the platform was a completion endpoint. You just like send a prompt to get a response. Um after that, it's like a completion endpoint with tool calling and a couple and like chat sessions, like that kind of stuff. And now it like with Claude managed agents, you're essentially getting a Claude on a computer um with memory and all this other stuff. Um so, I'm just trying to I'd love to help I'd love for you to help me unpack that trajectory and like what it means to build a platform in AI. Yeah, um I think like, you know, your your characterization is like very accurate. I think like as we've kind of like as a lot of these kind of like technologies have evolved with the LM like for starting and then I think like uh putting that behind an API was very fun. A lot of people were like, "Wow, I could like do some at the time." I think it was very cool. Now we'll probably look back at it and be like, "Oh, that was like really basic." Um and then, you know, I think like we've moved more and more towards like a slightly more like stateful world as you kind of like want to persist the kind of like sessions, state um to be able to make sure that the kind of performance of the model is like better and better. I think that that's probably like actually the the through line. Like as a lot of these kind of like um as we make improvements to Claude and as it continues to get better and like more autonomous, we find ourselves like basically needing to kind of like evolve the platform to be sort of like higher and higher order abstraction, but it's in the pursuit of like helping you get the best outcomes out of something. Like I think in the very beginning, you know, we were very like everyone was very exploratory. It's like you have no idea what people are going to build with these LLMs, and you wanted to kind of have as much possibility out there as um as available. And then as those use cases started kind of narrow down, like people started building products with it. People started now like building agents with it. And more and more of that is about, you know, like customers coming to us and being like, "How do I get the best out of Claude? Um how do I like set up my tools? How do I run the loop?" And so on and so forth. And you have some people who are like really really experimenting, and they're on the edges, and that's great. And then you have like just a whole host of other folks that are coming in who are like, "I kind of want a lot of this stuff like out of the box." Um and in our pursuit for get make making sure that like Claude is basically producing the best outcomes, we find ourselves like enriching the platform to be richer and richer and richer, and that's in uh you know, contained in that is like both the state, it's like the tools that you start to see us adding. Um it contains a lot of kind of like almost like sort of the cloud components of a lot of these types of things. Um but it's in pursuit of the same mission of like just making things literally as easy as possible. And I think in probably, you know, the forward state of a lot of these things in terms of maybe the philosophy of what a platform ultimately ends up doing, it probably ends up just being like whatever it's like the set of primitives and infrastructure that enables you to basically get the outcome as fast as possible with actually as little of work as possible. And I think that that tends to follow a certain form factor at least in this current stage. But yeah. How would you characterize like what the primitives are today? So maybe that's just asking what are the primitives in Claude managed agents? Yeah, so Claude managed agents is built on all of our same primitives that you could otherwise build on directly. So the messages API. And within the messages API we've built a whole bunch of I guess maybe innovations around the API. Like you could just get tokens in and out if you really wanted to, but you know, you can use some of our built-in tools. You can build you can use stuff like code execution, spawn a sandbox and execute work. You can use I guess like you know, web search and all these sorts of different things. And so I think we've taken what we see as all the most powerful of those things and put them together into a harness and a set of infrastructure that is you know, just the way to get what we think is the best outcomes out of Claude. So I'm sitting here feeling this sense of I've been thinking of it as like time deflation. Like my time gets more valuable in the future as opposed to the opposite. What whatever the the opposite would be. My time gets less valuable in the future. \>\> \[laughter\] \>\> Um Uh and and and the reason is because we're So for example, internally for us we're building an agent. We're building some agent products where it's like agents that do specific things for us internally and then hopefully for customers. And in order to do that we've like you know, we have a couple Mac minis with you know, Claude running in a loop on the Mac mini, right? And a lot of that and and it's like a thousand line Python file or whatever. And a lot of that mirrors what you guys are building in Claude managed agents. And so for for for me and I think for a lot of people building on Cloud or on the Cloud platform or ecosystem, there's there's at least I feel this, maybe we should just wait for you guys to build it. Um, but then I don't know what the lines are and uh and I yeah, I'm sort of wondering if if I want to build an agent, like what is the best path to do that in a way that aligns with what you guys are doing? Yeah, um I think, you know, this is this part of the the kind of platform business is actually somewhat similar to any other form of the platform business where you do have customers like like yourself who are building and, you know, you're kind of thinking, should I go ahead and do it cuz maybe I have this like immediate need, but at the same time I don't kind of want to like, you know, repeat the work per se and you could have just when you could have just gotten it in there for free um out of the platform. Um \>\> And also infrastructure sucks. It's so it sucks so much to like spin up servers. I can't believe you do that all the time. \>\> \[laughter\] \>\> But I will actually say um part of why we ended up building Cloud Manager agents was because Anthropic ourselves had gone through enough of these iterations where we built products that were agents that you could run autonomously in the cloud and we did that stand up the infrastructure so that it works well sort of work enough times that um we ourselves were like, okay, we're done building this for ourselves. We're we're doing it once in a way that's going to really work from everything that we've learned, but also for all the people who are doing it, like you can run whatever you're running on a couple of Mac Minis maybe, right? And for a lot of people that could work, but I think if you're building agents into your product and you're running something really at scale, right? Like that's where it really starts to become more and more challenging to get that infrastructure, right? That's really interesting. Yeah, and then maybe to answer the other part of your question, I think we have like two pieces of the philosophy here. One is is a bit in the way that we kind of design managed agents, which is that we try to have it be modular enough. Like we want to be opinionated about some pieces that we feel like should be, you know, very well like married to the Claude model. Um but then we like often times like the way we want, for example, we want Claude to like very specifically use like file systems. Um that's like a very particular like Claude kind of style. \>\> or just file systems in general? \>\> systems in general. We We also really want to lean into skills. I know like a lot of folks like skills, but like that's something that we like we want to have our hearts be really opinionated about that. And so we're kind of particular about like those kind of primitives being the case. So like use the file systems, use the skills. They're really basic. Um but at the same time like we still find people who are like still trying other methodologies to go do that. And we want to kind of like help you, you know, when you build to start uh just kind of starting the best foot. Um so that's one piece uh on some of the kind of more opinionated ones. But as each one of these kind of like, you know, endpoints or or APIs that we have as part of the suite, we try to like open them up a little bit um in certain areas. So there's like things that you know, we're looking uh kind of forward to and being like, you know, from maybe it's not available today, but in our design um we are trying to make it flexible enough for people to kind of like add in different pieces cuz we recognize that this API or suite of APIs is not necessarily going to solve like maybe everything in its original construct, and there're going to be pieces that need to kind of open up. Um and then the second bit is like, you know, we're we're kind of public about this is like when we do design a lot of these things, we do put out like blog posts and sort of like reference implementations. So if you did want to kind of at least be inspired by that construct, but still maybe make your own on the messages API, um you can definitely do that. I think that's to the to the point you just made, that's something that's that's coming up for us. Again, we have, you know, Claude's running on a Mac mini with a Python file and a couple other like uh you know, bigger more serious implementations on like, you know, cloud infrastructure that we're trying to figure out what to do with. And I think I I told the team that we were that we were talking today, and I think one of the uh one of the questions that they have or or one of the feelings of consternation that they have considering using Claude managed agents for this kind of thing for spinning up agents for our customers is just right now it's a like we have a playground. We have we just have like a little we have a server or Mac mini. We can just like pipe stuff to to Claude. It can do anything that Claude code can do. It has a file system. It has a browser. It has like all this stuff. If we want to you know switch it switch it out to GPT 5.5 or Gemini or whatever it's like pretty easy to to do that. Um so is that kind of and I feel like they they they feel like they're we're going to get if we use a Claude managed agent we're going to get locked in and it's not going to we're not going to have the flexibility to do all the stuff that we want. And it it there there's also a worry that features are going to come to Claude code itself that won't be in Claude managed agent for a little while and that it'll prevent us from being at the edge which is sort of what we promised to our customers and really to ourselves. Like we just love being like just doing whatever the new thing is. How do you think about that? Yeah, so I think the what's nice about the way that we work internally I guess is like so we run the platform and the platform for what most people think of it as is our externally facing APIs and our suite of APIs. Um the other rest of what our team actually does is internal platform in the sense that all of our first party products are built directly on the same platform as everybody else. And so what's cool about that is we're we spend all of our time not all of our time but a lot of our time working with the teams internally who are building on top of the platform and kind of enabling the features that they will build, sharing ideas and these sorts of things. And so I think over time you'll maybe see less and less divergence of um you know like what might be available in Claude managed agents, what might be available in co-worker Claude code that might sit on top of the same infrastructure, right? Like that's I think one way to think about that. Yeah. And then I think, you know, on your point around or your team's point around like, you know, having some kind of like model lock-in fear, I think that that's like valid. Like, many folks kind of have that consternation. And I think we're kind of at this place where there's a bit of like an evolution here where, you know, if you look back, um maybe even just a couple months ago, it was very standard to kind of build a very, very, very generic harness. It's super generic, and then you can kind of hot swap models across all of those things. And I think for kind of an older generation of models uh across labs, that kind of worked like okay. A lot of things were were moving at a pace where I think that that was like mildly reasonable. I think now, um for the next kind of generation of models, and as we kind of see it forward, I think you kind of see this a little bit from every lab. Like, everyone's taking like slightly different um techniques and perspectives on how they want to kind of advance their particular form of the model. And so, in theory, I guess you could do kind of the super set of all those things. But, more often than not, I think, you know, like when you build agents for your company or for your customers, you do want to deliver like an outcome ultimately for them. And so, I think that that level of abstraction of like what you're actually hot swapping stops becoming this like really generic harness and hot swapping the model, and it gets more to like the harness and the model get very paired. You still need redundancy, and you still might want to use other models for things, but you probably do it at the layer of like the agent, meaning like the harness plus the model, um rather than necessarily the other architecture of like, you know, really, really generic harness and and hot swapping everything underneath. \>\> That's really interesting. Is that how, I don't know, the Cursors of the world are doing things? Like, do they have a a separate harness for each model, or is it a generic harness that they're kind of hot swapping the models in and out of? Do you know? Um I'm not entirely sure. My uh intuition would be that like, I don't know about Cursor in particular, but there have been like teams that we have talked to who have kind of fallen on similar kind of perspectives. And it's mostly cuz they're just trying to squeeze the most out of each model to kind of like uh almost like harness engineer like every single like nuance. Um and you know, one example that we have, it's it's It's an external customer per se, but um something that we've done a lot internally. Like we recently watched like memory for example with with manage agents. And we tried a bunch of different different harnesses ourselves. Like we tried one that was like the one that we ended up launching. We tried a bunch of others using a bunch of different other techniques. And at least personally for myself like when I saw the kind of like eval suite from like the team. Like each one of these harnesses performed drastically differently. And so I think like just even looking at something like that shows you that like you can actually hill climb a tremendous amount by just like harness engineering the right pieces together. And I think if you were to just take that forward across like all model combinations across all different labs, all different kinds of providers. There is a lot of alpha in that kind of construct. And so I wouldn't be surprised if more than just ourselves have experimented with that level of like you know unit tying. It's really interesting that there's this path dependence where you make some choice for how you do requests and responses or how you tool calls or whether you're you have the model want to use file systems or not. And then that sort of like changes the trajectory of all these different models. Yeah, and it feels like maybe at the time it's like a small almost like you know kind of like footnote. But it ends up becoming very big. Do you think that that will end up affecting the models generalizability in the sense that at some point they'll just have these sort of maybe locked in lanes of stuff that they're good at because they're you know Claude is really good at file systems and opening eyes you know GPT's good at some other things. Like yeah how how is that going to how's that going to flow through the models like personality and behavior if it's like locked into a specific way of doing things? I do think it does actually kind of tend to lock the model. So like what what we end up like kind of treating as like the right path and the right primitives need to be like very carefully thought through. And so like I think in the in some areas you know like of of other models they become really really really good at like reasoning. And then they almost like over optimize on that level of reasoning. And there's other perspectives around like, okay, like yes, we want it to be really good at like a computer. Like maybe the computer part is the the interesting part. And so, if you think through maybe some of the the primitives which we could get right, we could get wrong, but at least we'll like go through the thought process of like that will probably at least lead us, you know, one path or the other. Um I think it's hard to say like, you know, in in which direction per se will ultimately be true, but I do think there's a lot of like path dependency in its up taking. So, being really like thoughtful about what you choose to actually include or give kind of the model more natively is really important. \>\> Are there any of those path dependencies that you've had to undo? Hm. Um probably. Um I can't I can't speak enough about that at the Anthropic level. I've only been here like a couple of months, but I have to imagine that that has been the case. Um I mean, we've experimented like even at other labs like that the kind of like primitives that we have to take a look at are constantly changing. Um and you do kind of hit like a little local maximum and rethink like, okay, maybe there's like a more generic approach to doing it. \>\> Yeah, yeah, yeah. Interesting. Um I want to take a take a step back and and ask you something that maybe I should have asked at the beginning, which is like who who is Cloud managed agents for? Right? Like I I set one up earlier today. We we've got some people already using it in production inside of Every, and I just I just did one today. I really loved the um the sort of like getting started chat experience that you that you had and the sort of um some of the examples that you had, and it it felt to me like even if I was not technical, I might want to use this to set up an agent. It it might be a little bit complicated, but what I actually did is I just and I'm sorry to say this, but I did it in the Codex in app browser, so I had Codex driving the uh the manage agent setup, and it like I had a Slack bot working pretty pretty quickly. It was like it was really cool. So, how do you think about when you're designing stuff, when you're designing Cloud managed agents, who it's for? Yeah, so it's interesting because I think you're right that especially with that quick start experience, which we actually felt pretty strongly about launching not specifically for the sake of making it so that non-technical people could go and build agents, but actually just for anybody technical or not to be able to wrap their head around the primitives like the API. \>\> and here's how they fit together. \>\> Like, you know, the the kind of education portion of it. Um, but I think when we think about who it's for, we think about a couple different things. One is we're seeing people internally within companies build automation or build really powerful platforms or systems. Like, we've seen people say, "I want, you know, a full end-to-end software development platform, right?" And like Manage Agents a perfect solution for something like that. Or, you know, "I want to automate a little process over here where like legal has to review my marketing copy, right?" And things like that. And so, you shouldn't have to re-implement memory and like \>\> Exactly. Every time you're doing that, right? You can get started really quickly and you can get something running quickly. The other user that's top of mind for us is people building into their products that they expose to their customers. Um, and so, that's the other one where actually, yes, like you do still want a lot of customization. You do still want to make something that's going to be really powerful for your product. But, we still like definitely, definitely believe that not spending your engineering resources on the infrastructure and on all the little harness engineering tweaking sort of stuff is like worthwhile. \>\> like a month ago? You would have saved us so much \[laughter\] time. We'll just have to talk more. \>\> \[laughter\] \>\> But, I am I am sort of curious. Okay, so maybe infrastructure is one of these things, but um when you see people setting up agents, what do they what do you see them think the hard thing is and what ends up actually being the hard thing and are they the same? Good question. I I Maybe this is I don't know, spicy, I'm not sure, but I think I think people think the harness engineering part is the hard part. Um, and so, actually like, you know, in the past we launched the agent SDK, which is what you guys I think are using um, on your Mac minis. And for a lot of people they were like, okay, great. I don't have to do the harness engineering part where I have to do prompt caching and I have to maximize my context window and all these sorts of things. \>\> we're just actually using just Claude in bat, like the Claude -p command. Oh, wow. Yeah, okay. It's It's pretty good. Yes. Yeah. \>\> \[laughter\] \>\> Okay, cool. And but regardless, like, you guys did that because it takes off your hands building the harness, right? Um, but I do think what we saw with a lot of customers was, okay, now I want to go and take that thing and like get it into production and scale it, and everybody hits an infrastructure wall. Like, everyone hits the same problem of like, oh, wow, I either need to like keep a server constantly running or I need to use infrastructure that will spin up and spin down, and I need to store the transcript data, and I need secure sandboxing, and all these sorts of things. And so, um, you know, and like, if you boot a Claude code session or you boot the agent SDK in a sandbox, and like, that's the thing that you have running, but your sandbox loses connection and dies or whatever, your whole agent dies, right? And so, I think the infrastructure part, especially, is the wall that most people end up hitting, but they're more expecting that the actual harness engineering and like getting the most out of the model is the part that's going to be harder. Yeah, I totally agree with that. I was just going to say, like, we do we we talk to so many people who are at now the place where they're like prototyping really quickly, and they're super excited, and it's like it's doing the thing. And then yet, there's like a class of people who are, you know, really pushing and being like, okay, I I do want to hill climb. I I really want to edit the hardest. Um, but then, once you have that thing, like, productionizing is just a freaking nightmare. Um, especially for like the more interesting kind of long-running async ones that you want to do a bit more remotely, that are a bit more autonomous. Um, and everyone kind of runs into that wall, and it was a big inspiration for why we built what we built. I feel like uh, one of the like, er, examples of the shape of an agent is open claw. Um, and in particular the the thing that it has brought to us internally is you have an always on agent in Slack that has its own personality and has its own like part of the world that it like ends up working on. Are you guys like is is that a possible future for like okay a one click agent that lives in my Slack that yes, I can go set up all the internals, but like I don't have to really think about all of the um, you know, the technical infrastructure stuff. Um, cuz I I think you you all have the the beginnings of that, but it's still like a lot of steps from the current manage agent to something that's always on in my Slack that I have to like set up and customize. So is that does that fall in the realm of platform's job or is it like too far in the product direction? No, it it definitely is uh, something that we really want to do. I think like, you know, we we focused a lot on kind of the infrastructure piece to start because that's where we just see a lot of these like pain points. Um, but yes, like I think in like it's like, you know, I don't want to say exactly say final shape, but in its like advanced shape, we actually want to make it so that you can kind of deploy these agents really really easily. Like um, we've made like some light steps in this direction. Like for example, we included vaults um, as one of the primitives as just kind of And vaults store your like keys and stuff, like your auth keys? \>\> Credentials. Credentials, yeah. Yeah. Um, as like, you know, kind of solving some of the lower level pieces as a starting point, but once you kind of wrap some of these more sort of like agent identity type of primitives in a more secure way and you can handle it really easily and it works with like the whole like system, then uh, you know, I think it's very natural for us to get to a place where maybe you are either one clicking uh, Slack integration or alternatively even maybe just telling, you know, Claude like add Slack and it just like handles absolutely everything and then before you know it, your little bot is just pinging you on Slack. I love it. I can't wait for that world. \>\> \[laughter\] \>\> Um, what are the best internal use cases of agents? Cuz I I think there's this big question happening right now where okay, yeah, everyone's in Codex or cloud code, but then now we have these agents that are out in the cloud. Now everyone inside of a company can like have their own agent. There are team agents. There are company-wide agents. So, what are the patterns that you see for when people make really useful internal agents, what they do and what they look like? Yeah, I would say we similar to I know we've actually seen a few examples of these in some of the more like AI pill AGI pill companies like um Stripe built Minions and they talked about that a lot as their kind of like end-to-end platform that their engineers could use. Um I think Ramp did something similar and um we've done similar things as well, right? \>\> Yeah, we've built kind of platforms internally that are, you know, I have agents running that I can talk to you from Slack or from wherever, right? And um at a certain point that becomes actually like a pretty thin layer on top of managed agents. Like you don't have to do very much to accomplish that. \>\> That's what I was thinking. Like I looked at Minions or whatever Ramp does and I was like, it Why? Why? You know? So, is it Is it actually useful to have a sort of like thin coding agent that anyone in the company can use or like why not just install the Claude app in Slack? Yeah, I would say the difference in a platform like that and some of the things that we've done internally is there's a lot of customization that you might want to do on, you know, the development environment where an agent is actually running and able to verify its changes, right? And and things like that. \>\> here's how our CI/CD works. \>\> Yeah, exactly. And so, you know, I think for lots and lots and lots of people like Claude code is an excellent tool, right? And and you can run Claude agents with Claude code and and that is really great, but I think if you're trying to do a bit more end-to-end development, right? And you maybe want to bake in more custom things and you could start with something like managed agents and build a layer on top of that and end up with something that's maybe closer to that end-to-end experience. It also seems to me like there's something in particular about having a team that you need to work with that makes a the managed agent shape important as opposed to it just all works in cloud code. Like I guess technically you could like sync the skills between everyone's cloud code, but like there's something about just we all have one agent that does this thing that seems to work. Yeah, I'm really glad you brought that one up because I think like that's actually like one of the more common areas where we see a lot of the opportunity is that to your point, you know, there's a lot of like individual productivity that's happening whether you're developer or non-developer. There's like so many tools that you're using to just like make yourself like more automated more, you know, high leverage. But then when you get to the team layer suddenly everything gets like massively more complex. Like number one obviously it can't like sit on your laptop. And yes, you could maybe like, you know, put it in the cloud, but it's again more for yourself. Um to kind of like handle with your laptop closed. But then you go to like okay, then well now like the three of us want like, you know, a couple agents that interface with each other and work with each other. And then maybe we're automating a process kind of end to end. And especially for some of the more complex processes that you kind of envision being like really transformed with AI. You do need like you do need that kind of like team orientation. And that needs to happen at like a layer that's a slightly higher bit of abstraction than just a single agent. And I think some of the teams exploring, you know, kind of multi-agent architectures and things like that are really exciting. But it needs to be built on top of a a little bit of like a platform that everyone kind of spin up and down and control. And I think G from Vercel like had a really good perspective on this in a way where I think his company Vercel's obviously incredibly like AI built. And he kind of describes it as sort of like an AI like software factory like internally. And I think that's exactly like the right mindset and that like produces you know, like an extremely high leverage organization that's really just like creating a tremendous amount of productivity, but not just for themselves just like for every single process that they have in the company. \>\> Mhm. And I really want to go back to this like okay, agent use cases. We've got coding agents that that anyone can use in the company. Like what are the other ones that are that you see people standing up that are really useful? We've seen a few. So one of the fun things that we get to do is just kind of work with our internal teams of different functions and like help them identify because we actually just get to learn a lot as a result of doing that. And so the silly example I brought up earlier of like legal team needs to review marketing copy \>\> \[laughter\] \>\> was one of the ones that Very real. Yeah, like extremely real and like really like blew people's minds with like very basic agents that just give people the right set up to be able to do that. So you've seen that Well, what does that actually do? So it's like there there's marketing copy and there's a legal agent that is just like watching what everything marketing does and is like stop like No. It is It is more like Okay, \[laughter\] I'm a marketer and I've written some copy, right? And in the past maybe you would have opened a ticket or something. Be like, can you please review this copy? Um but instead you submit it to this like, you know, a little app that we built on top of agents that is like, okay, cool. Now I'm going to go as an agent review first and then put it in legal's inbox as a already first pass review was done and maybe actually like the agent is it's clear enough that it can say, okay, marketing, you're good, right? Or maybe it's still like, no, this needs like an extra human review. And so yeah, it's just And that's the sort of thing where again, just thin layer on top um but you can build the, you know, you have access, I have access, we can both see the outputs and we can work together on it. \>\> Okay, but then so for example, why is that not a skill? So it's a It can It very much can be a skill and that actually is like if you you would probably build that agent as a, you know, legal reviewer agent, right? And so you would have MCP servers or whatever it is that help you access external contacts. You would have skills that help you understand like here's what rules we have to follow and not follow, right? And all those things and you'd put all those things together, but then you can just fire off a session with that agent. And then I think the last piece you need and this is where I'm saying it's a really thin layer is just like the form factor on top where like different people can collaborate together and like work with that agent and multiple agents can be involved in the system. Um and so I think it goes a little bit broader than a skill because you kind of still need like the right form factor for the agent to be able to go run and then for people to be able to interact with it. Another core bit of why it's like not a skill is because or not exclusively a skill is because you actually do need human in the loop. Um and so like if you were to automate the whole thing and you would just you know like taking the skill and looking at yourself from like legal skill for example. Like in that world of course you could have just like done a pure skill. Um but if you need a human in the loop to be like okay like I want to review and I do want to check and I want to like if we're looking at like legal things and so there's a bit of like you know authentication that's sort of necessary. Um in order to automate that entire process you kind of need like agents to go do the thing. And so because you need to spin up sort of separate sessions for that to happen some sort of stitching is necessary that can't be instantiated in a single skill. That's really interesting. Yeah. Um okay. So just to push on that a little bit. So what is the best practice for you create an agent that uh its its job is to make sure that when marketing is writing something they can get it approved really quickly by legal. And sometimes it'll approve things immediately sometimes it sends stuff to legal. And ideally it's like getting better all the time so it can do more and more right? What is the best practice for who owns that agent once it's built? Cuz one of the things that we found is if you don't have a human who's responsible for the agent it gets stale very quickly and then it ends up being kind of this like dead thing that's just like out there doing stuff but it's not actually good. And also uh even if it kind of works there's all there going to be all these times where legal's like you asked me to approve this but I don't really need to approve this thing. Like let's update your prompt. So like how does that all work when it works well? So it's actually really interesting because so the form factor thing right? Like the app that sits on top of that that we originally built um one of our teams worked on that right? And and like kind of sitting with these teams and understanding what they needed, um, and they were kind of like, "Okay, here you go, and we're going to go do other stuff now, and like let us know how this goes for you." And then a really cool thing actually ended up happening where people on those teams who were using the tool were like, "Oh, I wish like this little thing could get tweaked or this thing could get better." And they like popped open Cloud Code and made some of the changes to the actual And so it's funny \>\> is your team responsible for approving the PR, or does it just like go in? Uh, usually my team's responsible for reviewing the PR if it's a system that we actually own, but but yeah, like people can kind of self-serve making changes to those things, which I think is really cool. So, it is I I do think we're still in a stage for a lot of teams, a lot of companies, like even going back to, you know, like Stripe has Minions, right? Like Stripe has a large developer productivity team. We used to work at Stripe, so we spent a lot of time with them, but they have a large developer productivity team. They're awesome, and they're obviously putting a lot of work and energy into building platforms and tools like this, and so I think we're definitely still in a place where something like managed agents or being able to build on top of our platform is really powerful, but you still kind of need the like AI-pilled people and technical people within a business to then go like create something really excellent on top of that that works well for whatever you're trying to do. That's interesting. Yeah, I I I love the anyone can open a PR to to do this cuz everyone's using Cloud Code. One of the things that I find talking to people who are in infrastructure roles at companies where this is starting to happen is like you know that you know the meme where it's like there's there's a person and he's like going like this and he has like daggers in his like back and he's like, "Cover your back." \>\> \[laughter\] \>\> It's like infrastructure people are that for like, "Now anyone can like can what's can submit PRs." How do you how do you deal with that? And how do you do that well? Cuz obviously like in an ideal world you would love for a legal to be able to submit PRs to improve this agent and also um sometimes they're probably going to submit stupid stuff that wastes time. And so what are the what are the right ways to either organizationally like culturally or technically like make that possible without ruining your your lives? For this particular one that we've constructed that Kito's given as an example, we actually have like a couple layers of abstraction away from like that kind of like PR layer. So at the very beginning it kind of like started that way and to kind of like basically prevent users from kind of foot cutting themselves a little bit, uh they kind of get to a place where often times their way of interacting with the agent that they own like that whether it it's the marketing team who owns the marketing agent requesting or if it's the legal team, you know, owning the agent that does the review. Um they actually engage with those agents through Claude itself. So they actually spend more of their time like kind of talking directly to Claude and then Claude will often times figure out what should be the right way for them to go and handle it so that they're not kind of like, you know, hopping straight down to the absolute core bit and doing something that may result in, you know, some complications. \>\> talking to Claude or Claude code like Claude chat or Claude code or co-workers or like \>\> instantiation of of of Claude um that we made that actually is a managed agent in and of itself. So it's just kind of like managed agents all the way down um in that construct. Uh but you we found that each layer if we kind of tune and and prompt each variant of the managed agent, it helps to solve like, you know, different parts of the problem for users. So at the end state for, you know, like that marketing person or that legal person, it is like a really simple interface where the way that we tell them is like you're just talking to Claude. But under the hood it's many many Claudes engaging with each other to get to the part where then they the Claudes themselves are doing the more complex work that the human doesn't really necessarily need to interpret. \>\> Interesting. You guys just launched multi-agent orchestration. What are the coolest what are the coolest things that people are doing with that? Mhm. One of the more interesting ones is like um I think people are using it to like construct sort of different harness techniques. And that one I'm personally very excited by um because like there's different techniques that people have experimented with where um you know, like for example, we recently did like the advisor strategy one. But really if you were to generalize it, you just separate like execution from advice. And there's also one where you can have like two, you know, modes where there one is generating someone something and the other one's adversarial to it. And then there could also be sort of like, you know, you split it into a bunch of different like little tiny pieces and then they kind of recombine. And then there's ones where maybe it's kind of something closer to like best of N kind of like style of thing. And then there's so many more. And like in each one of these different types of like architectures or strategies, they are good for a very specific use cases. So some of them are much better for like uh deep research or wide research type of uh style use cases, right? And there are others that are like these are like the kind of ones where they all sort of swarm together are better for like bug hunting, for example. Um and so like that's like really cool to see that like if we can make the primitives very LEGO-like, um then people can put them together to solve things at a slightly higher form factor, which is more like an architecture or like a strategy. Um and they get much more like interesting results out of that. Um and that's like really exciting to see cuz it also suggests that you can actually hill climb at um multiple layers um of abstraction. How do you know if an agent is successful? How do you measure success for an agent? Yeah, I mean, there's like evals and stuff like that which everyone has talked about like ad nauseam. One direction that we we really like is like uh this kind of verifiable outcome. Um we've been somewhat opinionated on that one and it's almost like in the absolute end state of, you know, we talked a little bit about what's what's a platform at the end of things. Um going from that philosophy, it's like our kind of principle of like maybe the end state of some of these things is that everything should kind of compress down to an outcome and like a budget. And that's probably like about it. Um and everything else should be figured out for you to kind of resolve exactly across those parameters. And so for us, we're kind of yes, we still have evals. We have a lot of these other things that we measure that are domain specific like, you know, some coding evals would be like you might want to measure like just the actual PR getting merged. Those are more verifiable. But as we get to the place where you know, you like an outcome is actually a spec that you are just as a human able to define and our ability to interpret that and regrade itself over and over is closer to what we care about. \>\> Claude, make me a billion dollars. Your budget is $10. Exactly. \[laughter\] And then say no mistakes. Go. Exactly. Maybe Mythos could do that. Um and then what one of the things that we've been running into that I'm curious if you have a solution for is agents like get outdated pretty quickly. Um sometimes because there's no human attached to them. Sometimes like they're just running an old model or there's an old in an old architecture or whatever. And it feels like there needs to be a um end of life cycle for agents. Like we've talked about having like a little like funeral for them and like having like a little page on our website that's like here's all the decommissioned agents and stuff. Um like how how do you manage especially in a in a really big company? How do you manage the all the agents that are like sort of out there but and maybe they're like in Slack like pinging stuff once a week but you're like this is super stale. How do you make sure that you you retire them as quickly as you are making them? So one of the things we have actually done is we have made skills that help you do things like upgrade to a new model when a new model comes out, right? Like we've actually put a good amount of work into making it easier to do exactly what you're talking about. Um and I think maybe some of the most like AGI pill people are like running agents that are monitoring their agents to see if their agents are, you know, like outdated and in need of that sort of stuff. But I think for you know, the way that we like to talk to customers who ask us this question. I do the the most interesting instantiation of this is there's a new model and now I need to go upgrade my agents or maybe be done with those agents because, you know, the new model enables me to build agents that are way more powerful and do more interesting things than the old agents did, right? But I think that upgrade process and that migration process is like something people have had to wrap their heads around as like it's like a breaking change and I have to like put actual energy into making that work. Um And obviously, sorry to talk about evals, but like if you have evals, this process is easier and things like this, but I do think that's one of the things we've tried to do is how do we give you skills and how do we give you the right like just tools to make that process easier. Um and then you could go be AGI pilled and choose to actually automate more of that with more agents. Yeah. So, a year from now, we're back at Code with Claude. Um where do you think the platform will be? What will I be able to do and how it will be different from what I can do today? Do you want to go first? You can go first. A year is a long time. It's In this In this industry, especially. How close are we to Claude making me a billion dollars? \>\> \[laughter\] \>\> That's really what I'm asking. I think you probably won't be sitting here. Yes, yes. \>\> \[laughter\] \>\> We'll be asking Claude for this. I mean, yeah, like we want to get closer and closer to that that state where I think we we kind of Okay, so a couple things. I think in a year from now, I mean, one thing that we'd love to get really really close to is actually that kind of like simplicity and this might be significantly higher order of abstraction. I don't know what the form factor will look like or whatever, but the kind of parameters we will care for from users will be that outcome. And of course, it has to be verifiable. There are some parameters that that have to be restrictive. And And the budget. And I think like we'd want to experiment with with directions where Claude actually gets so good at understanding itself. It It figures out what model you should be using. It figures out how to spin up all the sub agents. I actually don't think you need to think so much about harness engineering in that world. Today, you know, you don't have to think so much more aggressively about like tool construction, for example. Like we've kind of made that a little easier and you get to leave a little bit of that scaffolding. \>\> Less prompt engineering, too. \>\> Exactly. And I think if you just keep going up that stack, like today a lot of the innovation is happening at this kind of like like like really high-level, almost like harness architecture-like level, which is really fun. But I think a lot of that honestly also kind of goes away where you almost like don't have to think so much about like model selection and you don't have to think so much about what kind of architectures are there because we probably would have would have like gone through enough iterations with Claude where Claude is actually able to understand itself enough um that it can come almost like write itself on the fly to figure out what is necessary in that kind of like two-parameter world of like outcome and budget. I don't know that we'll get there like in a year, but I feel like we might be able to do like the outcome part of that with like maybe, you know, some bars of some error bars on on the budget side. Really cool. Yeah. Um okay, that was really cool. I'm going to give you a slightly more boring answer, which is in that world, if Claude is like on the fly or agents on the fly are like becoming what they need to become in order for you to do what you're trying to do, the platform has to like seriously scale. That it does. Um and so I do think some of this will be what are the right abstractions that actually enable that, right? Like somewhere on the primitive to higher order realm, right? But I do think so much of what our team is going to be doing is making sure that the tokens that people want to come in and out um are going to be able to come in and out of Claude because our system is scaled to meet not just the demand, but like in that world where it's just like you have agents that are like literally constantly running and recreating themselves and and doing this sort of work. Um you just need a system that, you know, can handle long-running requests, can handle a bunch of differently shaped things. And so I think for us it's going to be I never want the ability of the platform itself to be able to scale to get in the way of what people would otherwise be able to accomplish with these things. And so, I think that's something that's going to probably be very front of mind when we're talking in a year. Awesome. I'm excited. Um thank you so much for joining. I really learned a lot. Thanks for having us. Oh my gosh, folks. You absolutely, positively have to smash that like button and subscribe to AI and I. Why? Because \[snorts\] this show is the epitome of awesomeness. It's like finding a treasure chest in your backyard. But instead of gold, it's filled with pure, unadulterated knowledge bombs about Chat \[snorts\] GPT. Every episode is a roller coaster of emotions, insights, and laughter that will leave you on the edge of your seat craving for more. It's not just a show. It's a journey into the future with Dan Shipper as the captain of the spaceship. So, do yourself a favor. Hit like, smash subscribe, and strap in for the ride of your life. And now, without any further ado, let me just say, Dan, I'm absolutely, hopelessly in love with you.