Interview with Alex Rattray, founder and CEO of Stainless, a company that builds APIs, SDKs, and MCP servers for clients including OpenAI and Anthropic. The conversation covers what MCP (Model Context Protocol) is and why it exists, the tradeoff between tool specificity and tool count when designing MCP servers, design principles for reliable MCP servers, how Stainless uses MCP for business operations, Rattray's view on MCP's security model, and how one-off AI actions become permanent production software. (Disclosure: host Dan Shipper is a small investor in Stainless.) # Channel Identity Observations — Video `01a0f15a-85e8-706a-af2f-081a29cf99b3` ## Explicit Self-Description ### Show name and host - The host is named **Dan Shipper**; the outro names the show: *"subscribe to AI and I… a journey into the future with Dan Shipper as the captain of the spaceship."* - The host refers to it as "the show" in the intro: *"That's why I brought Alex Ratray, the founder and CEO of Stainless, onto the show."* ### Stated audience assumptions - The host addresses an audience already familiar with MCP: *"I'm sure anyone familiar with, you know, with every and and who's regular listeners is going to be familiar with MCP, model context protocol."* — implies an audience of **regular listeners versed in AI/tech topics**. - Guest assumes a technical-but-not-expert audience: *"to start, like what's an API?… not everybody's familiar with that."* ### Host's disclosed affiliations - Host discloses: *"I'm a tiny investor in Stainless"* and describes the guest as *"a good friend of mine… we were very good friends in college."* - Host mentions his own products/company during the interview: *"I'm thinking right now about Coral, the email assistant"* and *"you had a conference room at a venture capitalist office as your office"* — referencing his startup history ("everything happening with Every"). ## Observable Presentation Evidence ### Format - **Long-form interview podcast**: host-led conversation with a founder/CEO guest, opening framing monologue, mid-roll sponsor read (*"Braintrust is the AI observability platform… Get started at braintrust.dev"*), and closing outro. - **Technical depth for practitioners**: detailed discussion of MCP tool design, context-window limits, OAuth scopes, SDK ergonomics, evals — e.g., guest advice to *"keep the number of tools relatively small"* with *"tool name and the description be really precise."* ### Claimed scope - Intro claims coverage of AI-internet infrastructure trends: *"the software companies that learn how to do MCP well are going to win over the next decade"* and promises discussion of *"what the future of MCP looks like, how to design good MCPs, why MCPs are actually really hard to scale and possibly insecure."* ### Demonstrated audience - Audience is addressed as **builders/founders and AI-technical listeners**: host pushes guest on product strategy (*"there might be a version that you could do… for individual developers… people like me who are building at this scale"*) and asks practical adoption questions (*"Are you using MCP servers yourself?"*). ### Cross-promotion / engagement patterns - Hyperbolic automated-sounding outro asking viewers to *"smash that like button and subscribe to AI and I"* — the title references **Anthropic's $300M acquisition of a dev tools startup** as a news hook for the interview. ## Notes on Claim vs. Demonstration - No explicit channel-wide mission statement appears beyond the outro's promotional language ("knowledge bombs about chat GPT"); scope is demonstrated through topic selection (MCP, agentic AI, developer tooling) rather than a formal channel description. - Host-guest friendship and investment disclosure is a self-described claim, included here as stated, not as evidence of motive. # Delivery Observations ## Overview Interview-style conversation between host **Dan Shipper** and guest **Alex Ratrai** (founder/CEO of Stainless), on the topic of MCP and AI-internet interaction. --- ## Guest Delivery (Alex Ratrai) ### Teaching Through Analogies - **Biology analogy for APIs**: > "APIs are are the dendrites of the internet. Um, dendrites are where your neurons connect um and actually exchange information with each other." - **Simplified definitions before diving deep**: > "So to start, like what's an API? Um, uh not everybody's familiar with that, so um, it stands for application programming interface." - He explicitly checks comprehension stakes with humor: > "Um, there will not be a quiz, right? Right, Dan? No quizzes?" ### Concrete, Narrative Examples - Alex repeatedly grounds abstract points in a running **"stripey socks" customer refund** scenario: > "let's say, you know, Dan walks into my store and buys a pair of stripy socks." - Uses specific product/code examples: > "you'll write stripe.customers.create" and "pip install Stripe." ### Heavy Verbal Disfluency Pattern - Very frequent filler and repeated words, e.g., > "it's it's how a one computer program talks to another computer program," > "Um, uh not everybody's familiar with that." - Repeated word-stuttering appears throughout: > "we're we're we're using this also for for hey, a customer comes in with a question." ### Epistemic Honesty / Calibrated Claims - Frequently states limits: > "Is that going to work out 100% of the time? Definitely not. Is that going to work out 50% of the time? Still no, um, to be honest with you." - Flags difficulty of his own recommendations: > "Good writing is hard," > "That's also very hard cuz you may not know a a priori which things the model's really looking for." - Uses "I think" / "in my view" hedges often: > "in my view, that's kind of the that direction is sort of the right the right layer." ### Aspirational/Futuristic Framing - Coined-phrase style claims: > "the the the future of AI is cyborgs." - Describes unpublished work vaguely but positively: > "we're cooking something up that I'm really excited about" — repeated phrase pattern ("cooking up" appears at [1229] and [1150]). --- ## Host Delivery (Dan Shipper) ### Active Listening & Restatement - Dan frequently paraphrases guest points to confirm understanding: > "what what MCP does is just like a a website is built for humans to be used. MCP is sort of the equivalent... of exposing a set of tools for the model." - Follow-up restatement: > "It's just model writes API code, and API provider uh executes that code, runs it on their API, and returns the results." ### Enthusiastic, Informal Reactions - Casual exclamations: > "That's [ __ ] so cool," > "Wait, that's crazy," > "You guys should build that." - Humor and teasing to build rapport: > "The longer you wear your feet." ### Direct Challenge / Pushback - Dan pushes on tension in claims: > "Aren't those two things at odds?" - Strategic pressure framed as investor persona: > "I want to I want to push you as a as a hashtag value add investor," arguing YOLO-style products beat cautious ones (DALL-E vs. Stable Diffusion, Claude Code vs. Codex examples). ### Practical Extraction Habit - Dan repeatedly asks for stealable specifics: > "like what what are you actually doing and what is the report that comes out and how often are you doing that... so I can tell me so I can steal it." - Asks for concreteness explicitly: > "is there anything specific you've learned... but like more concrete, more more applicable stuff?" --- ## Structural / Format Habits - **Framing intro**: Cold open explains stakes before introducing guest: > "The internet runs on computers talking to each other, but it's entire architecture was built for a pre-AI world." - **Topic-preview habit**: Host previews content: > "Alex and I get into the nitty-gritty of what the future of MCP looks like." - **Personal-relationship framing**: Both speakers emphasize friendship history ("we were both starting companies in college"; Alex: "you let me crash there"). - **Mid-roll sponsor read** with a relatable failure scenario: > "And then 3 days later or even sooner, the support tickets start rolling in." - **Humorous exaggerated outro**: Over-the-top subscribe appeal: > "you absolutely, positively have to smash that like button and subscribe," ending on a joke: > "Dan, I'm absolutely, hopelessly in love with you." ## Uncertainty Notes - Speaker attribution between "Dan" and "Ian" is inconsistent in the transcript ([6], [77]) — likely a transcription error; identity of the speakers should be treated as Dan (host) and Alex (guest) per the closing outro. - The outro and sponsor-read voice may or may not be the host's normal delivery; only one instance of each appears, so no pattern can be claimed. # Observation Document: Stainless, MCP, and the Future of AI Tool Use ## Speakers - **Dan Shipper** (host, "AI and I"; identifies himself as a tiny investor in Stainless, friend of Alex from college) - **Alex Ratray** (founder and CEO of Stainless; previously worked on the Stripe API) *Note: the transcript's names ("Ian," "Dan") are inconsistent; both apparently refer to the host, referred to here as Dan Shipper per his self-identification.* --- ## Framing Claims (Host, Dan Shipper) - The internet's architecture was **built for a pre-AI world**; MCP (Model Context Protocol) turns websites/web services into tools AI can use natively. - **"The software companies that learn how to do MCP well are going to win over the next decade."** - Stainless makes APIs/SDKs for major companies including OpenAI and Anthropic, and is starting to build MCP servers. --- ## Alex Ratray's Positions ### On APIs and Stainless's mission - APIs are "the **dendrites of the internet**" — without connections between programs, no software activity occurs, analogous to neurons that must connect for thought to happen. - Stainless's mission from day one: make it easier for computers to talk to computers. - Automation is the long-running trend of technology; APIs are how most business-to-business interactions become automated. - LLMs are a **"new computer"** that needs a way to interact with other systems — hence MCP. ### On MCP's current shortcomings - The core vision: an agent should handle a multi-app task (e.g., "refund Dan for the stripey socks and send a discount code") by traversing five apps and 15 screens, as a human operator would. - **The central problem: context window limits.** Exposing the full Stripe API as MCP tools — hundreds of endpoints with full documentation — would "burn through your entire context budget" (potentially hundreds of thousands of tokens). It's also "confusing to the model." - Additional problems: - **Security/permissions**: the AI could "color outside the lines" (e.g., refund every customer, send money to its own account). - LLMs struggle with **repeated sustained chains of actions** and paginated data ("needles in the haystack"). - To succeed today, MCP tools must be **handcrafted for the LLM** rather than a one-to-one mapping of API endpoints. - Analogy: humanity took a long time to learn to make great Python SDKs; exposing an API ergonomically to an LLM is a **new research problem**, harder because "I can go learn how to be a Python developer... I can't really learn how to... see like an LLM." ### On designing good MCP servers - "There have been relatively few times that I've seen it done well." - Principles: - **Keep the number of tools small**; keep tool names and descriptions **precise and specific** — Dan notes these two goals are at odds; Alex: "Yes. Good writing is hard." - Small number of concisely-but-sufficiently described input parameters. - Return **minimal response data** — only what the model needs (hard because you may not know a priori). - A trick Stainless uses: giving the model a **jq filter** to filter JSON. - Requires good product management (customer research), strong **eval systems**, and accounting for a "pretty crazy matrix" of clients (Cursor, Claude Code) and models. Feedback to the server is a **black box**; Alex suggests a "send feedback tool" so servers learn when users say responses were "useless garbage." - **Tool browsing** approaches: exposing every endpoint works for small APIs; "dynamic mode" (three tools: list endpoints, get endpoint, execute endpoint) scales context well but adds latency, cost, and "some lossiness." ### On his own MCP usage - Uses MCP mainly on the **business side**, not coding: Notion, HubSpot, Gong, and a **read-only database** MCP server to identify interesting new signups and cross-reference data. - Caveats: still "playing around mode"; servers disconnect; "a lot of little paper cuts." - Practice of **"collecting notes for the AI by the AI"** — a notes/research folder in a special Git repo where Claude Code stores customer quotes (with full citations) and refined SQL queries for reuse (e.g., board-prep metrics). - The repo is messy and contains confidential info; he's not prioritizing structure yet because "Claude code can handle unstructured stuff really well." - Claude Code sometimes attempts to fix incoming customer bugs from Linear tickets; success rate is **"Definitely not" 100%, "Still no" to 50%** — explicitly experimental, "but we're seeing a lot of promise." ### His big vision: "The future of AI is cyborgs" - Agents will be **part LLM, part traditional CPU code**. - **Code execution as the super-tool**: instead of a "bajillion tools," the model gets (1) a code-execution tool (write TypeScript using the API's SDK) and (2) a docs-search tool. - Benefits: minimal upfront context (~1,000 tokens or less), zero context cost for paginated list operations, fast CPU execution near the API, tiny context hits on return (e.g., "10 lines of text"). - Models are "really good at writing code" and extrapolate well from SDK patterns. - Limitation of running code yourself today: **LLMs struggle with libraries** (versions, hallucinated APIs). Without a typed library, the model must use raw HTTP plus the massive OpenAPI spec — "back at square one." A code-execution tool with a **type checker** can catch errors inline and even use a sub-agent trained on the API to suggest corrections. ### On security - Security "has to take place at the **API layer itself**" via OAuth with granular permissions/scopes — not by limiting what's exposed through MCP, since MCP can reach anything the API can underneath. - Acknowledges OAuth scopes have limitations and are hard to build; "it'd be nice if someone made that easy." - Sandboxed code execution should allow **no outbound network connections** except the target API (e.g., only api.stripe.com), expandable incrementally. ### On what Stainless is building - Building the code-execution tool; **"We're working on it"** (in response to Dan urging them to build a controllable computer-use environment for developers). - Starting with MCP server providers, but ultimately the model needs one environment reaching multiple APIs — "but not too much anything else." - Once a code-execution "super tool" exists, **the only way to build a tool will be instructions/prompts** — though he qualifies: "we'll see if it's that quote-unquote easy... prompt engineering can be really tricky." - Repeated one-off agent actions that prove "enduringly useful" should be committed to the repo — mirroring how software teams automate repetitive work. - Stainless's generated MCP servers let developers mix and match API parts when composing tools. --- ## Dan Shipper's Positions - **Pushback on caution**: first attempts in AI are often overly cautious, but "the things that get adopted are often the ones that are willing to take the risk to be YOLO very early." Examples he cites: Stable Diffusion overtaking DALL-E's gated access ("fumbled the bag" but had a lead); Claude Code outpacing Codex CLI because of skip-permissions industriousness versus Codex's pair-programming, locked-down design (noting Codex has since caught up). - He argues smaller AI-first builders adopt faster than big enterprises and wants an early version of the code-execution environment he could use "immediately" — for **Cora**, his email assistant (mainly the Gmail API). He says such a tool would make it "much more flexible for us to make more tools and not break old ones." - His own framing: "chat is a really good interface for exploring, but sometimes you just want a dashboard." --- ## Sponsor Segment (Host-read) - Ad for **Braintrust**, an AI observability platform combining evals and observability; customers listed include Notion, Stripe, Zapier, Vercel, Ramp; SOC 2 Type 2, GDPR, HIPAA compliant. --- ## Preserved Tensions & Qualifications - Small tool count vs. precise descriptions — explicitly acknowledged as conflicting; left unresolved. - Dynamic mode solves context but adds latency/cost/lossiness — no settled resolution. - Alex's internal tooling success claims are heavily qualified (not 100%, not even 50%, "experimental"). - Dan (investor) pushes for faster, riskier rollout; Alex does not directly concede the timeline, only offering "I would love to get this in your hands." - Alex repeatedly hedges his vision claims: "we'll see if it's that quote-unquote easy." # Speaker Attribution Record ## Video **Title:** Anthropic Just Bought a Dev Tools Startup for $300M. Here's What Its Founder Told Me. **ID:** 01a0f15a-85e8-706a-af2f-081a29cf99b3 **Format:** Interview/podcast conversation ## Identified Speakers and Roles ### Dan Shipper — Creator / Host - Primary host of the show, identified in closing promotional segment as **"Dan Shipper as the captain of the spaceship"** and via show name "AI and I." - Also identified as **a small investor in Stainless** (self-described: "I'm a tiny investor in Stainless") and a **personal friend of the guest from college**. - Refers to his own company/product **"Cora" / "Coral"** (an email assistant), apparently part of "Every" (mentions "everything happening with Every"). - Addresses guest variously as "Ian," "Dan," and "Alex" in the transcript — an apparent **transcription inconsistency**; the guest is identified as Alex at the outset. ### Alex Ratray — Guest - **Founder and CEO of Stainless**, the interviewee. - Formerly worked **at Stripe on their API** (stated by host; confirmed in context). - Identified by host as making APIs/SDKs for companies **like OpenAI and Anthropic**, and building **MCP servers**. - Host notes Stainless has **~50 employees** (guest confirms "just about"). ### AI Voice / Narrator (Implied) - The closing promotional segment ("smash that like button... I'm absolutely, hopelessly in love with you") shifts voice and appears to be an **AI-generated narrator/promo voice**, not Dan Shipper speaking naturally. Flagged as a **promotional segment**. ## Promotional Segments (Flagged) ### 🚩 Mid-Roll Sponsor Read: Braintrust - Delivered by the host (or production voice), promoting **Braintrust** as an "AI observability platform." - Cites named customers: **Notion, Stripe, Zapier, Vercel, Ramp**. - Claims: SOC 2 Type 2 certified, GDPR and HIPAA compliant; SDKs for Python, TypeScript, Go, Ruby, C#. - Call to action: "Get started at braintrust.dev." ### 🚩 Closing Subscribe Promotion - Exaggerated "smash that like button and subscribe" segment for the show "AI and I," in a voice claiming to be "in love with" Dan Shipper — characteristic of an AI-generated promo bit. ## Third-Party Companies/Products Referenced (Not Speakers) - **Stainless** (guest's company; stainless.com), **Stripe**, **OpenAI**, **Anthropic**, **MCP (Model Context Protocol)**, **ChatGPT/Claude/Claude Code**, **Notion, HubSpot, Gong, Postgres, Salesforce, Slack, Cursor, Linear, Gmail, Codex/Codex CLI, DALL-E, Stable Diffusion, Every, Cora/Coral.** ## Uncertainty Notes - Host's name varies in transcript ("Ian," "Dan"); the closing promo explicitly names **Dan Shipper**, which is treated as authoritative. - Video title references an Anthropic acquisition "for $300M" — this claim is **not substantiated within the transcript itself**. - No curated metadata was supplied; comment availability is **unknown/not recorded**. - No timestamps available in the transcript; segment order is inferred from transcript sequence. The internet runs on computers talking to each other, but it's entire architecture was built for a pre-AI world. Now we're trying to hook AI up to the internet with MCP, model context protocol, which turns any website or web service into a set of tools that an AI can use natively to get work done. And the software companies that learn how to do MCP well are going to win over the next decade. That's why I brought Alex Ratray, the founder and CEO of Stainless, onto the show. Stainless' job is to help computers talk to each other. They make the API and SDKs for all the big companies that you know about, like OpenAI and Anthropic, and they're starting to build MCP servers, too. So, Alex and I get into the nitty-gritty of what the future of MCP looks like, how to design good MCPs, why MCPs are actually really hard to scale and possibly insecure, and we try to figure out together what a better model for allowing AIs to use the internet might look like. This is a great episode. Alex is a good friend of mine. Let's dive in. Alex, welcome to the show. \>\> Thanks, Ian. It's uh really exciting to be here. \>\> It's good to have you. So, for people who don't know, you are the founder and CEO of Stainless, which is the API company. Uh you make APIs for companies like OpenAI and Anthropic, and just name your big company that you might use their API, Stainless is probably behind it. Um before that, you worked at Stripe doing their API, surprise. Um and before that, most importantly, we were very good friends in college, and we remained good friends. Uh and we were both starting companies in college. I'm a tiny investor in Stainless, uh but it's been really, really fun to watch your journey and get to get to hang out together so much over the years, and uh I'm just very excited to bring you on to talk about AI and and what you're doing at Stainless. \>\> Thanks, Dan. Yeah, it's um it's uh been really fun over the years. I mean, you know, when when we were in college, um I was working on a startup, you were working on a startup, you you had a conference room um at a venture capitalist office um as your office and uh you let me crash there um with uh with my co-founder and team. Um and we were just like on the other side of the conference table hacking away into the evening um uh and you know, very fun memories of those days and and these days it's it's not every evening, but you know, on the weekends, whatever, same thing is still happening um and it's you don't you don't see that every day and it's it's it's really nice feeling and um it's been great to see everything happening with Every um along the way. \>\> Thank you. As I say, started from the bottom, now we're here. Um uh I and uh yeah, I mean, I the thing that I always say when people when I run into people and they ask me about you, um in order to embarrass you, I I just talk about how you're the only person that I know of who has consistently run barefoot through the streets of Philadelphia uh cuz when we first met, you were you were not a fan of shoes and you were a fan of running. You want to talk about that? \>\> Yeah, it wasn't that I didn't like the concept of shoes, it's that I couldn't find a good pair. Um and at a certain point, you know, it's like I was running through Nikes and they would they would bust open every few months. Um I think what was actually going on is that I had really wide feet. Um I was I I was buying probably narrow shoes um but they would shoes would constantly get ruined. And um you know, on a college budget, it's just like this is this is it this is no good. Um and uh eventually I decided, okay, the longer you wear your shoes, the the more worn out they get, but the longer you just wear your feet, the tougher they get. Um, so \>\> The longer you wear your feet. \>\> Try it out. Try this at home. What could go wrong? Uh, I actually currently have a really annoying splinter in one of my feet uh that I was uh and so don't actually uh try this at home, but um \>\> Are you still running barefoot? \>\> No. No, this is just from around the house. Um \>\> I see. Dangerous. \>\> Yeah. Yeah. But see, that's the thing. If I had been going around uh on the asphalt um without socks on, then uh my feet would have been tougher and I'd have no splinter. \>\> Um, so when you're not running barefoot, uh you're running you're running stainless. Um So, you're running stainless and so how how many people are you are you now you're you're around 50, right? \>\> Just about, yeah. \>\> That's that's pretty wild uh and you started stainless in a pre-AI world and now we're in an AI world and I think you have some ideas for what the future of AI is going to be and maybe how how APIs fit into that, maybe how MCPs fit into that. Do you want to like paint a little bit of a picture for us about where we're going? \>\> Yeah, I would love to. Um, so to start, like what's an API? Um, uh not everybody's familiar with that, so um, it stands for application programming interface. Um, there will not be a quiz, right? Right, Dan? No quizzes? \>\> No. No quizzes. \>\> Great. Um, but basically it's it's how a one computer program talks to another computer program. Um, it's how it's how computers talk to computers, how apps talk talk to apps. Um, and so APIs are are the dendrites of the internet. Um, dendrites are where your neurons connect um and actually exchange information with each other. So, if you have like two neurons in your brain, but they're not talking to each other, uh you're actually not thinking, right? There is no thought happening in a brain without connections between neurons. And if you think about the internet, if all these servers in the cloud aren't talking to each other, you wouldn't you wouldn't have internet, right? Like there's there's nothing going on if you know, programs internet software is doing nothing without APIs, without connections to to other programs. And so it's really fundamental to the nesh to the mesh of pretty much all modern software. Everything that we think of when we think about technology at this point, APIs are kind of at the the heart and center of that, just like um dendrites are, you know, the center of the mesh of the of the brain and and how we think. And Seamless's mission from day one was sort of to make it easier for computers to talk to computers, so and um you know, it's the long running trend of technology to have more automation, right? Automation is what we mean when we say, okay, we're going to, you know, we're going to we're going to apply technology to that. You know, we're trying to be making things more efficient. And APIs are how most business-to-business interactions in some format or another become become real, become automated. Um and what we see with the the rise of AI is that there's a a new a new computer has entered the chat, right? There's a new there's a new kind of system that can talk to other systems. At least we would like it to be able to. Um you used to have either, you know, humans interacting with a computer through a user interface, a UI, or a computer acting with a computer through through an API. And now we have LLMs interacting with computers, right? What's that through? And I'm sure anyone familiar with, you know, with every and and and who's regular listeners is going to be familiar with MCP, uh model context protocol, which is um a system for connecting LLMs to to computers, uh broadly speaking. Um and it's an area that we're investing in at Stainless. It's really, I think, part of our core mission of, you know, like I said, make it easy for computers to talk to computers. And um we've invested a lot of time, you know, at Stainless the core product that we first brought to market is um software development kits, SDKs. And so, these are ways of saying, "Okay, Stripe has this great REST API, you know, you can send JSON over HTTP and get back JSON over HTTP." Um and if you want that to be really convenient, you're going to use the Stripe Python library, the Stripe Python SDK. So, you can go, if you're a Python developer, you'll go pip install Stripe, and then um in your application code, you'll write stripe.customers.create, and all of a sudden you have a nice new customer object in in sort of your Stripe database. Um and you're off to the races. Um or stripe.charges.create in the old days, um to charge a credit card. Um and and SDKs are what gives developers that easy way to to to interface um with an API. What's the thing that gives LLMs an easy way to interface with an API? And you might say MCP, and in a sense you'd be right, um but what we're seeing so far as MCP is rolling out um into the world and people are experimenting with it and trying it out, um is that it's not working so great. Like, there's it's it's difficult to deliver on what I see as the core vision of of what's so exciting about MCP, um which is just like a a dashboard and a user interface. Lets you click around, see a bunch of stuff, fill out forms, click buttons, do things. Anything that you would do while you're interacting with the software, you do through the user interface generally. Um, but LLMs interacting with through MCP it tends to be much more restricted. You can only do a few little things. There's usually not a ton of tools that you're going to be exposing to the models. Um, \>\> And And just just just to stop you there. So, I think what I'm hearing you say is what what the what MCP does is just like a a website is built for humans to be used. MCP is sort of the equivalent and you can think of it in in certain ways of exposing a set of tools for the model that it can it can use to perform certain functions. Just like you might click a button on a website, the MCP gives to the model a bunch of things it can click on or use to get work done. So, an example might be you know, an a Gmail MCP has like a send mail tool or like a compose mail tool or a read inbox tool, that kind of thing. And instead of a human going on the Gmail website and doing it, it's the it's the LLM is like, you know, essentially logging in and and and using it itself. And it's a it's a native interface for for language models. But you're saying that that's not working that well. Can you tell me more about that? \>\> Yeah. Um, so let's let's start actually with with kind of what I see as the big vision of MCP and in some sense the big vision of agentic AI in the first place. Um, and I'll start with the most pedestrian example you can imagine. It's going to be funny given some of our context. Um, which is let's say, you know, Dan walks into my store and buys a pair of stripy socks. Um, and maybe a few other things. And then the next day I hear back from Dan that there was something wrong. Unfortunately, it happens, you know. And I turn to someone on my team and I say, "Hey, um can we refund Dan for those stripey socks he bought yesterday and send him a discount code for for the next time he comes in with like a little thank you note um cuz we like to take care of our customers. Um this is like the most normal thing to do in software is is some little task like this. And what you're going to do what you know, the member of my team would be doing would be opening up um their internal admin and looking around for some things. They might go to the stripe dashboard and try to look through the list of payments or list of transactions or orders and try to find one that has someone named Dan. Who which Dan? I don't know, there might be a bunch of Dans. Try to look through the list of products in the order and see whether there was some stripey socks in there. That might be a few clicks required depending. Um find the right one, then go to the screen where you can create a refund, create a refund, make sure it's the right amount, um then go and create that discount, and then take that discount code and send it over to some other SaaS app where you log in to um send some some mail automatically, right? Um and of course, if you step away from the consumer version of this to a business-to-business context, of course, you might be going into Salesforce and sending a Slack message to an account um administrator, you know, an an account manager, uh so on and so forth. And in the normal course of of work, it's just the most normal thing in the world to be doing having one task involve going through five different apps each time, 15 different clicks and scrolls and loadings loading spinners um just to do sort of like one simple thing. And the promise of Agentic AI is to be able to take that same prompt I just said and type it into ChatGPT or Claude or whatever and say, "Hey, Chatty, buddy, can you help refund my my friend Dan da da da da da um and just have the AI go off and do that. And basically go through these five different apps and the 15 different screens and the various different, you know, button presses to complete the task and then come back and say, "Great, it's done." That in order to do that Now, that's there's only so many tool calls you have to make as a as an AI model to perform that exact linear chain of events. It's it's somewhat tractable. But if you think about this in the general case, you want the LLM to be able to do the you want your agentic AI to be able to do anything that that human operator would have done. And you would want them to be able to do it without having to wait for a bunch of JavaScript to load on a website or anything like that. And that means you need not only the Stripe create refund tool and the Stripe list transactions tool and the Stripe, you know, list products and look up customer and, you know, create discount tool. You need not only those tools, but you need everything that you can do in the Stripe dashboard, which is basically everything that you can do in the Stripe API. And that's actually a lot. Like there are hundreds of different endpoints that you have access to in the Stripe API. The Stripe dashboard is is actually massive. It's a huge application. And if you were to take that list of tools today and go to an LLM and say, "Hey, here's our MCP definition for all of this. Here's a create refund tool. Here's a create transactions tool." So on and so forth. And you tell it all about those tools. Here's the description. Here's all the different request properties that you can send. Here's the response properties you can get back. Here's all the documentation for each of those things. Everyone listening to this should already know you've just burned through your entire context budget. Um that's, you know, maybe a hundreds of thousands of tokens just there. Um just in pretty much translating the Stripe open API spec directly over to MCP tools. Um and today's models not only can't handle that amount of context, it's a poor use of context cuz you have a lot else going on. Uh but it's also confusing to the model. It's just It's just too much to hold in your brain at one time. Um and that's just the straight part of it, right? Um because what you're really trying to do is enable your operators to do anything they would normally do. And again, that spans many, many different SAS tools, right? In the course of one interaction, it might be five. In the next interaction, it might be a different five. Um and so if you think about every single SAS tool that your business uses on a daily basis to get your work done, ideally, you would want every single one of those tools to be exposed to your operators in in their in their AI chat with every single tool available in there, with every single nook and cranny and corner case available. Um so that you can do anything um through AI. That's That's the vision. Now, there's a lot of problems with that. The biggest one that I mentioned is sort of this context uh window limit. Um but you also have all sorts of security and permissions problems because you don't want the AI to color outside the lines and say, "Okay, in addition to refunding Dan Socks, I also refunded every customer for all transactions ever, you know, and then I sent, you know, a bunch of money to my own AI bank account, hahaha." Um and so there's more to the challenge, but that's the vision I see. \>\> Um but I think, you know, the place we started there was you said it's not working. Um but I don't think that that's the reason why it's not working today, right? Or is that is that the reason why it's not working today? \>\> So what people do with MCP today is sometimes they'll try to um expose all parts of their API. Uh the way the way people build MCP tools is is generally speaking they have an an underlying API, usually a REST API, and they wrap different parts of that, different endpoints, different operations in MCP tools. And you can kind of do that in a one-to-one mapping, or you can kind of uh handcraft things for the MCP. And today, in order to succeed, people are finding that you really have to kind of handcraft it to the MCP um to the LLMs. You have to say, "Okay, I'm making one specialized tool to look up a customer and refund their transaction based on a description." \>\> So, there's all these like decisions that you have to make um where you need to have like the ergonomics of the model and how the model thinks in mind in order to make sure the model does the right thing more often than not. \>\> Yeah, it's hard. \>\> It's hard. \>\> Yeah, yeah. So, I use this SDK analogy sometimes. It took a long time for humanity to get to the point where we could make a really good Python SDK for a Python developer wrapping an API and I think we've we've we've cracked that nut. Stainless offers really great Python libraries, but you know, we're building on the shoulders of giants here. A lot of people have um have done this over time. Um we haven't figured out how to expose an API ergonomically to an LLM in the same way that we've figured out how to expose it ergonomically to a Python developer. Um and that's a kind of like a new research problem in a sense. Um and it's harder because I can go learn how to be a Python developer if I want. I can't really learn how to go think or see like an LLM. Um But, uh you know, sure would be powerful if I could. Um And and and that makes and that makes it tricky. We do have at Stainless, I think, some some things that we're cooking up to to address some of these problems including not you know including the ones that you you also mentioned like LMs have a really hard time with a repeated sustained chain of of actions um and you know even like if you get an API response back around hey like list all the transactions there's so much data and you might have to go through the next page and the next page and the next page to go through all the transactions to find the one that has Dan with the stripey socks um and that's again a ton of context you know one or two small needles in the haystack um and LMs are pretty good at that but um they're not perfect and with too with too much hay you know we we we all kind of end up throwing up our hands and and that's true for LMs too um so yeah so there's a lot of challenges today \>\> and um and so when you look at I mean and you're building MCP servers for people um but when you build them and just generally when you see people doing it well today like what are the principles or how do you think about um making an MCP MCP server that one people use which is actually a big one um and then two when it is used actually does the right job \>\> there there have been relatively few times that I've seen it done well I have seen it done well um we're cooking something up that I'm really excited about but with today's technology um you really have to do a good job of product management I mean you have to go out into the market and talk to your customers and see what their actual needs are and look over their shoulders as they you know use and operate you know your software and think about um what could we unlock through AI where people would be doing things that they can't really do with our software today um because it just got so much easier and then you have to do kind of a lot of engineering work usually um to wrap it up in a bow that works for for the models and you have to you know you have to set up a really good system for evals. And if you're doing MCP, you have to think about the different clients that people might be using. Are they using cursor? Are they using Claude code? Are they using something else? And the different models um underlying all of that. So, you end up with this pretty crazy matrix of things that you might want to optimize for uh and ways that you might want to evaluate and make sure that what you're offering is is working well. Um and it's also kind of a black box to get that feedback uh back to your um servers so that you can find out, "Hey, we we gave it we gave it tool call response here. We gave an answer of some kind. Was it actually any good? Um did did the user like it? Um was the LM able to use it? Uh and and that's a problem that I think I haven't seen a lot of people solve um yet as well. And so, um thinking about that as a first-class thing, maybe you have like a send feedback tool. Um that's something that we've been thinking about doing. Um just so if a user like says out loud, you know, in the chat, "Oh man, that was useless garbage." Like, "Okay. Now now now at least the MCP server's going to find out about that." Um \>\> Mhm. But is is there anything specific you've learned about like how to do it well other than like obviously you got to talk to your customers, think about your use cases, but like more concrete, more more applicable stuff about how to design a good MCP server? \>\> You want to keep the number of tools relatively small, uh relatively low. Um you want to uh have the tool name and the description be be really precise and specific. Um uh \>\> Aren't those two things at odds? \>\> Yes. Good writing is hard. Um yeah, I mean, that that's that's why like, you know, you can make a great tool of look up person by name and product description and then refund them. You can make a great tool that does that. Um and you also want a small number of of in you know, properties in the input schema. um you want a a small number of parameters and you want them concisely described but sufficiently described. Um this is this is also hard. Um and you want the response data to come back with a a very small amount of data. Um only exactly what the model will need. That's also very hard cuz you may not know a a priori which things the model's really looking for. Um and you know, we have a technique that we use in our MCP servers today where we give the model a JQ filter, which is a a way of filtering out JSON. Um and that can work pretty well. Um but but that's kind of a a special trick. \>\> Doesn't this mean that like MCP just needs another level of like a search tool function search tools search like find a list of relevant tools given my task? \>\> The The tool browsing problem is is is definitely one very serious one. Um and that is one approach and so we actually do this at Stainless today where you can get an MCP server for your API that just has like I was saying earlier, the very simple thing of every endpoint is exposed as a tool. And if you have a small API, that works great. Um uh you can also filter it out so you expose an MCP server server with only a small subset of of your of your endpoints. That works great. Um you can also use kind of what we call dynamic mode where there's three tools no matter how big your API is. One is, you know, list endpoints. The other is get endpoint and and learn about it. Um and then the last one is execute endpoint. Uh and so that enables this context thing to scale really well, but it means there's three turns of the model just to do one thing. Um and so that that gets slower. It's it's more expensive in another sense. Um and um there's some lossiness. The It It doesn't perform It It performs pretty well um usually but not not quite as well because um the the tools aren't loaded up in quite the same way. \>\> Are you using MCP servers yourself? \>\> Yeah, I use I use MCP um uh to actually uh uh funnily enough not so much on the um coding side, but I use it on the business side. Um so I'll use like the Notion uh HubSpot Gong um MCP servers to kind of say, "Hey, like and and actually an MCP server for for our database um a read-only a read-only copy of our database and say, "Hey, what are the interesting customers that signed up for Stainless last week?" Um and it'll go off and make a great query of our Postgres database and then it can cross-reference those things in HubSpot and then look up our notes in Notion um maybe even look at transcripts in Gong um and tell me all about it. Um it's it's incredible. \>\> Lots of us are shipping AI to production, which is great for productivity, but it also comes with anxiety. You tweak a prompt, swap models, adjust parameters, and everything looks fine in testing, so you merge. And then 3 days later or even sooner, the support tickets start rolling in. The AI is giving your customers unexpected answers, and you have no idea when it happened or why. Braintrust is the AI observability platform that fixes this. It connects evals and observability in one workflow. That way you see what actually happened in production, and you can measure whether a change has made things better or worse. Traces show the full execution path, evals define what good looks like, and experiments let you compare prompts and models side by side before shipping. Production traces feed directly into your eval data sets. Every failure becomes a test case. You catch regressions in CI before they reach users, and teams at Notion, Stripe, Zapier, Vercel, and Ramp use it to ship quality AI at scale. Braintrust is designed for teams building production AI systems where silent regressions are expensive. It's built for any stack. They have SDKs for Python, TypeScript, Go, Ruby, C#, There's no framework lock-in or vendor dependencies. It's SOC 2 type 2 certified and GDPR and HIPAA compliant. Get started at braintrust.dev. That's braintrust.dev. And now, back to the episode. \>\> And so, so that's one of your that's one of your big use cases. Like, are you doing that like every week or how like how are you I'm now I'm interested not even from an MCP perspective, but for anyone running a um business that has some complexity and you're like, I want to know what's going on in the business. Like, what is what are you actually doing and what is the report that comes out and how often are you doing that and all that kind of stuff so I can tell me so I can steal it. \>\> Yeah. Um uh for me it's still usually in kind of like playing around mode. One of the things is the MCP servers disconnect and then I get annoyed. Um and so, you know, you have to just kind of reconnect and whatever. It's not a huge deal. Um uh But, there are there are a lot of little paper cuts still in in a technology this new that you're going to expect um that that can hold back um some amount of your usage. Uh one of the things that I've I found really helpful kind of at the meta level um and I'm sure you've had other guests talk about this um is the practice of just collecting notes for the for the AI by the AI um that and and kind of edited and curated by yourself. So, um you know, I have a like a I I can't remember if I call it a note I I think I have a notes folder or research folder or something like that in a special Git repo um uh that I that I use just for this sort of like internal stuff and I'm like, "Hey, when you find interesting customer quotes, put them in this folder and give the full citation um so that the next time I start asking interesting questions, it doesn't have to go searching through the MCP servers again. It has them kind of cached in um um just on desk um in markdown files. \>\> Wait, that's crazy. Wait, so how are you getting like what are you what are you using to write into that into that get repo? Like is it Claude code? Is it are you using touch of PT? Like how does it get in there? \>\> Yeah, I use I use Claude code these days for that kind of thing. \>\> And so you just have a Claude code open and running and then a new customer testimonial comes in and you're just like hey, can you throw this in in my like get master company get knowledge repository basically and and then whenever you need anything later, you're like Claude like go search through my master repository to figure out where the best customer quote is for this. \>\> Totally. \>\> That's \[ \_\_ \] so cool. What kind of can we see it? \>\> Um No, it's too messy and probably has a lot of confidential information. The latter being more more important. \>\> Is it when you say it's messy like are you having Claude organize it at all or like how is it structured? \>\> There's a lot that that I want us to do here that we haven't had the chance to do yet. There's some there's some other low lower hanging fruit that that I'm working through that that our business team is working through right now just on the on the basics of your kind of CRM systems and so on. Um But um And so and so it's not as it's not well structured now, but I think that's fine. Um yeah, I I I would I'm not I don't plan to prioritize structuring it super super well until we're using it more I'm using it more broadly because you know, I use this stuff some of the time. One of the one of the business people on the team uses it a fair amount. I think like one or two kind of of our customer support engineers use uses this stuff a lot, but it's not yet kind of broader than that and I would like I would like it to get there and once we see how everything's evolving, I think that's when we'll start bringing in more structure, but as it is Claude code can can handle unstructured stuff really well. So you don't have to think about it too too hard in advance in my view. Um, you can move things around later. \>\> What else do you have in there other than customer quotes? \>\> Um, SQL queries. Um, so, you know, I I'm a software developer. Um, uh, I I I don't write a lot of code these days, but, you know, I spent a lot of time doing that. And so, um, when I say, "Hey, you know, can you look up, uh, you know, I might be, hey, how is our month-on-month growth of XYZ metric over the last 3 months?" You know, I did this recently. I did this for my last, uh, board prep. Um, and, um, it came out with a pretty good answer right away. And I was like, wow, this is awesome. And then I kind of looked a little bit deeper, and I was like, oh, I actually want to exclude, you know, these users from this analysis, and I want to filter it this way, and filter it that way. And I kind of imbued more of this business context into that SQL query. And I iterated with, um, with Claude Code, um, to get it to be better and better for the specific kind of metric that I was looking for, the specific kind of story that I was trying to tell. And then I got it to a good place, and I was like, great. Let's dump this to, you know, an analysis folder, um, for, um, or an analytics folder, um, for future use. \>\> Hm. And then next time you're doing your board prep, you can be like, hey, what was that query that we did last time? And it'll presumably go get it. \>\> Yeah. \>\> That's really cool. What else? \>\> You know, as any software, um, team is these days, we're we're we're using this also for for hey, a customer comes in with a question. Can can Claude Code just fix it? Uh, you know, and so you'll have, uh, in some cases a linear ticket is filed, and then, you know, our support engineers are really very technical. Um, and so they may not have the the wall clock time to go down and chase down the fix themselves to, you know, an incoming bug. Um, they have the technical skill, uh, but guess what? Another customer writes in 2 minutes later and and they want to jump on that. They don't want to be um, knee deep in a debugger. Um, and so um, something that we do sometimes is they'll file the ticket um, in case and by default it'll maybe they intend to do it later or some other engineer's going to be doing it later. Um, but hey, can we can we see if Cloud Code can just take a crack at it? Um, is that going to work out 100% of the time? Definitely not. Is that going to work out 50% of the time? Still no, um, to be honest with you. Um, but can that improve the overall efficiency? Um, yeah, maybe. Uh, we're still I would say experimental there. Um, but but we're seeing a lot of promise. \>\> That's really interesting. Okay. Well, I know you also, you know, in our in our pre-production uh, call you were talking about you have a big vision for the future of AI. Do you want to Do you want to talk talk me through that? \>\> Yeah, yeah. I I I would love to. You know, um, we talked earlier about um, how agentic AI can can make um, operators' lives a lot easier by taking their you know, certain pedestrian tasks and sort of running with it independently. Um, and that's something that I think as an industry we're almost on the cusp of. Um, and if you start stepping you know, you ask how you get there and you also start asking about the steps beyond that and beyond that. Um, a big part of of uh, the way I see things unfolding from here, uh, I like to say um, is the the the future of AI is cyborgs. Um, which is like sort of like extra ridiculous because like what is a cyborg other than like already like a a robot? Um, but you know, cyborg as I understand it is a term that means you're sort of like part, you know, person and then part machine. Um, and in this case I mean, um, when you go and talk to an agent, what you're going to be getting is part GPT neural net LLM, part AI, and part code. Um, where the the machine quote unquote that I'm talking about is is, um, traditional CPU not GPU software. Um, and uh, to me I think I expect this to play out in two main ways. One is your kind of one-off operational use cases like we were talking about a minute ago, and then the other is production software. Um, and in in the use case we were talking about a minute ago, um, where someone needs to kind of perform some tricky one-off action with a bunch of points and clicks and now you want an AI to just do a bunch of tool calls. The way I actually see that happening and what we're building towards is code execution. So rather than the model having a a bajillion tools, model has two tools. Um, one to execute code where it just kind of has a text box of like, "Hey, put in some TypeScript and you're going to use this API's TypeScript SDK, and you're just going to write stripe. transactions.list, um, or stripe. you know, uh, charges.list, um, and you're going to stripe.customers.retrieve and stripe.refunds.create. This is really easy for models. They're really good at writing code. Um, and, um, if you give that tool a little bit of sort of a read me where you say, "Here's an example request, and here's some other resources, some other API calls that you can make. It's really good at extrapolating from patterns with if the SDK is sort of and the API are well-formed and predictable. And then you give it an additional tool to kind of search the docs and ask questions to the docs. And anything it's not sure about or gets wrong on the first try, you give it the documentation. And um what this does for that scenario that we were talking about earlier is you have very, very limited um impact on the context window up front. I mean we're talking about 1,000 tokens or something like that. Maybe less. And um the context impact of doing a whole bunch of paginated list requests zero. You know, the the model will go look for somebody named Dan and it'll double-check um that the purchase was stripey socks and you might write three nested for loops, but then only at the end when it found the right thing, it'll console.log found Dan, customer ID blah blah blah, transaction ID blah blah blah. Um and then create refund, you know, refund ID 1 2 3. Um and the context uh hit coming back from all of this is going to be like 10 lines of of text. You know, it's it's really minimal. Um and all of this will run really, really quickly, too. So, you don't have a round trip to the model every time you're doing something like this. It's just CPU code and it runs in a server in the cloud right next to the Stripe API in AWS somewhere probably. Um and it goes super, super fast. \>\> Okay, so what I'm understanding you're saying is like the language model has a tool where it can write code and send that code to the this tool that the you know, whoever the company is, whether it's Stripe or whatever, whoever's MCP server you're using, they'll go and execute that code and that code is going to interact with their API and then return the results, rather than like these sort of, you know, you have 50 different you have 50 different possible tool calls, and you know, all that stuff. It's just model writes API code, and API provider uh executes that code, runs it on their API, and returns the results. Why wouldn't I just um why wouldn't my model just like write the code that I then run myself, instead of relying on an API provider to do it? \>\> Um I expect that that will happen a lot more. I will expect I expect that the code execution tool is going to become the most widely used tool. Um the problem One One of the problems that we have today is that um the code execution tool doesn't work so well with libraries. LLMs have a hard time working with library, and knowing exactly what version of the library it's using, using the right version, probably usually the most late the latest version. Um and um uh not hallucinating, you know, aspects of the API, and knowing how to iterate if it hallucinates wrong. And if it can't use any library off NPM, or or, you know, uh the Python package index, or anything like that, really really well, basically perfectly out of the box, um then, okay, well, s- forget about using um a library. At that point, you just have to hit the raw HTTP API. And at that point, in order to figure out what's in there, you need the whole open API spec, and you're back at square one, because that document is massive. Um and furthermore, something that's really scary about that is if you don't have a typed library with with static typing, where the computer can say what you're trying to do is wrong, then the LLM will try to make an API request that is wrong some percentage of the time. The code execution tool can run a type checker, and say, "Oh, you know, you're asking about stripe.transactions.list, but that actually doesn't exist. Stripe doesn't have a transactions API. You might want payment intents, you might want orders, you might want balance transactions. Which one do you want?" And if you if the API provider is doing a great job building this tool, it'll return the documentation for all of these things in line. It might have its own AI look at what the model's trying to do and come up with suggestion. Um and that and that sub-agent, you know, is well-trained, specified, always updating, um and isn't burdened with the context of the full conversation. \>\> Hm. What do you think of the security model? \>\> The security model is really, really interesting. Um I This is another area where um we're really starting to think about things um at Stainless and I'm getting really excited about it. So, if any listeners are are really interested in this and and have some ideas or um want to talk, you know, please do reach out. Um At the end of the day, I think the security has to take place at the API layer itself. Uh right now, you see people trying to implement security by sort of limiting what's exposed through MCP, and that kind of makes sense, but at the end of the day, you you you you could do anything that's in the API under the hood, right? Um and what people should be doing is using OAuth with granular permissions with with with um with proper scopes. And at that point, the security happens the right place, which is at the API layer. Um there's limitations to OAuth scopes, um and it's pretty hard to build. Um so, it'd be nice if someone made that easy, but um in my view, that's kind of the that direction is sort of the right the right layer. \>\> So, go going back to my my earlier question, I'm I'm I'm thinking about the the of having a model write code that then the API provider executes to, you know, interact with their API and then returns the results. Would you ever consider just creating a tool use tool that developers use? Because like, for example, I'm thinking about for Cora. Got all these tools. Maybe Gmail's going to build, you know, like a code use thing or whatever, but really I just want um I would probably use what you're talking about inside of Cora, but we we would need a uh a tool use tool or like It's not a tool use tool. It's like a It's a computer It's a computer use tool. Where and I know OpenAI has this, but it's not really well built for for for for lots of libraries and stuff. It's not a custom environment. Like I need a computer use tool where I control the environment and I can install different libraries in it and uh be able to call it anytime to to then call any any API or it has to have network access, basically. \>\> Yeah. \>\> You guys should build that. \>\> We're working on it. \>\> \[ \_\_ \] yeah. You're building it for for for uh for developers who want to access MCP servers or people who are providing MCP servers? \>\> We're starting with people who are providing MCP servers, but ultimately I think that we're going to need this to work such that um you can give the model a a code execution environment where it can hit not only the Stripe integration, but also the Salesforce integration and also anything else. Um and but not too much anything else, right? And so one of the advantages of starting where we're starting of just one API provider is that you ensure that there's no network connections allowed out of that sandbox where we're running the code to anything other than in this case api.stripe.com. Um and that's that's really really critical for security for something like this. Um and so there's ways to expand that bit by bit um and keep things and keep things secure. Um Uh it'll it'll it'll take some time. The other thing I think to point out as you see some of these generalizations is it's not just that you want this like code execution sandbox to work really well for any API, for any library, um which I think we really do. I think I think we really need that. Um you also start to see that you This is just a powerful model for AI doing stuff and sometimes you you want you realize that the thing that the AI did this one time in this one-off case is actually enduringly useful. Maybe anytime a customer writes into support and says, "Hey, my socks had holes in them." You should automatically get a refund, you know. Um maybe you want that, maybe you don't, but there's a lot of stuff that people do one or one time and then two times and then three times and then they say, "Okay, we should automate this." Right? And that's and that's what software teams do all day every day, right? And we're going to be I think we're also going to be seeing that with AI where the same the the same code search tool that we're talking about, all the same prompting that will make an AI really really good at interacting with an API in one of these code sandboxes, kind of like almost \{quote\} in \{quote\} in its brain, um or kind of like write code in its head, run the code in its head, see the results, and then move forward with your with your with your query. Um with your task. Uh it should be able to say, "Okay, actually this is enduringly useful code. Let me Let me commit this to the repo." \>\> Yeah, yeah. Yeah, yeah. It's like uh you know, um chat is a really good interface for exploring, but sometimes you just want a dashboard, you know? You just I just want to like log into my Stripe dashboard and see all the stuff without having to be like, "What is my MRR?" It should just show up, you know? Cuz I just do that every day. Um but I want to I want to push you as a as a hashtag value add investor, um because I I think that there's a um I think that there's this thing that happens in AI where often the first attempt at something like this, um people try to be really cautious. And I'm sure that your customers care about you being cautious, like big enterprise customers. But the things that get adopted are often the ones that are willing to take the risk to be YOLO very early. So, an example is um DALL-E was like totally private for like a long time and people were like posting some images, but you couldn't get in. And then uh Stable Diffusion was just like, "Fuck it. Like anyone can use this." And then that just really started the whole im- image generation wave. Obviously, Stable Diffusion sort of fumbled the bag, but they had a lead for a little while. Um same thing for for Cloud Code, honestly. Like, if you look at uh Codex is not like this as much anymore, but if you look at the difference between Codex CLI and Cloud Code, Cloud Code was just like, "Fuck it. Like, YOLO mode. It's super industrious. It has a sandbox, but you can just do dangerous \[ \_\_ \] Skip permissions." And Codex just fell way behind because it was First, it was in the browser, and so their whole thing was the whole thing was like locked down. And then it was in the it was in the in the CLI, but it was really built for pair programming, and so it just wasn't particularly industrious. It it wouldn't go off and do a bunch of stuff. It it didn't it it would get locked out of doing certain things even if you did full auto mode. Um and now they've like caught up because they're they're like Yeah, you can just let it do whatever you want. And so, I would I would really push you on there might be a version that you could do like today or tomorrow or like very soon for individual developers that would let them set up this environment that, for example, I would use like immediately. And I can't I I care about security, but I care I care a lot less than some ex, you know, gigantic enterprise company. But I think that people like me who are building at this scale \>\> to be the big companies, but we're the ones that are really doing the AI first adoption, not the big not the big companies. \>\> Well, I would love to get this in your hands. What what are some of the APIs your team uses the most? \>\> Um I'm I'm thinking as we've a bunch of different products, but I'm thinking right now about Coral, the email the email assistant. Um and uh it has all of the like the the big APIs that it's using it's mostly the Gmail the Gmail API. Um and so you're interacting with the assistant over chat and then it has a list of tools that are like, you know, archive email or draft email or send email or whatever. Uh like there's a whole categorized tools, so it categorizes your mails mail in certain ways. And I think we would definitely try out something like this because it would if it if it ran the same way, um it would make it much more flexible for us to make more tools and not break old ones, you know? Um it's really interesting. \>\> I mean, in a sense, what what I actually predict is that people who are quote-unquote building tools, once we have a a code execution kind of super tool like I'm talking about, is that the only way you really quote-unquote build a tool is with instructions, with prompts. Um and the full power of everything you could possibly do in the API in the Gmail API, for example. Um it's all there in one tool. Um but sometimes you have specific tasks or specific you know, categories of of work that you want to describe in a particular way um to help the LLM perform a sequence of actions as productively as possible. Um and at that point, the only work in engineering that you have to do is is prompt engineering. Um we'll see if it's we'll see if it's that quote-unquote easy. Um as we all know, prompt engineering can be can be really tricky. \>\> It's hard. Yeah. \>\> But um but I think I think that's that's part of the vision. Um, that that being said, you know, we we do have uh some pretty nifty ways with the MCP servers that we generate today to help developers mix and match um all the parts of the different tools um underlying um all the different parts of the API um as they compose and write their own tools. \>\> This is awesome. Um, so for people who are listening uh and want to know more from you and know more from Stainless, uh where should they find you? \>\> Um, stainless.com. Um, our is that's that's our website. \>\> Awesome. Or at least visit stainless.com. Uh Alex, great to have you on. I can't wait to do more of this uh when you have some of these new things launched. This is really really fun and uh yeah, great to great to chat. \>\> Thanks, Dan. You too. \>\> Oh my gosh, folks, you absolutely, positively have to smash that like button and subscribe to AI and I. Why? Because 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 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.