# Hypermode Launch: Kevin Van Gundy AI Engineer · 2024-08-23 Kevin Van Gundy, founder of Hypermode, argues that iteration velocity is the compound interest of software and key to succeeding with AI, and presents Hypermode as a runtime that makes AI approachable by integrating models and data into AI functions with minimal friction. Drawing from his experience at Vercel, he explains how rapid iteration helped them win against competitors, and applies the same philosophy to AI development. Hypermode removes common pain points: it offers one-request RAG with in-memory embedding and search, model comparison and fine-tuning export, and strong defaults that work with existing stacks. The platform de-risks getting it wrong by making model switching and prompt changes frictionless. Kevin invites listeners to a workshop to build a demo and offers $1000 in Hypermode credits to get started. ## Questions this episode answers ### What is Hypermode and how does it help developers integrate AI into their apps? Hypermode is a runtime that enables developers to easily integrate models and data into AI functions, as described by Kevin Van Gundy. It provides tools for rapid iteration and observation in production, aiming to make AI approachable without specialized skills. Features include in-code type-ahead for models, strong defaults, and the ability to bring your own stack, all designed to reduce complexity and de-risk AI adoption. [2:29](https://aie.addtry.com/c3b2bfc4-9594-45f1-a62c-a5adad6cfd54?t=149000) ### How does Hypermode reduce the number of requests for retrieval-augmented generation? Kevin Van Gundy explained that Hypermode optimizes RAG with an in-memory embedding and search service. Instead of the typical N+1 requests—one to embed the input and another to query the vector store—Hypermode handles it all in a single request, saving a couple hundred milliseconds per request and reducing overall latency for AI-powered features. [3:26](https://aie.addtry.com/c3b2bfc4-9594-45f1-a62c-a5adad6cfd54?t=206000) ### What incentive is Hypermode offering to workshop attendees at the AI Engineer World's Fair? Kevin Van Gundy announced that Hypermode is offering $1,000 in credits to attendees who visit their workshop after lunch. Attendees will learn to build natural language search, sort data lists, detect outliers, and more, leaving with a demo and a plan to put something similar into production by the end of next month. [4:20](https://aie.addtry.com/c3b2bfc4-9594-45f1-a62c-a5adad6cfd54?t=260000) ## Key moments - **[0:00] Iteration** - [0:14] Vercel initially lost to JavaScript frameworks, hosting providers, and pepperoni pizza diet, says Kevin Van Gundy. - [0:58] "Iteration is the compound interest of software." - **[1:22] De-risking** - [1:54] "Picking the wrong model doesn't matter if there's no friction to switching it out." - **[2:12] Hypermode** - **[2:56] Developer Experience** - [3:12] Hypermode's in-memory embedding and search service enables single-request RAG, saving hundreds of milliseconds per request. - **[3:49] Model Comparison** - **[4:06] Workshop** - [4:06] Kevin Van Gundy invites attendees to a workshop to build natural language search and earn $1,000 in Hypermode credits. ## Speakers - **Kevin Van Gundy** (guest) ## Topics AI Infrastructure, Developer Productivity, RAG & Retrieval ## Mentioned Hypermode (company), Vercel (company) ## Transcript ### Iteration **Kevin Van Gundy** [0:14] Before Hypermode, I worked at Vercel. We had an office down the street above a pizzeria, and we had three big problems. One, we were losing to other JavaScript frameworks. Two, we were losing badly to other hosting providers. And three, I was losing to my diet of exclusively pepperoni pizza. Eventually we started to win, not because we were smart or we knew all theright answers, but because we dealt this core competency of iterating really, really, really quickly. We didn't know the optimum strategy, but we figured if we just tried more things faster than everyone else, we'd eventually be able to adapt and figure out theright products and strategies to figure out what the market wanted. Iteration is the compound interest of software. Keep doing it long enough and eventually really good stuff starts to happen. Because we tried a lot of things really quickly, we eventually figured out two things. One, developers want to incrementally adopt new technologies. And two, they don't want to commit to architectural patterns before they know how their application is actually going to work. But iteration can't happen if you're afraid of getting it wrong. The same thing that has held back web is also holding back AI. And if I'm honest, there are even more things for us to get wrong about Gen AI. ### De-risking **Kevin Van Gundy** [1:35] When I think about it, I'm grossly overwhelmed. What's theright hardware? What's theright model? What's theright prompt? How do I integrate? How do I monitor? How do I improve? Everyone here knows a horror story of someone with a runaway bill, a hallucinating chatbot, a project that took months and months and never delivered any value. And in the end, we need to build systems that de-risk getting it wrong. Because we are going to get it wrong a lot. Picking the wrong model doesn't matter if there's no friction to switching it out. Integration is simple when your classical systems and your AI systems use the same APIs. You can fearlessly make changes to prompts, strategies, data mixes if you can trace that inference step by step by step. At Hypermode, we care deeply about making AI approachable. Everyone here should be able to put AI in their apps without specialized skills. ### Hypermode **Kevin Van Gundy** [2:29] At its core, Hypermode is a runtime. It allows you to easily integrate models and data into AI functions. We then surround that runtime with a bunch of tools that make it easy for you to rapidly iterate and observe those AI functions in prod. We make it easy to get started, incrementally adopt AI as appropriate, and then as your team develops those skills, reimagine those applications as AI native. ### Developer Experience **Kevin Van Gundy** [2:56] First and foremost, we want to make the developer experience of developing with AI a lot less terrible. When it comes to adding a new model to your service, you probably don't want to read a bunch of pages of docs to figure out the temperature is on a 0 to 2 rather than a 0 to 1 or a 1 to 10. With Hypermode, we provide you type ahead and your favorite code editorright out of the box. No SDKs, nothing to download. Then when you do ship to prod, we give you strong defaults just to get started. Or if you have your own stack, bring it along. In either case, we'll remove a lot of that complexity for you. For example, traditional RAG requires N+1 requests. You need to make an additional call to embed the inputs, go talk to your vector store. With Hypermode, you can do that all in one request. We've built an in-memory embedding and search service that allow you to do that and save a couple hundred milliseconds per request. Finally, building intuition around nondeterministic systems is hard. Each model has its own personality, and we make it really easy for you to quickly compare different inferences, different tunes, different models. And you can then export this data set to fine-tune. ### Model Comparison **Kevin Van Gundy** [4:06] On Monday, your boss is going to ask you, "What did you learn at AI World Fair?" If you come by our workshop after lunch, I'll prove to you that you can make AI sorry. I'll prove to you that you can make iteration velocity a core competency. ### Workshop **Kevin Van Gundy** [4:20] The team that built all this amazing stuff will be there. We'll show you how to build natural language search, intelligently sort every data list in your product, detect outliers, catch bad guys. You'll walk over the demo that you're proud of and a plan to put something like it in prod by the end of next month. And if seeing my happy face again and building something really cool is not enough, we'll give you $1,000 in Hypermode credits to get started. Thank you all so much. --- This library is powered by PodHood (https://podhood.com), the podcast website platform.