# SERHANT.'s playbook for rapid AI iteration

DevFeed: [SERHANT.'s playbook for rapid AI iteration](<https://devfeed.tech/articles/serhant-s-playbook-for-rapid-ai-iteration-773.md>)

Original publisher: [Read original article](<https://vercel.com/blog/serhants-playbook-for-rapid-ai-iteration>)

Author: Eric Dodds

Published: 2026-03-23T04:00:00Z

Content type: article

Language: en

Sources: [Vercel News](<https://devfeed.tech/sources/vercel-news.md>)

Topics: [vercel ai sdk](<https://devfeed.tech/topics/vercel-ai-sdk.md>), [SDKs](<https://devfeed.tech/topics/sdks.md>), [Next.js](<https://devfeed.tech/topics/next-js.md>), [web applications](<https://devfeed.tech/topics/web-applications.md>)

Tags: [agentic](<https://devfeed.tech/tags/agentic.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [api](<https://devfeed.tech/tags/api.md>), [backend](<https://devfeed.tech/tags/backend.md>), [claude](<https://devfeed.tech/tags/claude.md>), [cost](<https://devfeed.tech/tags/cost.md>), [developers](<https://devfeed.tech/tags/developers.md>), [engineering](<https://devfeed.tech/tags/engineering.md>), [gemini](<https://devfeed.tech/tags/gemini.md>), [infrastructure](<https://devfeed.tech/tags/infrastructure.md>), [models](<https://devfeed.tech/tags/models.md>), [next-js](<https://devfeed.tech/tags/next-js.md>), [openai](<https://devfeed.tech/tags/openai.md>), [production](<https://devfeed.tech/tags/production.md>), [react-native](<https://devfeed.tech/tags/react-native.md>), [scale](<https://devfeed.tech/tags/scale.md>), [tools](<https://devfeed.tech/tags/tools.md>), [vercel](<https://devfeed.tech/tags/vercel.md>)

## AI overview

SERHANT.'s S.MPLE team uses Vercel AI SDK to abstract model providers, enabling faster iteration and model changes without tightly coupling the product to one provider.

## Source excerpt

Impact at a glance Started with Next.js on Vercel, which made it easier to expand to a React Native iOS app without rebuilding their backend Engineers focus on AI design and iteration instead of platform plumbing Orchestrates OpenAI, Claude, and Gemini by task to optimize cost vs output Scaled from an internal pilot to 800-900+ real estate agents without replatforming When Jeremy Bunting joined SERHANT. as VP of Engineering in February 2024, S.MPLE was already showing promise. 200 real estate agents were piloting the AI product, which was designed to save time by automating cumbersome and repetitive daily tasks, like market analysis and contact management. S.MPLE was a Next.js progressive web app deployed on Vercel, and that foundation gave the team leverage. They could keep the API layer steady while expanding the client experience, including expansion to a React Native iOS app, all without a backend rebuild. But Bunting had a problem that keeps many engineering leaders up at night: the AI landscape changes faster than most teams can implement infrastructure updates. The team needed to move fast, scale confidently, and stay flexible enough to swap models, add new capabilities, and adapt to the rapidly changing AI landscape. Traditional approaches meant choosing between velocity and flexibility, but Bunting wanted both. AI SDK: Moving fast without vendor lock-in As S.MPLE shifted from "one model" experiments to a production AI product, Bunting's team started evaluating Vercel's AI SDK, and he initially had concerns. "I asked, how much is this going to tie us in directly to Vercel?" he recalls. Then one of his engineers pushed back. The AI SDK wasn't infrastructure lock-in, it was infrastructure independence. "It's just an SDK that abstracts away the complexity of working with different model providers", the engineer pointed out. Bunting also realized that if the team picked one frontier model and built tightly around it, every future change would come with a rewrite