惯性聚合 高效追踪和阅读你感兴趣的博客、新闻、科技资讯
阅读原文 在惯性聚合中打开

推荐订阅源

GbyAI
GbyAI
Martin Fowler
Martin Fowler
I
InfoQ
腾讯CDC
钛媒体:引领未来商业与生活新知
钛媒体:引领未来商业与生活新知
爱范儿
爱范儿
Microsoft Security Blog
Microsoft Security Blog
Google DeepMind News
Google DeepMind News
D
DataBreaches.Net
云风的 BLOG
云风的 BLOG
F
Fortinet All Blogs
N
Netflix TechBlog - Medium
博客园 - 聂微东
Microsoft Azure Blog
Microsoft Azure Blog
D
Docker
博客园 - 三生石上(FineUI控件)
Y
Y Combinator Blog
博客园 - Franky
Engineering at Meta
Engineering at Meta
B
Blog
罗磊的独立博客
Apple Machine Learning Research
Apple Machine Learning Research
Jina AI
Jina AI
V
Visual Studio Blog

Vercel News

Vercel Open Source Program: Winter 2026 cohort How Notion Workers run untrusted code at scale with Vercel Sandbox How we run Vercel's CDN in front of Discourse From idea to secure checkout in minutes with Stripe Building Slack agents can be easy Scaling redirects to infinity on Vercel Advancing Python typing Gamma builds design-first agents with Vercel How Avalara turns pipe dreams into patent-pending with v0 Keeping community human while scaling with agents How OpenEvidence built a healthcare AI that physicians actually trust Security boundaries in agentic architectures Skills Night: 69,000+ ways agents are getting smarter Video Generation with AI Gateway We Ralph Wiggumed WebStreams to make them 10x faster How Stably ships AI testing agents in hours, not weeks How we built AEO tracking for coding agents Anyone can build agents, but it takes a platform to run them Introducing Geist Pixel The Vercel AI Accelerator is back with $6m in credits Making agent-friendly pages with content negotiation The Vercel OSS Bug Bounty program is now available Introducing the new v0 Run untrusted code with Vercel Sandbox, now generally available How Stripe built a game-changing app in a single flight with v0 How Sensay went from zero to product in six weeks AGENTS.md outperforms skills in our agent evals Agent skills explained: An FAQ Testing if "bash is all you need" AWS databases are now live on the Vercel Marketplace and v0
How Chatbase scaled rapidly with Vercel's developer exper...
Alli Pope · 2024-10-09 · via Vercel News

2 min read

With over 500K visitors per month, Chatbase relies on the AI SDK, caching, and streamlined workflows to stay ahead in the competitive AI market.

Chatbase helps companies build chat-based AI agents that are trained on their data to chat with users and perform tasks. It handles customer support, sales, lead generation, and more.

From the beginning, they prioritized building a platform that could move fast in the competitive market. To achieve this, they chose Vercel and Next.js as the tech stack for their app and marketing website, along with Vercel's AI SDK, which enabled them to quickly iterate and deliver AI-driven features.

By prioritizing iteration speed, Chatbase grew to 500K monthly visitors and $4M ARR in 1.5 years. Vercel's developer experience (DX) allows the team to focus on innovation, not infrastructure. The AI SDK enables rapid implementation of custom chats and model optimizations.

Link to headingThe perfect tech stack for building AI apps

  • AI SDK: The AI SDK by Vercel played a critical role in building Chatbase’s AI playground. Each chat instance can be configured with different models and settings, allowing users to experiment with different chatbot configurations. This enabled the launch of their LLM Compare Mode, allowing users to compare various LLMs for their RAG chatbots by adjusting parameters such as the model, temperature, and system messages. Thanks to the AI SDK's ability to quickly swap models, Chatbase users can optimize their chatbot configurations for specific use cases.

  • Rendering flexibility: Chatbase hosts both its marketing website and app in the same repository, leveraging Vercel to manage both efficiently. Static pages are optimized for speed and SEO, while the app uses a combination of server and client-side rendering to ensure personalization without compromising performance. Finally, Next.js’s App Router provides intuitive control over static and dynamic rendering components.

  • Vercel Firewall: Vercel’s security infrastructure, including the Firewall, provides essential protection for Chatbase’s AI applications, helping guard against costly DDoS attacks while maintaining reliability.

  • Skew Protection: Vercel ensures smooth synchronization between server and client code, removing version skew, and improving development workflows. With Skew Protection, Chatbase can ensure no issues are experienced by end users in production.

  • Next.js support: With Vercel’s support for Next.js, Chatbase leveraged built-in caching and streaming capabilities to deliver fast responses to users, both of which are essential for AI-driven applications.

Link to headingCurrent architecture and benefits

Chatbase follows a trunk-based development approach, where pull requests are continuously merged into the main branch, which is directly linked to production. For new features, developers create separate branches and use Preview Deployments for testing and collaboration.

Their current architecture and rendering strategies offer several advantages. Static content loads quickly, while dynamic sections render smoothly, resulting in a significantly improved user experience.

Vercel’s infrastructure also ensures stability, even during traffic spikes—crucial for an AI startup that often experiences sudden attention from feature launches or social media buzz. Features like Instant Rollbacks and the ability to disable auto-assigning production domains make the deployment process more flexible, reliable, and stress-free for the development team.

Overall, Vercel has been instrumental in helping Chatbase move quickly, innovate, and scale effectively, enabling them in maintaining rapid growth.

Unlock rapid AI development

Build AI-powered applications with the AI SDK.

Get started with the AI SDK