November 2025 Summaries

Vercel's recent release of their first mobile app, v0 for iOS, marks a significant step as the company ventures into native app development. The app, which aims to provide a seamless and intuitive chat experience, was built using React Native with Expo after extensive experimentation with various tech stacks. Emphasizing a design worthy of an Apple Design Award, the development process involved the creation of numerous iterations and the adoption of UI patterns that align with Apple's native apps. The app's chat feature is the centerpiece, designed to integrate AI seamlessly and provide a responsive user experience. Key challenges addressed during development included smooth message animations, dynamic height adjustments, keyboard handling, and content scrolling. To achieve this, Vercel utilized a variety of open-source libraries, custom hooks, and native code patches, while focusing on performance and a native look and feel. The company also developed a shared API to ensure efficient communication between the mobile app and their existing web platform, highlighting their commitment to creating a unified user experience.

Vercel has launched a redesigned Firewall experience to enhance user interface and usability, aiming to make security more intuitive and less obstructive while maintaining application resilience against attacks. The redesign was informed by user feedback, highlighting the need for improved visibility and faster investigation of traffic alerts and DDoS events. The new UI offers a unified overview page that provides a high-level view of security events, with clear navigation to sections like Traffic, Rules, and Audit Log. It features detailed tables and feeds to monitor and manage Firewall activity, including alerts, rules, and traffic patterns, helping teams quickly identify and respond to potential threats. The updates ensure that security professionals, developers, and SREs can efficiently configure rules, monitor unusual activity, and resolve issues without compromising on shipping velocity.

Workflow Builder is an open-source Next.js template designed to facilitate the creation of workflow automation platforms through its comprehensive visual automation capabilities powered by the Workflow Development Kit (WDK). It features a visual editor that allows users to construct and execute workflows using drag-and-drop steps, supported by real-time validation, undo/redo, auto-save, and persistent state functionality without requiring code. With AI-powered text-to-workflow generation, users can input natural language prompts to generate structured workflows, while webhook triggers enable real-time integration with external apps and APIs. The platform offers six prebuilt integration modules, including Resend for emails and Slack for notifications, and converts visual workflows into executable TypeScript. Deployable to Vercel, Workflow Builder is suitable for a variety of use cases, such as building internal tools, customer-facing products, and integration platforms, effectively allowing users to design complex, data-driven processes with ease.

Vercel has revamped its Firewall user interface to enhance security tools' usability, ensuring they are intuitive and do not impede workflow efficiency. The redesign, informed by user feedback, aims to make the Firewall more accessible and effective for developers, SREs, and security teams by providing clear, actionable information and simplifying navigation to resolve issues promptly. The new interface combines visibility, context, and control, featuring a high-signal overview page, streamlined sidebar navigation, and improved inspection tools to quickly transition from alerts to insights. Key updates include comprehensive traffic intelligence with dedicated feeds for various data points and a focused view for managing Firewall rules and activity. This redesign emphasizes that security should be seamlessly integrated into the user experience, allowing teams to act quickly and maintain high shipping velocity without compromising on security.

In November 2025, Vercel announced the fall cohort of its Open Source Program, continuing its initiative to support open-source project maintainers with resources and guidance. The cohort includes a diverse range of projects, from AI-native applications to developer infrastructure tools, highlighting innovative contributions to the tech community. Notable projects include Claude Code Templates, an extensive library of production-ready code components; Ora, a Swift-built macOS browser; Databuddy, a community-driven analytics tool; and OSSTag, a transparent alternative to Google Tag Manager. Other projects focus on areas such as music production, AI chat applications, UI design, and monitoring dashboards, each showcasing significant growth and community engagement. The program emphasizes Vercel's commitment to fostering open-source development and invites new applications for its upcoming cohorts.

Vercel is pioneering the development of self-driving infrastructure that aims to transform how application code is managed and optimized, reducing the operational burden on developers and operations teams. By leveraging framework-defined infrastructure, Vercel automates the provisioning and management of cloud resources based on application code, allowing developers to focus on innovation rather than maintenance. The introduction of Vercel AI Cloud and the Vercel Agent marks a significant step towards autonomous cloud operations, with AI-driven capabilities for monitoring, analyzing, and optimizing deployments to enhance stability, security, and performance. This approach creates a feedback loop where production insights inform code improvements, leading to continuous advancement in reliability and efficiency. As the platform evolves, it aims to allow infrastructure to autonomously handle operational challenges and adapt to real-world demands, enabling teams to concentrate on high-value tasks and product development.

The Gemini 3 Pro Preview model, released by Google and available through the Vercel AI Gateway, demonstrates significant advancements in coding, multimodal reasoning, and tool use. It has shown improvements in instruction following and response consistency, achieving a 42% success rate in Vercel's Next.js evaluations, tying with OpenAI's GPT-5 Codex and outperforming several other models in reasoning quality. This model excels in frontend generation and multi-turn agent flows, providing stable, well-structured UI components, and benefits from a 1 million token context window for maintaining fidelity in long generation chains. It is available for testing on AI Gateway and supports integration with Google AI Studio and Google Vertex AI, making it an attractive option for developers looking to build high-performance applications with advanced AI capabilities.

Vendor lock-in is a significant concern when choosing a cloud platform, as many platforms use proprietary primitives and APIs that tie applications to their ecosystem, making migration difficult. Vercel, however, adopts a framework-defined infrastructure approach, allowing developers to write code based on their chosen framework rather than platform-specific requirements. This method ensures code portability across different infrastructures and reduces dependency on Vercel's ecosystem. By supporting frameworks like Next.js, Remix, and SvelteKit, Vercel automates the provisioning of infrastructure without requiring specific Vercel modules or APIs, allowing applications to run seamlessly across various environments. The company prioritizes open standards and protocols, ensuring that services like databases and AI gateways remain compatible with industry standards, thereby facilitating ease of migration and interoperability. This approach not only promotes a healthier web ecosystem but also enhances trust and broader adoption, as developers are assured that investing in a Vercel-supported framework won't lock them into a single platform.

Nous Research, an AI lab, temporarily made its open-source language model, Hermes, free to enhance accessibility, but the initiative was exploited by automated scripts that overwhelmed the service with fake accounts to bypass rate limits, leading to wasted resources and inflated costs. Despite having initial bot protection measures like Cloudflare Turnstile, these were insufficient to prevent abuse during the promotional period. In response, Nous implemented Vercel BotID Deep Analysis for enhanced bot detection and prevention, which operates invisibly and verifies users without disrupting their experience. This new system enabled Nous to effectively block a coordinated attack that increased traffic by 3,000% without affecting legitimate users or service availability, allowing them to continue offering the free tier safely. The improved bot protection not only safeguarded their infrastructure but also maintained cost efficiency and app performance, highlighting the importance of robust security measures for open-access platforms.

AI Gateway is a Node.js service designed to connect to various AI models through a single interface, effectively processing billions of tokens daily by leveraging Fluid compute for cost-efficient scaling. Fluid compute enhances concurrency and resource efficiency by allowing multiple simultaneous operations within a single instance, reducing the need for separate serverless instances for each invocation. AI Gateway operates within the Vercel infrastructure using a global delivery network that optimizes request routing through Anycast routing and Points of Presence (PoPs), ensuring low-latency and high-throughput communication with AI providers. By employing Active CPU Pricing, AI Gateway significantly cuts costs by only charging CPU rates when actively processing, while the rest of the time incurs lower memory-only charges. Vercel provides native observability and detailed metrics for developers to monitor performance, provider health, and costs in real-time, ensuring reliable and resilient operation across fluctuating model APIs. This setup allows developers to rapidly deploy AI features without the complexities of managing provider connections or underlying compute.

Agents are increasingly being utilized by enterprises to boost productivity and improve outcomes, with applications in customer support, code reviews, and sales operations. The challenge lies in identifying suitable problems for AI solutions that provide value at a reasonable cost. Vercel has developed a methodology for selecting AI projects with the highest potential impact by focusing on tasks that require low cognitive load and high repetition, ideal for current AI capabilities. Two examples include a lead processing agent that automates research and qualification, significantly reducing manpower requirements, and an anti-abuse agent that cuts ticket processing time by 59% by automating the initial analysis of abuse reports. Vercel encourages organizations to explore AI applications by asking employees about repetitive tasks they dislike, offering templates for various agent applications, and providing hands-on support for discovering and implementing high-ROI AI projects.

An integration between v0 and Snowflake has been announced, allowing users to connect v0 to Snowflake for building data-driven Next.js applications directly on the Snowflake platform. Vercel's secure vibe coding architecture manages application and authentication, ensuring the data remains within Snowflake's secure environment. Users can interact with their data via chat, using natural language to query databases and understand table structures, and can build applications that incorporate semantic context, such as dashboards or custom tools, which deploy directly to Snowflake. The integration enables non-developers to create AI applications without waiting for engineering resources, with use cases including sales dashboards, inventory monitoring, and customer analytics. Vercel's architecture ensures that applications adhere to Snowflake's existing security and access policies, thereby eliminating the need for additional security configurations or infrastructure. Access is currently being offered via a waitlist, with notifications for testing readiness.