AI BriefingVercel Blog news
The latest AI and developer news from Vercel Blog, with short summaries.
Visit website →Dashboard project cards now support customizable metric widgets
Users can select from firewall, observability, speed, and analytics widgets to display on individual project cards, with choices saved per project.
Vercel Agent adds pre-paging alert validation for Critical incidents
Vercel Agent can now validate alerts from monitors, sending only those classified as Critical to specific webhook destinations when enabled.
Vercel adds custom monitors to Observability for AI Gateway and performance alerts
Available on Pro and Enterprise plans with Observability Plus, the feature costs $0.0035 per GB of data scanned and supports alerts via email, Slack, and webhooks.
OpenAI GPT-6.1 Terra Available on AI Gateway with 1M+ Token Context
The model supports configurable reasoning, structured outputs, and tool calling, with a fast mode option for latency-sensitive work.
Vercel Connect CLI adds discover command for 1000+ services
The new vercel connect discover command allows users to search and filter over 1000 services by name, keyword, or connection method.
Vercel Sandbox adds stdin support for running commands
Developers can now send input to running commands via the TypeScript or Python SDKs to interact with stdio MCP servers like agent-browser.
Scale AI AgentEnv Evals Now Run on Vercel Sandbox
The Vercel provider runs agents and task environments in separate Sandboxes, allowing users to inspect task scores and recorded actions.
Vercel speeds up pnpm installs by reusing dependency verification
The optimization reuses successful dependency verification across deployments, allowing installs to complete in milliseconds when dependencies are unchanged.
Vercel CLI Adds Spend Management Commands for Budget Control
The new vercel budgets command allows users to view current spend, set budgets, and pause deployments when limits are reached.
Moonshot AI's Kimi K3.1 Pro and Highspeed now available on AI Gateway
The new models improve coding, 3D modeling, and financial analysis while maintaining a 1M-token context window and image input capabilities.
Vercel deployment summaries now display build cache size and limit proximity
The feature is available by default on all plans for deployments built on or after October 21, with data also accessible via CLI version 65.1.0 and the REST API.
Vercel MCP adds submit_feedback tool for agent-based bug reports and feature requests
The new tool requires sign-in and only transmits feedback when explicitly requested by the user, allowing agents to attach structured context about tasks and errors.
Vercel CLI adds vercel feedback command for terminal-based bug and feature reporting
The new command allows users and coding agents to send structured context to the Vercel team using key-value pairs.
Interfaze Serves 50 Million Monthly Requests on Vercel Using Fluid Compute and AI Gateway
The platform uses Vercel Fluid compute for scalable backend processing and AI Gateway to route traffic across multiple model providers to ensure reliability.
Vercel Connect adds managed Stripe API keys for per-agent access control
The new Managed API Key option lets Vercel generate and store scoped credentials, eliminating the need to paste secrets and allowing rotation without redeployment.
Vercel Agent uses scoped plans to limit production access
The system requires users to approve a specific plan and its requested scopes before the agent gains write access to production resources.
Vercel CLI Enables Account-Free App Deployments with One-Hour Expiry
Temporary deployments use the tmp.now domain and require claiming within one hour to keep the project live.
Vercel to delist Marketplace vendors lacking OIDC support by January 2027
A survey of over 1,000 SaaS vendors found only 8.4% support secure authentication, prompting Vercel to enforce OIDC standards to replace static credentials.
Vercel adds eight new TLDs to free domain offer for Pro teams
The eligible TLD count for the one-year free domain offer has increased to sixteen, including .co, .studio, .company, .info, .pro, .live, .digital, and .agency.
Baseten's Mammoth-1 and Elephant-1 available free on AI Gateway through October 27
Mammoth-1 (27B) and Elephant-1 (9B) offer 16k-token context and return choices, probabilities, and scores for text classification and routing.