AI Briefing#vercel
The latest AI and developer news about #vercel, with the original source and a short summary.
The latest AI and developer news about #vercel, with the original source and a short summary.
Vercel Drives is now generally available for Vercel Sandbox, allowing agents to persist files across different execution environments with default capacities of 1 TiB.
Vercel's new enterprise governance tools include generally available BYOC on AWS and a public beta for Enterprise-Managed Authorization via Vercel Connect.
The release includes automatic framework detection for FastAPI, Flask, Django, and FastHTML, along with Python SDKs for storage, queues, and AI models.
Developers can provision S3 storage directly within Vercel, integrating with existing AWS database services on a single bill.
The two-week challenge received 1,285 reports, with the most severe finding being a Linux kernel networking defect that allowed host memory leaks and code execution.
The integration uses short-lived OIDC credentials and offers $100 USD in AWS credits for new accounts created through Vercel.
The open-weight reasoning model features 30B parameters with 3B active per token and a 1M token context window.
Average file preparation time drops by 20% on build machines with more than two vCPUs, with LFS projects seeing a 54% reduction.
The model features a 1M token context window and supports text, image, PDF, and video inputs.
The framework allows developers to define agent instructions in Markdown and tools in TypeScript, deploying directly to Vercel in under 60 seconds.
The purchase decision remains with the user, as non-interactive commands return errors requiring explicit confirmation.
Deployments older than 30 days will be automatically deleted starting October 23 unless teams opt out.
A two-person frontend team closed over 800 Linear tickets in four months using AI agents deployed on Vercel.
The new configuration option reduces Fast Origin Transfer usage and improves time to first byte by preventing request bodies from being sent to Routing Middleware.
Snapshot restoration time now counts toward creation, adding about 50 ms to p50 latency but eliminating wait times for the first operation.
StepFun's flagship model supports text and image input with a 1M-token context window for agentic coding and analysis.
The model introduces effort levels and adaptive thinking, supporting low to max settings to control token usage and reasoning depth.
The model is free for Pro and Enterprise teams with purchased AI Gateway credits but lacks Zero Data Retention support.
Developers can now configure timestamp attributes for entities to enable time-based targeting rules such as 'is after' or 'is before'.
The new SDK allows Python developers to use Jev, a universal classifier model, via the experimental evaluate() function.
The team now pushes more than 73,000 deployments a month using six production AI agents.
The integration includes MAI-Voice-2.1, MAI-Voice-2.1-Flash, and MAI-Transcribe-2 Streaming with no platform fee or markup on inference.
Vercel Agent now supports installing private dependencies from npm and custom registries using credentials stored as shared environment variables.
The tools are available in AI SDK 7.0.116 and later, allowing models to access current web information via a single API key.