Search: “tools”

The Chat SDK now enables developers to schedule Slack messages for future delivery. This functionality utilizes `thread.schedule()` by passing both the desired message content and a specific `postA...

Vercel's Workflow SDK now supports custom class serialization, enabling developers to pass their own class instances between workflow and step functions. Previously, the SDK only handled standard J...

Vercel's Custom Reporting API for AI Gateway is now available in beta for Pro and Enterprise plan users, providing programmatic access to cost, token usage, and request volume across all AI Gateway...

Vercel has launched Elastic build machines in beta for all paid plans, giving teams control over build performance without project-level micromanagement. Elastic build machines auto-scale based on...

Vercel Workflow now automatically encrypts all user data end-to-end with no code changes required — workflow inputs, step arguments, return values, hook payloads, and stream data are automatically...

GLM 5.1 from Z.ai is now available on Vercel's AI Gateway with no markup and no separate provider account required. Designed for long-horizon autonomous tasks, it handles planning, execution, testi...

GLM-5V-Turbo is a multimodal vision model from Z.ai, now available through Vercel AI Gateway, that specializes in design-to-code workflows and generating UI components. It can be accessed via Verce...

Waldium is a YC-backed, two-person agentic CMS that automates content research and creation, and gives every customer blog its own Model Context Protocol (MCP) server endpoint so AI agents can quer...

Inception has launched Mercury 2, a model providing reasoning-grade quality with low, real-time latency, making it suitable for complex applications like agentic loops, coding assistants, and RAG p...

On April 10, 2026, Simon Willison posted a short note sharing a podcast clip from his ~1 hour 40 minute conversation with Lenny Rachitsky, highlighting a segment about kākāpō parrots. The kākāpō (*...

Vercel Microfrontends now simplifies setup and management through two key additions: an AI coding skill and new CLI commands. The dedicated Microfrontends AI skill allows developers to use natural ...

Vercel's 2026 AI Accelerator cohort is a six-week program selecting 40 early-stage AI startups, giving teams access to Vercel infrastructure, $8M+ in partner credits from AWS, Anthropic, OpenAI, C...

MiniMax M2.7 is now available on Vercel AI Gateway in two variants: standard and high-speed, accessible without requiring separate provider accounts. It represents a significant improvement over pr...

Agentic workflows are already used for initiating action. To be successful, agents typically need to combine multiple steps and execute business logic reflective of real-life decisions. But, as develo

The Vercel GitHub App now requests two additional repository permissions: **Actions (read)** and **Workflows (read & write)**. These permissions enable Vercel Agent to read workflow run logs to hel...

Vercel Sandbox snapshots capture the complete filesystem state of a running sandbox — including installed packages and configured environments — allowing new sandboxes to be launched from that save...

Vercel AI Gateway now supports Fast Mode for Claude Opus 4.6, an early experimental feature that delivers 2.5x faster output token speeds while maintaining the same model intelligence. It is partic...

Vercel now allows users to query and manage Marketplace databases directly from the dashboard, with access to a Browser section on each database page for hands-on data management. Users can view t...

Vercel's Observability Plus query builder now supports custom queries on Vercel Workflow runs and steps, enabling teams to visualize traffic, performance, and other key metrics across their workflo...

Vercel Sandbox SDK version 1.9.0 introduces native file permission control within the `writeFiles` API, allowing developers to set Unix-style permissions by passing a `mode` property in a single op...

SERHANT., an AI-native real estate brokerage, built its internal AI platform S.MPLE on Next.js and Vercel, scaling it from a 200-agent pilot to over 900 agents without replatforming or rebuilding i...

CVE-2026-23869 is a high-severity Denial of Service vulnerability affecting React Server Components. It can lead to Denial of Service and is present in Next.js 13.x, 14.x, 15.x, and 16.x, impactin...

The AI Gateway now provides robust, centralized controls for data governance, enabling team-wide and request-level enforcement of Zero Data Retention (ZDR) and prompt training opt-outs. By integrat...

Vercel now supports transferring Marketplace resources (such as databases) between teams directly from the dashboard, eliminating the need to use the API. Team owners and members can initiate trans...

Vercel's AI Gateway now supports xAI's Grok 4.20 model family, including variants for multi-agent, reasoning (beta), and non-reasoning use cases, accessible without requiring a separate provider ac...

Leonardo.AI and Relevance AI — two Australian AI-native startups — operate at global scale (processing millions of images daily and running autonomous agents across time zones, respectively) withou...

Vercel's Custom Reporting API for AI Gateway, now in beta for Pro and Enterprise plans, provides programmatic access to cost, token usage, and request volume across all AI Gateway traffic — includi...

The Vercel CLI allows users to interact with and manage the Vercel Sandbox functionality directly via the `vercel sandbox` command. This integration eliminates the need for users to install a separ...

Vercel's CDN now automatically respects caching headers from external origins by default for new projects. Previously, responses served through rewrites to external origins were uncached by defaul...

Commands like `vc project ls` and `vc domains ls` now automatically use the scope of the linked local directory instead of defaulting to the global team. Previously, running these commands inside a...

The Vercel plugin now supports OpenAI Codex and Codex CLI, expanding on its initial launch with Claude Code and Cursor. With the plugin, teams can access over 39 platform skills, three specialist ...

Vercel Sandbox now supports creating sandboxes with up to 32 vCPUs and 64 GB of RAM for Enterprise customers, enabling large, resource-intensive applications that are CPU-bound or require significa...

As of March 26, 2026, Vercel Sandboxes created with the latest beta package support unique, customizable names within a project, replacing the previous ID-based identification system. Named sandbox...

Vercel now displays specific error codes directly in the request details panel of the Runtime Logs page, alongside the standard HTTP status response code. This enhancement makes it easier to diagno...

Vercel now supports Django with zero configuration, enabling developers to instantly deploy Django full-stack applications or APIs without any manual setup. Vercel automatically detects Django's `m...

Vercel now supports Go backend applications with zero configuration, allowing developers to deploy Go APIs and Go Gin API applications without any configuration required. Go files placed inside ...

This AI Gateway enforces zero data retention policies, ensuring sensitive information is not stored after processing and preventing third-party AI providers from using your data for training. The p...

Ray Day Seattle (April 9, 2026) was an Anyscale event where ML engineers from Notion, Uber, Salesforce, and Apple shared real-world experiences scaling AI infrastructure with Ray. Notion highlight...

The Sentence Transformers v5.4 update introduces first-class multimodal support, enabling the same familiar API to encode and compare texts, images, audio, and videos using both `SentenceTransforme...

Waypoint-1.5 is Overworld's updated real-time generative world model, trained on nearly 100x more data than its predecessor to deliver improved visual fidelity and environmental coherence. It intro...

ALTK-Evolve, published by IBM Research, is a memory system for AI agents that enables on-the-job learning by helping agents improve over time, learning from and using guidelines generated from pre...

Physical Intelligence (Pi) is building a general-purpose robotic intelligence system whose core Visual-Language-Action (VLA) model takes visual observations, natural-language instructions, and the...

Safetensors, a secure tensor serialization format originally developed by Hugging Face, has joined the PyTorch Foundation as a foundation-hosted project under the Linux Foundation, alongside DeepSp...

At Google Cloud, we help organizations of all sizes build and operationalize complex agentic workflows with total confidence. By combining world-class AI research with an open, fully integrated AI pla

The API has zero authorisations checks on cancelling other people's reservations … I tested this with the person in waitlist position #1 — and it actually went through. So you've moved from #4 to #3 a

The intersection of medicine and AI has led to remarkable innovations. However, developers now face the thorny challenge of building robust medical AI tools that have been tested and evaluated on dive