Skip to content
AI NEWS JOURNAL
AI, IN PERSPECTIVE

Search AI news

Search headlines, summaries and articles to connect the dots.

Newest first

Vercel Board is now available

Vercel Board is now accessible across all plans, offering an experimental message board for agents to coordinate tasks and maintain context. It enables unified task discussions, access controls, and bidirectional sync with tools like Slack and GitHub via Vercel Connect. Agents can interact using the Vercel CLI or JavaScript SDK, with setup instructions provided through the Board skill.

Hy4 Flash now available on AI Gateway for 50% off

Tencent's Hy4 Flash model is now available on AI Gateway with a 50% discount on input, cached input, and output tokens until November 29, 2026. It offers the full feature set of the Hy4 family—reasoning with preserved thinking across turns, tool calling, structured outputs, prompt caching, image input, and a 1M-token context window—at approximately one-tenth the cost per token. The model can be used with the identifier 'tencent/hy4-flash' in applications and coding agents via Vercel's CLI setup. AI Gateway provides unified API access, usage tracking, cost management, and performance optimizations without markup or platform fees. Additional resources include reference architectures, agent stacks, web application guides, backend options, and a prompt library.

Introducing eve 1.0

Vercel announces the general availability of eve 1.0, an open-source framework for building production-ready agents. The release includes performance improvements, expanded integrations, enhanced observability via OpenTelemetry, and new features like multi-tenant support, persistent memory, multiplayer sessions, and lower workflow costs. eve enables developers to build agents with customizable workflows, native UI integrations with frameworks like Next.js, and secure, scalable deployments on Vercel. Early adopters report significant gains in development speed, reduced codebases, and lower AI costs.

Agents are users, so your software needs evals

Agents interact with software through a funnel similar to humans: Discovery, Selection, Access, and Success. To measure whether agents complete user tasks correctly, end-to-end (E2E) evaluations are essential. These tests run multiple trials, score outcomes, and help identify failures across steps like searching cafes, checking budgets, and placing orders. Using frameworks like Harbor, teams can define tasks with specific instructions, environments, verifiers, and known-good solutions. Metrics such as success rate, Pass@k, and Pass^k reveal how reliably agents perform, while trace analysis uncovers root causes of failure. The process includes setting a goal based on observability, customer feedback, or roadmap needs; defining measurable metrics; designing task sets covering common and edge cases; running evaluations at scale using tools like Vercel Sandbox and AI Gateway; and analyzing traces to iterate improvements. Automated trace analysis enables scaling, and repeated evaluation supports continuous improvement, regression detection, and product optimization.

WTF are evals? How to test agents and the software they use

Agents interact with software through a funnel similar to humans: Discovery, Selection, Access, and Success. To measure whether agents complete user tasks correctly, end-to-end (E2E) evaluations are essential. These evaluations assess the full sequence of steps an agent takes, ensuring outcomes meet user requirements. Using frameworks like Harbor, developers can design tasks with defined environments, verifiers, and known-good solutions, then run trials across variants to measure success rate, pass@k, pass^k, efficiency, time, and cost. Analyzing traces reveals root causes of failures, enabling targeted improvements. Iterative evaluation helps catch regressions, test changes, and guide product development, turning evaluations into ongoing infrastructure for building better agent-driven products.

AI Gateway adds DeepSeek Search and Fetch tools

DeepSeek Search and DeepSeek Fetch are now accessible through Vercel's AI Gateway, enabling users to find relevant web pages and retrieve their content as Markdown using a single API key. These tools work with any model supporting tool calling, support fallback search options, and are available in AI SDK versions 6.0.321 (v6) and 7.0.160 (v7). Each search or fetch request costs $0.75 per 1,000 billable requests, with no charge for failed or empty results. Usage is tracked via AI Gateway, which also supports routing, retries, and failover configurations.

Introducing Vercel Schedules

Vercel Schedules enables applications and agents to create, modify, or cancel one-time and recurring tasks dynamically through code without redeployment. It supports both static schedules defined in configuration files and dynamic schedules managed via SDK, CLI, or API during runtime. The service integrates with Vercel Queues to trigger tasks at specified times, allowing apps to handle work like data cleanup or AI-driven summaries securely and efficiently. Users can test schedules in preview environments before production, and the feature is now available in Public Beta.