Vercel

Every agent needs streaming, models, durability, isolation, channels, and integrations. The Agent Stack has them all: ▪︎ AI SDK ▪︎ AI Gateway ▪︎ Workflow SDK ▪︎ Sandbox ▪︎ Chat SDK ▪︎ Vercel Connect 𝚎𝚟𝚎 implements them with one command ↓https://lnkd.in/gaumKRec

We're closing out SHIP LDN with Guillermo Rauch and Harry Stebbings for an exclusive fireside chat on building, backing, and what's next. Sign up for your spot on the waitlist today: https://lnkd.in/ebYsr9dw See you there! 🇬🇧 

Deepseek has entered the chat. Read the latest production index summary from Vercel's AI Gateway ↓

We're at AWS Summit New York - come say hello at Booth 708 come chat with us about how v0 and Vercel give engineering and ops teams an AWS-native path to build, iterate, and bring internal tools and AI-powered applications into production faster and at scale. Learn more and get in touch with the team attending: https://lnkd.in/gwTGYNM7

Stop rewriting code just to test a new model. AI Gateway gives you a single endpoint for routing, failover, and observability across hundreds of providers including OpenAI, Anthropic, and Google. Join Vercel DX Engineer Nico Albanese to learn how to build AI systems that can use any model without changing application code. https://lnkd.in/gprEKpKe

The 2026 AI Engineering Survey is live. We partnered with Notion and Amplify to ask builders what's actually happening in their workflows: how AI is changing feature velocity, what teams are building vs. buying, and where compute is headed next. Results will be published and presented at AI Engineer World's Fair. Share your take (and enter the raffle) → https://ntn.so/ai-survey

Vercel removed 80% of their agent’s tools to make it more accurate. Join Abhi Sivasailam, VP of Data at Vercel, to learn how simplifying agent architecture created a more adaptive and operationally reliable internal AI agent. https://lnkd.in/gpnmKhi3

Ask which AI model is best and the answer changes before the ink dries. Vercel's AI Gateway sees tens of trillions of tokens across real production workloads. The picture looks nothing like the benchmarks. • Spend and volume crown different winners. • Agentic requests carry 59% of all token volume, up from 32% six months ago. • Teams at scale average 35 models. Full breakdown in the article. ↓

Vercel Sandbox firewall can now proxy and filter outbound requests. ▪︎ Control all agent traffic from your own proxy ▪︎ More granular credential injection ▪︎ Log and audit outgoing traffic https://lnkd.in/e_A_7sR2

Use tags to easily manage thousands of Vercel Sandboxes. • Tag by environment, team, or customer • Filter to surface exactly what you need • Built for agents and multi-tenant platforms https://lnkd.in/e3uTHuxB