How we made v0 an effective coding agent
Last year we introduced the , and described how the v0 models operate inside a multi-step agentic pipeline. Three parts of that pipeline have had the greatest i...
79 posts from this source
Last year we introduced the , and described how the v0 models operate inside a multi-step agentic pipeline. Three parts of that pipeline have had the greatest i...
We open-sourced , the Bash execution engine used by to reduce our token usage, improve the accuracy of the agent's responses, and improve the agent's overall pe...
Teams can now create, update and delete Secure Compute networks directly from the Vercel dashboard, the API, and Terraform. Secure Compute networks provide priv...
now applies your repository’s coding guidelines during code reviews.Vercel Agent Add an file to your repository, or use existing formats like , , or .AGENTS.mdC...
At our recent Next.js Conf and Ship AI events, we introduced an activation that blended technical experimentation with playful nostalgia. The idea started long...
For any request involving a Vercel Function invocation, you can now view the function start type in the right hand details panel of Runtime Logs. A Function inv...
You can now access Z.ai's latest model, GLM-4.7, with Vercel's and no other provider accounts required.AI Gateway GLM-4.7 comes with major improvements in codin...
You can now access MiniMax's latest model, M2.1, with Vercel's and no other provider accounts required.AI Gateway MiniMax M2.1 is faster than its predecessor M2...
At our recent Next.js Conf and Ship AI events, we introduced an activation that blended technical experimentation with playful nostalgia. The idea started long...
It got better. We spent months building a sophisticated internal text-to-SQL agent, d0, with specialized tools, heavy prompt engineering, and careful context ma...
Vercel now supports , a new TypeScript-based configuration file that brings type safety, dynamic logic, and better developer experience to project configuration...