ToolsThe story, in brief

Web Application Firewall control now available with vercel.json

Vercel embeds AI-native security: agents can now auto-generate WAF rules via vercel.json.

Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
New tools for building and creating with AI.AI illustration by KeyNews
The KeyNews take

Why it matters

Vercel is lowering the friction for AI agents to author and deploy security rules declaratively. This is an infrastructure play that makes it easier for LLM-based code generation tools to handle security configuration at scale, reducing manual security toil for developers.

The key facts

9 to know
  1. WAF control now available in vercel.json alongside dashboard, API, and Terraform

  2. Agents can use code-generating prompts to author WAF rules

  3. Enhanced matchers support headers, rewrites, redirects, routes

  4. Matching includes: string equality/inequality, regex, prefixes/suffixes, array inclusion/exclusion, numeric comparisons

  5. Declarative approach enables structured rule injection into projects

  6. Explicitly designed for agents to author rules via code-generating prompts

  7. Enhanced matchers: string equality, regex, prefixes/suffixes, array inclusion, numeric comparisons

  8. Supports more expressive conditions across headers, rewrites, redirects, and routes

  9. Published July 9, 2025

Go to the source

Vercel Blogvercel.com

Publisher excerpt: You can now control Vercel’s Web Application Firewall (WAF) actions directly in , alongside existing support in the dashboard, API, and terraform.vercel.json This approach provides a structured way for both developers and agents to declaratively define and push rules to projects. Agents can use…
Read original report
Back to today's editionMore tools news

The wider picture

View all
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
AI illustration by KeyNews
Tools01

The Genie One MCP is now Generally Available

Genie One MCP is a production-ready tool layer for integrating coding agents into enterprise workflows. Practitioners building agentic systems now have a standardized, vendor-backed protocol for connecting agents to IDEs and development environments — lowering friction from pilot to deployment.

Databricks
Illustration of a transparent lens revealing connected networks across layers of paper.
AI illustration by KeyNews
Tools02

llm-typesafe 0.1a0

A new Python library for enforcing type-safe outputs from LLMs—useful for practitioners building production applications where unpredictable output shapes break downstream code. Early alpha, but addresses a real friction point in AI app development.

Simon Willison
Paper-cut illustration of a coral software window opening into a three-dimensional drafting space.
AI illustration by KeyNews
Tools03

Right-size generative AI endpoints with concurrency sweeps on Amazon SageMaker AI

Practitioners deploying generative AI on AWS can now benchmark endpoints at scale and make data-driven capacity decisions, reducing over-provisioning costs and avoiding under-capacity surprises in production.

AWS Machine Learning Blog
Web Application Firewall control now available with vercel.json | KeyNews.AI