Engineering Insights

How Fern runs multi-tenant docs for Webflow and ElevenLabs on Vercel

Fern on Vercel 3x faster time to first byte Page load times reduced by 80% 6 million+ page views per month from 1 million+ unique visitors 65% of the platform migrated from Pages Router to App Router in 7 days Fern helps companies ship developer documentation and SDKs, running customer docs for Webflow, ElevenLabs, and others across custom domains from a single Next.js app on Vercel. Mid-migration from the Pages Router to the App Router, the team moved 65% of the platform in seven days ins

How Code and Theory cut time-to-prototype 75% with v0

Code and Theory on Vercel Time-to-prototype cut by 75% Deployment timelines reduced by over 50% Wireframe and PRD process replaced by live prototypes Code and Theory is a digital-first creative and technology agency that combines strategy, design, and engineering for brands like Microsoft, Amazon, and NBC. The agency replaced wireframes and requirement documents with prompt-to-code workflows in v0, so product, engineering, and go-to-market teams can turn a client brief into a working protot

Sandbox SDK - Deprecating Sandbox SDK features

Today we are announcing the deprecation of several features from the Sandbox SDK. The SDK has grown and matured substantially since it first launched. As agent workflows have developed, we have shipped many new features and experiments so developers can easily integrate secure, isolated code execution into their workflows. We want the SDK to continue providing a stable foundation for agentic workflows while we iterate quickly on the codebase. These deprecated features have either been superseded

Gremlin: turning open tasks into pull requests

Gremlin is an autonomous engineering agent for small, well-scoped tasks. It uses Mastra for orchestration and OpenCode in a sandbox to turn Sentry issues, Linear tasks, and Slack instructions into reviewable pull requests.

Context engineering for AI agents: the infrastructure behind every decision

Your agent is only as good as the information it can see at decision time. The data sitting in your infrastructure doesn't count, and neither does what the model learned in training months ago. What counts is the specific tokens loaded into its contex...

Budgets for API keys on AI Gateway

AI costs are getting harder to forecast. As teams lean more on coding agents and other token-heavy workflows, a key can burn cost faster than anyone notices: Set a spend cap on any key, and rejects further requests on that key once the limit is exceeded, until the budget resets or you raise it. The cap applies to all AI Gateway providers and models running through the key, making it easier to consolidate and govern AI costs.AI Gateway On the , click , enable the option, enter a limit in dollar

Migrating Your GitHub CI to Hugging Face Jobs

WAF - WAF Release - 2026-06-09

This release introduces new detections for a critical SQL injection vulnerability in Drupal installations utilizing PostgreSQL (CVE-2026-9082), alongside targeted protection for an unsafe deserialization flaw in the Mirasvit Cache Warmer extension (CVE-2026-45247). Additionally, this release includes coverage for a prototype pollution vector in Axios (CVE-2026-40175) and a new generic rule designed to identify and block sophisticated SQL Injection (SQLi) bypass attempts leveraging obfuscated boo