Ideas for building
better software.

Browser Run - Browser Run adds structured handoff for Human in the Loop

Browser Run now supports structured handoff for Human in the Loop workflows. Using Cloudflare-specific CDP commands, your agent can signal that it needs help, a human steps in through Live View to handle the task, and the agent resumes once the work is done. For agents running multi-step browser workflows, a single login wall or unexpected prompt can fail the entire run. Previously, scripts had to manage human intervention manually by sharing a Live View URL and polling for completion. Structure

Cloudflare One, Gateway - Control Cloudflare Gateway DNS caching with a maximum TTL setting

You can now set a maximum time-to-live (TTL) for DNS responses returned by Gateway. When an upstream DNS record has a TTL that exceeds the configured maximum, Gateway caps it to your specified value. This ensures that DNS policy changes - such as blocking a newly identified malicious domain - take effect faster across all clients. Traffic settings, showing a numeric input field that accepts values between 60 and 36,000 seconds" loading="lazy" decoding="async" width="2170" height="294"> The sett

Elastic Cloud Serverless: Ongoing multicontinent expansion

Elastic announces the availability of Elastic Cloud Serverless in two additional Azure regions and two additional Google Cloud regions. Elastic meets customers where their data is — all around the globe.

Vercel Connect now supports Custom Environments

now lets you link a connector to a so deployments there can request provider tokens and receive forwarded webhooks.Vercel ConnectCustom Environment Custom Environments appear alongside Production, Preview, and Development when you add or edit a project on a connector in the dashboard. From the CLI, pass the environment's slug to :--environment Passing replaces the default environments.--environment Once linked, a deployment in that environment can request tokens with as usual. If the calling

This Week in Spring - July 28th, 2026

Workers AI - Select models now require the Workers Paid plan

We are limiting Workers Free plan access to a few resource-intensive models so we can prioritize capacity for the broader Workers AI user base. This helps everyone get a more reliable inference experience, with fewer 429 and 3040 (Out of Capacity) errors. The following models now require the Workers Paid plan: @cf/moonshotai/kimi-k2.6 @cf/moonshotai/kimi-k2.7-code @cf/zai-org/glm-5.2 On the Workers Free plan, requests to these models now return a 403 HTTP error (internal error 5035) prompting yo

Workers - Workers tracing — write custom spans with new startActiveSpan() and span.end() runtime APIs

The Workers runtime now provides built-in tracing.startActiveSpan() and span.end() APIs, allowing you to write custom spans for operations that last beyond a single callback — for example, instrumenting a stream pipeline where the span should stay open until the stream is fully consumed. This augments the existing API for writing custom spans, tracing.enterSpan(), which automatically ends a span when its callback is returned. With startActiveSpan(), the span remains open after the callback retur

The 4 Failure Modes of Agent Context in Production

A production AI agent depends heavily on the context layer that tells it what to know at the moment it acts. It can pass every staging test, answer questions, call the right tools, and demo beautifully, then hit production and confidently offer a re...