… Throughput - A single-stream agent does one thing at a time, but real codebases need many hypotheses against many components at once, with the ability to fan out further when something interesting turns up. …
… We built this in production, with real users, against real accounts. …
… Last month, when we shipped the Dynamic Workers open beta , we gave those platforms a clean primitive for the compute side: hand the Workers runtime some code at runtime, get back an isolated, sandboxed Worker, on the same machine, in single-digit milliseconds. …
… Here is the plugin roster for a typical internal review: Plugin Responsibility @opencode-reviewer/gitlab GitLab VCS provider, MR data, MCP comment server @opencode-reviewer/cloudflare AI Gateway configuration, model tiers, failback chains @opencode-reviewer/codex Internal compliance checking agains… …
… The config is compiled at deploy time from structured source files and contains placeholder values like {baseURL} for the Worker's origin. At request time, the Worker replaces these, so all provider requests route through the Worker rather than directly to model providers. …
… Snapstone closes this gap by providing a unified way to bring progressive rollout, real-time health monitoring, and automated rollback to configuration deployments by default. …
… Add voice to your agent An experimental voice pipeline for the Agents SDK enables real-time voice interactions over WebSockets. …
… In March 2026, legacy Workers documentation was crawled around 46,000 times by OpenAI, 3,600 times by Anthropic, and 1,700 times by Meta. …
… And you can always follow real-time DNS trends and TLD data on Cloudflare Radar . …
… Over time, this got us to a place where benchmark scores improved consistently with each iteration and we had a generalized architecture that would work in the real world. …