This August, we made the core user experience of claude.ai and the Claude desktop app about 3x faster in a two-week sprint. Users had been telling us it was slow, and they were right. We ran everything from a single Slack channel, with Claude in every thread. We focused on four journeys that make up 95% of user activity. At the 75th percentile, time to a typeable page on a fresh load of claude.ai went from 3.1 seconds to 0.55, starting a new Claude Code session went from 0.8 seconds to 0.3, and loading a Claude Cowork cloud session went from 2.6 seconds to 0.73. In aggregate, we estimate that saves tens of thousands of user-hours of waiting every day.

We used Claude Tag (beta), running an internal research model roughly comparable to Opus 5.5. Claude found bottlenecks, built benchmarks, shipped improvements, and watched every deploy. We steered by setting goals, making tradeoffs, and approving every change. With that approach, we merged more than three thousand changes without a single customer-facing incident or rollback.

Before the sprint, we created a Slack channel with standing instructions for Claude to facilitate all things related to performance. Claude analyzed usage data through the Datadog MCP server, identifying four high-impact user journeys. We kicked off with about twenty hand-picked projects. Claude estimated each project's impact in milliseconds, and we hit twelve of thirteen targets by day three.

For faster launches, we baked a static composer into the HTML and precompiled a V8 code cache. For faster navigations, we kept the composer mounted between conversations, prefetched sessions on hover, and cut sidebar re-renders by 90%. Claude identified new workstreams that exceeded our initial targets, and we set new goals. We iterated faster than our deploy cadence, with Claude working asynchronously overnight.