How Anthropic made claude.ai 3x faster in two weeks with Claude, merging 3,000+ changes
trq212 · x · 2026-09-30
Anthropic's engineering blog details a two-week August sprint that made claude.ai and the desktop app 3x faster, run entirely from a single Slack channel with Claude in every thread.
Key numbers
- Focus: four journeys covering 95% of user activity
- P75 time-to-typeable-page: 3.1s → 0.55s
- New Claude Code session: 0.8s → 0.3s
- Claude Cowork cloud session load: 2.6s → 0.73s
- Estimated tens of thousands of user-hours saved daily
How it worked
- Claude Tag (beta) ran an internal research model roughly comparable to Opus 5.5
- Claude found bottlenecks, built benchmarks, shipped improvements, watched every deploy; humans set goals, made tradeoffs, approved changes
- 3,000+ merged changes with zero customer-facing incidents or rollbacks
Core method: "Once Claude can measure something, it can make it faster" — keep expanding what gets measured.
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16
- AI agent deletes 43,599 lines of OpenClaw test code in one PR — vincent_koc · 2026-11-16