design teams are drowning in review. more agents shipping more UI, and either sh*t gets shipped or design slows everyone down.
so we built a design review agent that lives in GitHub PRs. encode a ruling once, it runs on every PR forever.
Introducing Claude Opus 4.7, our most capable Opus model yet.
It handles long-running tasks with more rigor, follows instructions more precisely, and verifies its own outputs before reporting back.
You can hand off your hardest work with less supervision.
Even very complex work still only requires deep reasoning every few steps. But you never know *when* that reasoning step is needed.
So let the executor agent decide!
We're bringing the advisor strategy to the Claude Platform.
Pair Opus as an advisor with Sonnet or Haiku as an executor, and get near Opus-level intelligence in your agents at a fraction of the cost.
@aiDotEngineer Europe has been the highest signal conference I’ve seen to in a long time.
And I’m also old like @badlogicgames so I’ve been to plenty in my time!