Agentic development is moving beyond one-off chats.
The useful part isn’t just getting an agent to complete a task once. It’s being able to understand what it did, review the output, and turn that work into something repeatable.
That's where we focused in August across eight Agent Canvas releases:
⚡ Better automations with live run status, dashboards, Git sync, and reusable configuration
🎛️ More control over models, providers, context, cost, and agent behavior
🧩 Canvas Apps beta, plus better ways to inspect files, commits, and agent output
Read the full August product update: