Not really. Long-running tasks work, but you get zero visibility into what's happening. You submit something, it processes for hours, and you're completely blind to the intermediate steps or reasoning. If something goes wrong, you won't know where it failed or why. For simple tasks it's fine, but for complex technical work—deployments, optimizations, debugging—this is a real gap. You need to see what the agent is actually doing, not just the final result.
Happycapy