Latency is something we’re actively working on. Because the agent sometimes calls multiple tools (venue retrieval, cost estimation, ranking, etc.), it can feel slower than a traditional search UI. We’re optimizing tool chaining and caching right now, but it’s definitely an area where we need to improve. If it ever feels sluggish, that’s on us.

Filtering UI: Also agree. We leaned heavily into conversation because planning is iterative and constraint-driven, but that doesn’t mean everything should require typing. A hybrid approach (chat + explicit filters/sliders/toggles) probably makes more sense for power users. We already have structured results on the right adding faster, direct manipulation controls there is a logical next step.

Appreciate you calling it out. If you were using this for real, what filters would you expect to be immediately clickable instead of typed?

Price, location, time, event type, group size, for starters.