Test in the playground
Open the Playground tab in the designer and chat with your agent as if you were the customer. Every conversation you run is saved automatically — click History to revisit the last 20 test sessions for the agent, so you can compare behaviour before and after a change.
Connect inboxes
Click Inboxes in the designer header and select which inboxes the agent should handle — each inbox can only be assigned to one flow agent. Per inbox you can also set:
- Pause when a human replies — when a teammate answers (from the dashboard or the connected app), the agent steps back automatically instead of talking over them.
- Don’t reply to these labels — the agent skips any conversation or contact tagged with the labels you pick, so VIPs or complaint cases stay human-handled.
- Only reply to specific ads — limit the agent to chats that started from particular Meta ad IDs.
- Ignore WhatsApp group chats — the agent stays out of group conversations.
Publish
Click Publish and choose who can talk to the agent:
- Public — everyone messaging the connected inboxes.
- Testers only — only the phone numbers you list, so you can trial the agent on a live channel before opening it up.
If the agent is set to hand off silently (a blank handoff message), the first publish shows what customers will experience and asks you to confirm before going live.
Behaviour settings
The Settings button in the designer header controls how the agent behaves in conversation: whether it keeps answering FAQs after the flow ends, whether it answers FAQs on the very first message, how long it pauses after a handoff before resuming (15 minutes to 24 hours, or never), the re-ask limit for collect steps, and an optional delay before replying so responses feel less instant.
If the agent ever stops replying with an error about limits, check your plan’s AI credit usage — the agent pauses when the account’s credit limit is reached and resumes once it renews or is raised.