Please let us block the composer in AI advanced agents | The place for Zendesk users to come together and share
Skip to main content
Feedback submitted

Please let us block the composer in AI advanced agents

Related products:Chat/Messaging
  • April 13, 2026
  • 3 replies
  • 26 views

gonzalo.benitez

Please give a quick overview of your product feature request or feedback and note who in your organization is affected by this issue [ex. agents, admins, customers, etc.] (2-3 sentences)

We need the ability to block the messaging composer when the AI agent sends button or quick reply options in a dialogue flow. Currently, blockChatInput is only available via the Sunshine Conversations Post Message API, but not as a native option in the AI agents – Advanced dialogue builder. This affects our customers (degraded UX), our bot operations team (extra workarounds to handle unintended free text), and our agents (who receive unnecessary escalations caused by broken flows).

 

What problem do you see this solving? (1-2 sentences)

When the AI agent presents buttons, customers often type free text before the message finishes loading, which breaks the dialogue flow and causes misrouting or intent reclassification. Blocking the composer during button steps would guarantee customers follow the intended interaction path.

 

When was the last time you were affected by this lack of functionality, or specific tool? What happened? How often does this problem occur and how does this impact your business? (3-4 sentences)

This happens daily across multiple use cases. Customers type a response before the button options have fully rendered, which triggers a new intent classification and kicks them out of the current flow. They then receive an unrelated response or get routed to the wrong path, leading to confusion, repeated messages, and unnecessary escalations to live agents. This directly impacts our automated resolution rate and increases our average handling time.

 

Are you currently using a workaround to solve this problem? (If yes, please explain) (1-2 sentences)

No viable workaround exists. We attempted to send button messages via the Sunshine Conversations API with blockChatInput: true from the integration builder, but the dialogue builder cannot listen for customer replies to API-sent messages, making it impossible to continue the flow.

 

What would be your ideal solution to this problem? How would it work or function? (1-2 sentences)

A simple toggle on AI agent message blocks in the dialogue builder (e.g., "Block composer while buttons are displayed") that automatically sets blockChatInput: true on the underlying Sunshine Conversations message and unblocks it when the customer selects an option.

 

3 replies

Tobias11
  • Contributor
  • April 13, 2026

Hi, 

 

You can add a option with free text written, then agent message says please click button and move back to the step before should work 


gonzalo.benitez

Hey Tobias,

We already do that, but CX experience is bad, and sometimes the buttons take time to load. A better UX would be just directly don’t instruct the option to the CX and block the composer, making crystal clear that indeed they need to select a button

Thanks


Tobias11
  • Contributor
  • April 14, 2026

Hi,

i just mention this due to you wrote: “No viable workaround exists”.

I also support this request as I don´t like workarounds. I think the main issue is, that the button style is also not really good placed / visible color wise, so if your flow is a mix of typing + buttons there is a issue.

Another issue is that buttons are not supported in procedure, cause another conflict on that how customer navigate from start to end to the conversations.