SleekFlow Product Requests

Users can add an AI summary step in a workflow to automatically generate a summary of a conversation, helping save time and improve handover or review.

'Staff' level users should be able to create Broadcast Campaigns. However, before a Broadcast Campaign can be published, an 'Admin' user must have the ability to review and either approve or reject the campaign. This approval workflow ensures that clients maintain full control and oversight over all Broadcast Campaigns before they are published.

Create and manage WhatsApp group conversations directly within SleekFlow to collaborate with multiple customers or team members at once.

Add a Note/Description field to each Flow Builder so users can document the flow's purpose, trigger conditions, related flows, or other important information. The note can be added or edited under Flow Builder → Settings. On the main Flow Builder list, a note icon can appear next to the Flow name. Users can hover over the icon to quickly view the note without opening and manually checking the entire Flow. Proposed UI: https://drive.google.com/file/d/1d_9oYF2D9sRahYJjKuOq1eCpLDBPDJHo/view?usp=sharing

Currently, the Team Management feature in v2 only supports Meta channels: WhatsApp, Instagram, and FB Messenger. As SleekFlow supports multi-channel connectivity beyond Meta, this limitation impacts clients who operate dedicated teams for individual channels such as LINE or TikTok. Team Management should be available across all connected channels to reflect real-world workflows and ensure consistent functionality for all clients.

Send WhatsApp stickers from curated sticker packs to engage customers with expressive, visual messaging.

When investigating flow enrollment issues, we can currently view the enrollment activity logs. However, the enrollment details only show basic information, such as the timestamp and whether a particular node has started, completed, or failed. If we need to investigate what values or variables were passed through a node, we currently have to go back to the flow configuration and manually verify the contact's information and the relevant node settings. This becomes even more challenging when a contact property has been updated after the enrollment took place, it can be difficult to determine what data the flow actually processed at that point in time. It would be helpful if the Enrollment Details could provide more information for each node, particularly the values or variables that were passed and processed when the node was executed. For example, The input values/variables received by the node The values/variables processed by the node The resulting output values, where applicable This would make troubleshooting enrollment issues significantly easier and faster. Instead of having to trace back through the flow configuration and manually verify the contact's information, users could see exactly what data was passed through each node at the time of execution. It would also provide a clearer audit trail of how an enrollment progressed through the flow and help identify where unexpected values or processing issues occurred.

Request: Provide an easy way for users to activate or assign an AI Agent to an ongoing conversation, without requiring the customer to send another message. Current Behavior When a conversation is already in progress: The customer sends a message. The conversation is currently being handled by a human agent. The user decides that the AI Agent should take over the conversation. The user adds the relevant AI enrollment label. The AI Agent is enrolled, but does not respond to the customer's latest message. The AI Agent only responds after the customer sends another message. This creates a gap where the customer's latest unanswered message remains pending even though the AI Agent has already been activated. Requested Behavior Allow users to assign/activate an AI Agent directly within an existing conversation. For example: Customer sends: "What are your opening hours?" Human agent reviews the conversation and decides the AI Agent can handle it. User selects "Assign to AI Agent" or "Activate AI Agent". The AI Agent immediately processes and responds to the customer's latest unanswered message. The customer does not need to send another message to trigger the AI. Why This Is Needed The current label-based enrollment creates an unnecessary dependency on the customer sending another message. This can cause: The customer's latest message to remain unanswered. Delays in customer response time. Human agents having to manually respond before the AI can take over. A poor customer experience, especially when the customer is expecting an immediate response. Confusion for users who assume that enrolling the AI Agent means it will immediately handle the conversation. Expected Outcome A user should be able to move an active conversation from a human agent to an AI Agent at any point, with the AI Agent immediately handling the latest unanswered customer message without requiring the customer to send an additional message.

For the AI Assistant response, I would like to have the AI Assistant to be able to know whats the date and time at that moment when drafting the message, it will help cross-checking with other contact properties and draft the best answer. E.g. Understanding the contact's birthday is coming up. In addition, I'd like the AI Assistant to be able to include URL when drafting the response to easily link the contact to the websites.

Currently, a low-credit banner is shown in the platform when the WhatsApp credit balance falls below USD 20. However, users may not notice the banner if they are not actively logged in to the platform. Please consider adding an email notification when the WhatsApp credit balance falls below the low-balance threshold. The email could remind users to top up their balance or check their auto top-up settings before message delivery is affected. This would help teams monitor their credit balance proactively and reduce the risk of broadcasts or other WhatsApp messages being interrupted due to insufficient credit.