SleekFlow Product Requests

Building AI-powered WhatsApp journeys where the AI agent should proactively engage customers immediately after a lead form submission, without requiring the customer to first click a button or send a message. Current limitation: AI agents can only continue conversations after a user interaction / workflow enrollment. Current workaround requires: webhook/contact update. sending a static automated template/button message customer clicking the button. workflow enrolling the customer into the AI agent flow. Requested enhancement: Allow AI agents to proactively initiate outbound conversations dynamically as the first interaction, while using customer context/API data immediately. Example use case: Customer submits a quote/lead form externally. AI agent proactively reaches out on WhatsApp with personalized contextual information (supplier match, quote details, FAQs, etc.). AI continues the conversation naturally without requiring button-click enrollment. Business impact: Removes friction from AI engagement journeys. Improves conversion/engagement rates. Enables more natural AI-assisted lead nurturing. Important requirement for enterprise AI onboarding use cases.

Customers often upload Excel files that are visually formatted for human readability rather than structured as flat datasets. Example issue: Multiple sub-tables arranged in one sheet. Merged cells used for headers such as duration or calorie tiers. Repeated columns with different meanings in separate sections. Visual relationships between cells are clear to humans but not machine-readable. Current AI Knowledge Base parsing struggles to accurately interpret these files, causing incorrect retrieval of pricing or other structured information. It would be great to enable AI/Knowledge Base to better understand “visually connected” Excel layouts by: Detecting repeated table regions within a sheet. Interpreting merged cells as contextual metadata. Mapping headers hierarchically. Inferring relationships between visually grouped data. This would reduce manual preprocessing and improve usability for customers uploading pricing lists, menus, catalogs, and similar spreadsheets.

This feature enables users to search for specific information within their uploaded knowledge base content, including data from URLs. Users benefit by being able to quickly locate relevant details and answers across their entire library of resources, rather than being limited to searching only by file or source names.

This feature provides a simplified setup process for the AI assistant, enabling users to build their own internal co-pilot agent. By streamlining the configuration, users can quickly create a customized digital assistant tailored to their specific workflows and needs.

This feature allows the user to configure an agent to automatically reach out and re-engage customers who have stopped responding during a conversation. This helps the user maintain communication flow and ensures that customer inquiries are followed through to completion without manual intervention.

The AI Shopping Assistant allows users to provide a seamless end-to-end purchasing experience directly within the chat widget. By mimicking an in-store shopping experience, users can help their customers complete entire transactions without ever leaving the conversation, significantly streamlining the path to purchase.

Users can utilize AI agents to manage post-sales inquiries, such as retrieving order details and processing refunds or returns. This feature streamlines the support process by allowing the user to handle common customer requests automatically and efficiently.

This feature enables an AI agent to assist users by sending product or cart links directly to customers from their online store. Users also benefit from automated support for order tracking and personalized product recommendations, helping them provide a more efficient and helpful shopping experience.

This feature allows users to export AI performance metrics directly from the platform. By enabling this capability, users can more effectively analyze data and gain deeper insights into their AI operations for better reporting and decision-making.

This feature adds a "Group by" function to the AI Analytics Dashboard, allowing users to organize data by days, weeks, or months. By using these built-in time segments, users can easily analyze trends and patterns over specific periods without needing to manually export and sort data.