SleekFlow Product Requests

Feature request: Integrate SleekFlow with Google Calendar to allow users and AI Agents to manage and schedule appointments directly from the platform. Expected functionality: Connect a user's Google Calendar account to SleekFlow. Check real-time calendar availability directly within SleekFlow. Create, update, and cancel Google Calendar events from conversations or workflows. Allow AI Agents to schedule appointments based on calendar availability. Send automated appointment confirmations and reminders. Sync calendar events to help avoid double bookings. Use case: Many customers use SleekFlow to communicate with leads and customers who need to schedule appointments. A Google Calendar integration would allow teams and AI Agents to manage the scheduling process directly within SleekFlow, without requiring users to switch between platforms.

Feature request: Allow customers to check their Shopify order and shipment status directly through SleekFlow, either via AI or through automations/triggers. Current situation: Many Shopify customers contact businesses through WhatsApp and other channels to ask about their orders, such as "Where is my order?" or "When will it arrive?". Today, agents may need to manually check Shopify before responding. Expected functionality: Retrieve Shopify order information directly within SleekFlow. Allow AI Agents to check order and shipment status and respond automatically. Enable automations/triggers based on Shopify order status. Provide information such as order status, tracking number, shipment status, and estimated delivery date when available. Allow the AI to identify the customer and retrieve their relevant order information. Support proactive notifications based on changes in order or shipment status. Use case: For Shopify merchants, order-status questions are a frequent customer service request. Connecting SleekFlow directly with Shopify order and shipment data would allow AI and automations to handle these interactions automatically, reducing manual work for support teams and providing faster responses to customers.

Feature request: Make SleekFlow available through Claude connectors / Model Context Protocol (MCP), allowing AI Agents to securely access SleekFlow data and perform actions directly within the platform. Current situation: Customers are increasingly looking to use AI Agents that can not only retrieve information but also interact with their business systems and execute actions. In addition, many customers want to use their SleekFlow data for analysis, reporting, and business insights through AI tools such as Claude. Expected functionality: -- Provide a SleekFlow MCP server/connector compatible with Claude. Allow Claude-based AI Agents to securely access relevant SleekFlow data. Enable customers to use SleekFlow data for AI-powered analysis and reporting. Enable AI Agents to perform supported actions within SleekFlow, such as updating contacts, managing conversations, creating tasks, or triggering workflows. Implement appropriate authentication, permissions, and access controls. Use case: Customers want to connect Claude directly to SleekFlow so they can analyze their customer and conversation data, generate insights and reports, and take actions based on those insights. MCP support would make SleekFlow data more accessible within customers' existing AI workflows while also enabling Claude to interact with the platform.

Customers who run high-volume customer service operations need to report on agent workload at an hourly level, not just daily. Currently, Conversation Analytics only supports "Group by" at Day, Week, or Month granularity. The existing hourly heatmap in Advanced Analytics only covers conversation open/close events and shows a distribution pattern across a date range — it does not provide the actual metric counts for a specific hour. Requested capability: Add hourly grouping to Conversation Analytics, including both Dashboard view and CSV export, so customers can verify the following metrics per hour: > Messages received (incoming customer messages) > Unique customers received (deduplicated count of customers who sent at least one message) > Messages sent by human agents (filtered by isSentFromSleekflow=true and deliveryType=Normal) > Unique customers handled (deduplicated count of customers who received at least one human agent reply) Requirements: Support "Group by: Hour" alongside the existing Day / Week / Month options. Respect the workspace timezone setting when computing hourly boundaries. Allow filtering by Channel, so metrics can be isolated per channel (e.g., Telegram, WhatsApp, Facebook). Include hourly data in the CSV export, not just the on-screen view. Ideally include the same four metrics listed above, with consistent definitions matching the raw API fields.

This feature allows users to sync message history directly to their CRM's activity tab. Users benefit from a more organized and accessible communication log, ensuring that all interactions are visible within their primary workflow for better tracking and management.

This feature enables users to link Google Ads spend with actual converted leads in SleekFlow, enabling accurate ROI measurement and smarter budget allocation.

Develop a native integration between SleekFlow and n8n to enable automations without manual API/Webhook setup, reducing technical complexity, accelerating onboarding, and expanding integration possibilities for customers using advanced workflows, AI, and process automation.

Currently, the Facebook Lead Ads integration only captures the page_id and lead_id. It does not expose the campaign_id or ad_id. Adding these fields is crucial for our marketing team so we can properly track attribution, measure ROI, and know exactly which campaign or specific ad creative generated each lead directly inside SleekFlow. Reference: https://developers.facebook.com/documentation/ads-commerce/marketing-api/reference/adgroup

Context & Use Case: I have a requirement to support a WhatsApp typing indicator. When my end-customer triggers a message, my custom LLM takes a few moments to process and generate a response. To keep the end-user engaged on WhatsApp during this delay, I want to display a live typing indicator on the user's personal WhatsApp interface. The Proposed Solution: You already have an internal endpoint (POST /conversation/typing) that triggers this behavior natively. Instead of building complex backend/UI overrides on my end, I propose exposing this existing internal API to clients. This would allow my custom LLM setup to independently ping the endpoint and trigger the typing state on WhatsApp while my AI generates the payload. This change does not impact our core platform UI and leverages infrastructure we already own. Thank you!

Context & Use Case We are actively building automation workflows and deploying custom AI Agents within SleekFlow to handle customer inquiries. Our internal database, CRM, and inventory systems run entirely on a GraphQL infrastructure. Currently, when we use the "HTTP Request" action in Flow Builder or try to connect a custom API tool to an AI Agent, the platform only natively supports standard REST configurations (GET/POST with flat JSON payloads). The Problem (Pain Points) Requirement for Custom Middleware: Because SleekFlow cannot natively send or process GraphQL queries and mutations, we are forced to build, host, and maintain a dedicated intermediary middleware server. This middleware exists solely to translate SleekFlow's REST requests into GraphQL, and then map our GraphQL responses back into flat REST JSON bodies. Increased Engineering Overhead & Latency: This translation layer introduces an unnecessary single point of failure, extra infrastructure costs, and added latency to our real-time customer journeys. The Proposed Solution We request that SleekFlow adds native GraphQL support to the custom API/HTTP action modules in both Flow Builder and AI Agent integration settings. Benefits For Customers: Allows enterprise teams with modern tech stacks to seamlessly connect their internal data to SleekFlow’s automation and AI tools without building intermediate REST wrapper middleware. For AI Efficiency: Drastically optimizes token usage and accuracy for AI Agents by restricting data retrieval to exact fields.