AgentFlow empowers your business to deliver seamless, AI-driven customer interactions by configuring and deploying AI agents tailored to your unique needs. With AgentFlow, you can automate responses to enquiries, qualify leads efficiently, and optimize operational costs — all while maintaining control over your AI agent’s behavior through simple, flexible configurations. Whether you’re in sales, support, or operations, AgentFlow helps your team work smarter and scale conversations with ease.

Why use AI agents in AgentFlow

AgentFlow helps teams streamline customer conversations and reduce manual tasks by assigning AI agents to handle common interactions. Here’s how it makes a difference:

Pain points we are solving with this feature:

• Offer 24/7 customer support without extra staffing: AI agents can handle enquiries outside of business hours, reducing the need for a round-the-clock support team while keeping response times fast.
• Accelerate sales and support cycles: By automating first-touch responses and lead qualification, AI agents help speed up your workflows and get users to the right outcome faster.
• Lower operational costs through automation: Let AI handle repetitive or low-priority messages so your team can focus on high-value conversations.
• Control when AI participates in conversations: Set conditions for when the AI agent should enter, exit, or hand over to a human — giving you full control over the customer experience.

Common use cases:

• Handle FAQs automatically across channels: Set up your AI agent to respond to common customer questions using a connected knowledge base, keeping replies consistent and accurate.
• Qualify leads before handing them off: Use AI to score and filter incoming enquiries, so your team only engages with the most relevant prospects.
• Tailor AI behavior to different workflows: Adjust tone, logic, and actions to suit different teams or objectives — from customer support to pre-sales outreach.
• Trigger AI interactions with Flow Builder: Insert AI agents into automated flows that react to customer messages, ensuring the right response at the right time.

Accessing AgentFlow page

You can follow the steps below to access the AgentFlow page:

1. Click on the icon on the left navigation bar to go to the SleekFlow AI page
2. In the SleekFlow AI page, Click “AgentFlow” on the top navigation menu
   

Creating your AI agent

You can follow the steps below to create your AI agent in AgentFlow:

1. In the AgentFlow page, click on the “Create new agent” button on the top right corner
   
    
2. A “Create AI agent” modal will appear
   
    
3. You can choose a template to start, or create your own from scratch. We currently support the following templates that serve different purposes:
   1. Basic support:
      1. Use this if your goal is to handle common customer enquiries quickly and consistently. This template is ideal for support teams that want to automate FAQ replies or manage high-volume conversations with minimal setup
      2. Best for: Customer service or help desk use cases
      3. Focus: Speed and efficiency
      4. Available actions:
         1. Send message
         2. Exit conversation
         3. Add labels
   2. Sales growth:
      1. Choose this template if you want to qualify leads and support sales conversations. It’s designed for sales teams looking to automate lead scoring or early-stage prospecting before handing off to a human agent.
      2. Best for: Lead qualification and pre-sales engagement
      3. Focus: Quality and conversion potential
      4. Available actions:
         1. Send message
         2. Exit conversation
         3. Calculate lead score
         4. Add labels
   3. Custom:
      1. If your workflow doesn’t fit neatly into the templates above, you can build a fully custom AI agent. This option gives you full control over what actions are available and how the agent should behave, making it suitable for more complex or multi-team scenarios.
      2. Best for: Teams with specific workflows or advanced automation needs
      3. Focus: Flexibility and customization
      4. Available actions: Configurable based on setup
4. Once you have selected the template, you will be required to fill in the AI agent’s name. You can also fill in the description of this AI agent to provide context on its purpose, intended use case, or any specific instructions your team should be aware of.

Configuring your AI agent

Once you have created your AI agent, you will be redirected to the set up page of the agent you have created. 

To manage your AI agent’s configurations, you can click “Manage” to update its actions, instructions, or linked knowledge base at any time.

Here is a list of settings you can configure within an AI agent:

• Knowledge base: Link relevant content the AI can reference to generate accurate replies.
• Instructions: Define your agent’s objective, set a welcome message, and add guardrails to guide how the agent should behave in different scenarios.
• Actions: Select what the AI can do in a conversation, such as send messages, score leads, or exit.
• Flow deployment: Deploy your AI agent in Flow Builder to start using it. The agent will only respond in conversations once it’s added to an active flow.

Configuring AI agent's Knowledge base

To generate accurate and relevant replies, your AI agent must be connected to a knowledge base. This knowledge base acts as the central source of truth the agent uses to understand your business, answer customer enquiries, and take appropriate actions.

All AI agents in SleekFlow use the Global knowledge base, which stores all uploaded data sources shared across your workspace. When you add content through an individual AI agent, you’re uploading it to the Global knowledge base — ensuring consistency across agents.

To connect a knowledge base to your AI agent:

1. In the AgentFlow page, click “Manage” on the AI agent card
   
    
2. Click “Knowledge base” on the left-sided menu
3. You will be redirected to the Knowledge base of the agent
   
    
4. On this page, you can:
   1. Choose existing data sources from the Global knowledge base
   2. Or click “Add source” to upload new content
      
       
5. A pop-up modal will appear. You can import content by:
   1. Uploading a file (.PDF, .DOCX, .XLSX, or .JPG)
   2. Importing from a website URL
   3. Selecting from existing entries in the Global knowledge base
      

Uploading files to Global knowledge base

Once you have selected “File upload” in the previous step, you can then follow the steps below to upload files to AI agent’s Knowledge base:

1. In the “Import file to Global knowledge base” page, you can upload files in supported formats such as .DOCX, .PDF, .XLSX, or .JPG. Simply drag and drop your files, or select them from your device. Make sure your files meet the required format and size guidelines.
   
    
2. Once you have reviewed the uploaded files, click “Import”

Importing website URL to Global knowledge base

Once you have selected “Website URL” in the previous step, you can then follow the steps below to import website URL to AI agent’s Knowledge base:

1. In the “Import from website URL” page, enter the full public parent URL of the website you want to add. Parent URL refers to the main web page from which a linked article or subpage originates. It helps you identify the broader source or website domain your content is pulled from.
2. Once you have entered the parent URL, click “Scan URL”
3. The system will fetch all pages under the parent URL
   
    
4. Select the pages you wish to import to the Global knowledge base by checking the box to the left of each page name.
5. Once you have reviewed the URL sources you selected, click “Import”

Selecting data sources from Global knowledge base to an AI agent

Once you have selected “Selected from Global knowledge base” in the previous step, you can then follow the steps below to import website URL to AI agent’s Knowledge base:

1. In the “Select data sources for this AI agent” page, you will see the existing data sources in your Global knowledge base
   
    
2. Click on the checkbox next to the data source you would like to link this AI agent to
3. Once you have reviewed the selected data sources, you can click “Select”
   

Configuring AI agent's Instructions

The Instructions tab defines how your AI agent should behave during conversations — including its purpose, and how to respond in sensitive or unexpected situations. These settings help your AI agent stay aligned with your brand and ensure it engages customers effectively and responsibly.

To configure AI agent’s instructions, you can follow the steps below:

1. In the AgentFlow page, click “Manage” on the AI agent card
   
2. Click “Instructions” on the left-sided menu
3. You will be redirected to the “Instructions” page
   
4. In this page, you can configure the following:
   1. Instructions (overall behavior)
      1. Define the AI agent’s objective and provide detailed context about your business. You can specify who the agent represents, what types of enquiries it should handle, and how it should communicate (e.g. tone, language style, level of detail). The more specific your instructions, the more accurate and on-brand the AI’s responses will be.
      2. Example: “You are a friendly and knowledgeable assistant representing Cat Paradise. Our company provides premium cat grooming, boarding, and wellness services. When introducing yourself, say: ‘Hi! I’m from Cat Paradise. I’m here to help you with any questions about our services or products.’ You assist customers with booking spa sessions, explaining our service packages, and answering product-related questions. Use a warm, helpful tone and keep responses concise but informative.”
   2. Welcome message
      1. Write a greeting that appears when a customer first interacts with your AI agent. Use this to set expectations and establish tone.
      2. Example: “Hi there! I’m here to help with anything about our cat care services, grooming bookings, or product info 🐾”
   3. Guardrails
      1. Guardrails help your AI agent identify and respond appropriately to sensitive or complex topics. They guide how the agent should steer the conversation when certain types of input are detected — but they do not trigger additional actions like exiting or handing off the chat. Each guardrail includes:
         1. Observe for: Describe what the AI should watch out for. (For example: refund requests, pricing disputes, complaints, personal information)
         2. How to react: Specify how the AI should respond using tone, phrasing, or clarification questions (For example: acknowledge the concern politely and ask a follow-up question to gather more details)
      2. You can add multiple guardrails based on different types of sensitive content. For example:
         1. Example 1: Order issue
            1. Observe for: “Questions about refund status or order disputes.”
            2. How to react: “Apologize for the inconvenience and ask the customer to clarify their order number so you can better understand the issue.”
         2. Example 2: Damaged product
            1. Observe for: “Mentions of product defects or damaged items.”
            2. How to react: “Acknowledge the issue with empathy and ask the customer to describe the problem or provide a photo if possible.”
         3. Example 3: Data privacy concern
            1. Observe for: “Questions about personal data, privacy, or account security.”
            2. How to react: “Reassure the customer that their data is protected and direct them to review your company’s privacy policy for more details.”
      3. To add a guardrail, click “Add guardrail”, fill in both fields
5. Once you’ve finished configuring your AI agent’s instructions, you can test how it responds using the preview panel on the right.
   
   Note: You’ll need to have at least one fully trained knowledge base source before testing is available. If no source is ready, the test panel will remain inactive.
   
   
   ​
6. Once you are done with the configurations, click “Publish” on the top right corner to save the changes
    

Configuring AI agent's Actions

Actions define what your AI agent can do during a conversation — such as replying to customers, scoring leads, or exiting a chat. Each action is powered by a prompt that tells the agent how to respond. You can review and customize these prompts to match your workflow, brand tone, and business objectives.

You can access the AI agent’s Action page by following the steps below:

1. In the AgentFlow page, click “Manage” on the AI agent card
   
    
2. Click “Actions” on the left-sided menu
3. You will be redirected to the “Actions” page
   
    
4. In this page, you can configure the details of each available action for your AI agent:
   1. Send message and Exit conversation are required actions — they are enabled by default and cannot be turned off.
   2. For optional actions like Calculate lead score, and  Add labels, you can use the toggle switch to enable or disable them based on your agent’s role.
   3. Click on any action to view and customize the prompt that controls how the AI performs that task. This lets you fine-tune responses, scoring logic, and internal behavior to match your workflow.
       

“Send message” action

This is the core action that allows your AI agent to respond to incoming customer messages using the connected knowledge base. It is always enabled and runs automatically when a contact sends a message.

In this action, you can configure the following:

1. Response type: Choose how your AI agent prioritizes its replies:
   1. Prioritize speed – Uses basic knowledge retrieval to generate fast responses. Ideal for straightforward questions or high-volume support.
   2. Prioritize response quality – Uses advanced checks and personalization to generate more thoughtful, context-aware responses. Best for complex or sales-related enquiries.
2. Message tone of voice: Define how the AI should sound and what kind of behavior it should follow when replying to customers. This prompt guides the AI’s reply style, fallback handling, and content framing. You can include tone descriptors such as:
   1. Friendly and casual
   2. Polite and professional
   3. Conversational but confident
3. Trigger condition: Defines when this action is triggered during the conversation — for “Send message,” it runs automatically when a customer sends a message.
   1. This action automatically runs when the contact sends a message (#Run when: Contact sends a message)
   2. This condition is fixed and cannot be edited
4. Once you have completed configuring the instructions of the AI agent, you can test your AI agent on the right screen to see how it responds
   
   
    
5. Once you are done with the configurations, click “Publish” on the top right corner to save the changes

“Calculate lead score” action

This action allows your AI agent to evaluate each lead and assign a score between 0 and 100 based on message content, intent, urgency, tone, and fit. It helps your team identify high-quality leads, prioritize follow-ups, and streamline sales qualification.

This action is included by default in the Sales Growth template, but can also be toggled on manually when using other templates like Basic Support.

In this action, you can configure the following:

1. Trigger condition: The lead score is calculated automatically whenever the contact replies to the AI agent. You don’t need to configure this manually.
2. Scoring criteria and weights: Define the factors your AI should evaluate when scoring a lead. Each criterion is assigned a percentage weight, which determines how much it contributes to the final score.
   1. How scoring weights work:
      1. The AI evaluates each selected criterion based on the customer’s message.
      2. Each criterion contributes up to its assigned weight toward the total score.
      3. For example, if “Intent and interest level” is weighted at 40%, it can contribute up to 40 points out of 100.
      4. The total weight across all criteria must equal exactly 100% to ensure the AI calculates a complete score.
      5. If a criterion doesn’t apply to your workflow, you can remove it by clicking the “–” button in the top-left corner of the card. You must keep at least 1 active criterion for the lead score to be calculated.
3. Default example criteria (editable):
   1. Intent and interest level – Is the lead asking about features or making comparisons?
   2. Buying signals – Are they inquiring about pricing or expressing urgency?
   3. Depth and specificity – Are they asking focused, insightful questions?
   4. Engagement tone – Are they enthusiastic, hesitant, or neutral?
   5. Customer fit – Does their role or profile align with your ideal customer persona?
4. If you need to add more criteria, you can click “Add criteria”
5. Once you have completed configuring the instructions of the AI agent, you can test your AI agent on the right screen to see how it responds
   
    
6. Once you are done with the configurations, click “Publish” on the top right corner to save the changes

“Exit conversations” action

This action allows your AI agent to leave the conversation once a specific condition is met. Exit conditions are based on signals within the conversation — such as certain keywords or low confidence — rather than customer properties outside the chat. This action is always enabled and ensures smooth handoff or clean exits when appropriate.

In this action, you can configure the following:

1. Exit conditions: Define specific scenarios where the AI should end the conversation. You can create multiple conditions using natural language triggers such as:
   1. “Speak to human”
   2. “Confidence is low”
   3. “No matching answer found”
2. Each condition includes:
   1. Condition name – A label to help you identify the rule
   2. Exit condition – A short explanation of what triggers this exit (For example: when the AI is unsure, or the user explicitly asks to talk to a person)
   3. Condition type – Choose how the exit should be triggered:
      1. Exit based on message signal: Triggered when specific keywords or patterns appear in the customer’s message (e.g. “Speak to human”, “No matching answer found”)
         
   4. Exit based on lead score: This condition is triggered when the contact’s lead score meets a specific threshold. The lead score is calculated based on the criteria you’ve configured under the Calculate lead score action — such as intent, urgency, tone, or customer fit. You can set the AI agent to exit the conversation when the score:
      1. is less than a value
      2. is more than a value
      3. is between two values
         
         Use this condition to smoothly hand off hot leads or end conversations that don’t meet your qualification thresholds.
         
3. Once you are done with the configurations, click “Publish” on the top right corner to save the changes

Here are some of the examples of exit conditions:

Configuring AI agent's Flow deployment

Once your AI agent is configured, you can deploy it inside a conversation flow to start using it with real customers. The “Flow deployment” tab helps you view and manage all the flows where your AI agent is currently active.

To configure your AI agent’s Flow deployment, you can follow the steps below:

1. In the AgentFlow page, click “Manage” on the AI agent card
   
2. Click “Flow deployment” on the left-sided menu
   
3. You will be redirected to the Flow deployment page, where you will see a list of flows where the agent is currently in use. You’ll find details such as:
   1. Flow name
   2. Status (Active / Inactive)
   3. Logs
   4. Created by / Updated by
   5. Last updated time

If your agent hasn’t been added to any flows yet, the list will be empty and you’ll see an option to create new flow.

You can follow the steps below to create a flow in Flow Builder and deploy your AI agent:

1. In Flow Builder’s editor, click on the “AgentFlow (Beta)” action node to open up its form, which will appear on the right side of the screen
   
2. Select the AI agent you would like to use in this flow
3. Select the WhatsApp channel
4. Set triggers to determine when the AI joins the conversation
5. Define exit conditions and fallback actions to control handover logic
6. Click “Save” and then Publish your flow to make the deployment live

Writing effective prompts and instructions

AgentFlow relies on natural-language prompts to guide your AI agent’s behavior across various configurations — from overall instructions to guardrails, actions, and exit conditions. Writing specific and intentional prompts ensures your agent responds accurately, sounds on-brand, and understands how to navigate different types of conversations.

Use these best practices to craft strong prompts, with examples and where they apply:

1. Be specific about your business context

Providing clear context about your company, what the agent represents, and what it should handle helps your AI agent understand its role and generate relevant replies. This leads to more accurate and helpful conversations.

• Where to apply: Instructions (overall behavior)
• ✅ Good: “You are a support agent for Cat Paradise, a premium cat grooming and spa service. Help customers book appointments and answer grooming-related questions.”
• 🚫 Avoid: “You’re a support assistant. Help people.”

2. Define tone, style, and level of detail

Stating how your AI agent should sound and how much detail it should give ensures consistency with your brand voice and avoids overly long or overly vague answers.

• Where to apply: Instructions, Send message
• ✅ Good: “Use a friendly and casual tone.”
• 🚫 Avoid: “Just sound nice.”

3. Guide how the agent should behave in different situations

Good prompts don’t just define what to say — they clarify how the agent should react to uncertainty, edge cases, or sensitive topics. This helps reduce off-topic replies and improves reliability.

• Where to apply: Instructions, Guardrails, Send message
• ✅ Good: “If the customer asks something not covered in the knowledge base, politely ask for clarification. Avoid referencing external sources or assumptions. Provide as much business-specific context as possible to ensure accurate, on-brand responses.”
• 🚫 Avoid: “If unsure, figure it out.”

4. Use clear, structured prompts in actions

For each action, write prompts that describe what output is expected. This helps your AI agent perform consistently across conversations.

• Where to apply: Send message, Calculate lead score, 
• ✅ Good: Send message: “Answer using the knowledge base in a helpful tone. If the answer is unclear, ask the customer to clarify.”
• 🚫 Avoid: “Just write a response” or “Leave a note.”

5. Write precise exit condition

The Exit condition field tells the AI what kind of message or signal to look out for before exiting the conversation. This isn’t the message the AI will send — it’s a natural-language rule that describes when the exit should be triggered.

Writing a clear, specific condition helps the AI detect user intent accurately and prevents it from exiting too early or staying in the conversation longer than needed.

• Where to apply: Exit conversation → Exit condition field
• ✅ Good:
  • “Exit when the user says they want to talk to a human agent.”
  • “Exit if the message includes phrases like ‘cancel’, ‘stop’, or ‘end chat’.”
• 🚫 Avoid:
  • “Leave when it makes sense.”
  • “Say goodbye.”
  • “End the chat.”

6. Avoid vague or open-ended instructions

Instructions like “respond nicely” or “help the customer” don’t provide enough context. Your AI agent performs best when it has a clear purpose, role, and constraints.

• Where to apply: All prompt fields
• ✅ Good: “You are a support assistant helping customers understand product features. Keep answers short and friendly, and ask for clarification when needed.”
• 🚫 Avoid: “You’re here to help. Just be helpful.”