Step 1: Start in the Bot Builder #
- Access the bot builder and create a new bot.
Step 2: Configure Trigger and Conditions #
- Set the trigger for the bot (e.g., hot keyword).
- Define the channel (e.g., WhatsApp) and the necessary conditions for activation.
Step 3: Set Up the User Query Step #
- Add a step to ask the user, “What is your query?”.
- The next step should capture the user’s response to pass to the trained AI.
Step 4: Connect to Trained AI #
- In the builder, create a new AI integration.
- Go to your AI dashboard, copy the authentication token, and paste it into the bot builder.
- After adding authentication, select the AI agent you want to use (e.g., Support Agent).
- Choose all relevant files or leave the selection empty to use all agent files for response generation.
Step 5: Customize System Prompts and Replies #
- Optionally, add a system prompt for specific fallback replies if the AI cannot answer the user’s query.
- Your bot flow can also include parameters like contact number, channel name, or user name for personalization.
Step 6: Mapping AI Answers #
- Map the AI’s answer to a “send message” block.
- If no answer is available, configure a fallback message or route the conversation to a human agent.
- Use error handling to define fallback actions if the AI is unavailable.
Step 7: Continue the Conversation #
- Set up an “AI smart wait” step (e.g., 5 minutes) to wait for additional user replies.
- If the user responds, pass the new query back to the AI agent; otherwise, end the session politely.
- Implement exit keywords (e.g., “bye”) to close the conversation with an appropriate message.
Step 8: Test and Refine #
- Test your bot’s flow and edit steps as needed for smooth conversation and accurate answers.
This process will result in a WhatsApp-based AI chatbot that can reply intelligently to user questions based on your documents and data, and escalate the conversation to a human if needed.
Bot Flow Template Clone Link #
Copy to clipboard
/products/bot/flow/fc173d9d770af2f3c754c429c8d894fc