Lead Collection #
Chatsistant utilizes a multiple-agent architecture for its chatbot design. To facilitate lead collection within this framework, you have the option to either create a dedicated Lead Collection Agent or integrate its functionalities into an existing one.
Create Lead Collection Agent #
To create a Lead Collection Agent, navigate to the “AI Agents” tab within the Chatsistant platform. Here, you’ll find the template for a Lead Collection Agent by selecting “Create new Agent”.
Edit Lead Collection Agent Prompt #
After creating the new Agent, access its edit screen by clicking on it. Scroll down to review the base prompt. Depending on the information you aim to capture, configure the base prompt accordingly.
Click “Save changes”.
Add/Edit Agent variables #
Next, go to the “Variables” tab. For each piece of information you want to capture, make sure there is a corresponding Variable created to store it.
Define Agent Variable #
When defining the variable, be as explicit and concise as possible. Where you can, try to provide examples for what the intended values look like. You can also pre-define the variable’s default state. If left empty, its default value will be “NOT PROVIDED”.
Lead Agent Gateway -Make Variable have non-empty values #
Additionally, you can make it mandatory for the Variables to have non-empty (non-”NOT PROVIDED”) values before the AI Supervisor switches away from the Agent. You can do so using AI Supervisor Overrides. If you apply the appropriate settings there, the Lead Collection Agent will not switch away until all the Variables defined in this Agent have been assigned proper values.
Agent Knowledge tab enable/disable All Sources #
Next, head over to the “Knowledge” tab. Depending on what information you’d like the Agent to have access to when requesting user information, you can link the associated training data with this Agent. In general, Lead Collection Agents are designed to specialize in collecting personal information from users, so they may not need any knowledge base access. To disable all knowledge, simply toggle off “All Sources” and leave “Agent Sources” empty.
Save and connect Lead Agent #
Click “Save changes” and close the Agent edit dialog. Return to the Agent selection view. You can now “Connect” your new Lead Collection Agent. On the top right of the Agent card, open the “three dot” dropdown menu, then select “Connect”.
Agent training status (blue dot vs. green dot) #
You should now see a glowing blue dot next to “Lead Collection”, indicating that the Agent is being trained. Since you may want your Agent to collect user information before performing any service, you can set this as the “Initial Agent” to handle the first incoming user query.
After the blue dot turns green, your Agent will be good to go. You may need to refresh the page to check for status updates.
Preview mode for chatbot testing and debugging #
Go to the “Preview” tab. You can now test your new chatbot, now equipped with conversational Lead Collection capabilities!
Example Conversation trained to ask for contact info naturally like a human conversation. #
#
Here is a full example showing lead collection of the variables and the agent assigned. You can see how the Lead Agent collects the name, email, and phone number which is now ready to be sent seamlessly to your CRM or any application via webhook, etc. After Lead collection your default agent or whatever agent you want can take back over the conversation. Note: You can set that up with prompt, and use AI supervisor settings to set rules including the Bias/Stickiness and Agent Intents.
To review the data you collected, open the “Debug mode” while you are still in Preview.
See the variables collected in the screenshot below…
You can also head to the “Inbox” tab, find the test conversation session, then open “Debug view”.
You can export the data you collected across all chat sessions by going to the “Inbox” tab, then clicking the “Export” button. In the subsequent dropdown, select “Collected Data”.
