CSM recommendation AI Agent
Customer Success teams lose hours each week manually reviewing account data, usage trends, and integration activity, often inconsistently across team members. This use case automates that process using DBSync's AI Agent in Cloud Workflow. It reads customer account data, runs it through a structured CSM framework powered by an LLM, and delivers actionable expansion recommendations directly to your inbox or CRM, in seconds.
Target audience
This use case is designed for the following groups:
Customer Success Managers (CSMs) who manage a portfolio of accounts and need quick, data-driven insights on each customer.
Revenue and Expansion teams looking to identify upsell or cross-sell opportunities based on integration usage and tech stack signals.
No coding or AI expertise is required.
What you build
By the end of this tutorial, you have a working Cloud Workflow flow that does the following:
Pulls customer account data, either from a variable or live from your CRM.
Sends it to an AI Agent.
Generates CSM recommendations using a structured framework.
Delivers the output to your email inbox or writes it back to your CRM.
Phase 1: Connect your LLM provider
To add an LLM provider connection, do the following:
In the navigation menu, click 
(Apps).
Search for your preferred LLM provider among ChatGPT, Azure OpenAI, Anthropic Claude, Google Gemini, and Amazon Bedrock. Then select it.
In the API Key field, enter your API key.
Click Save Connection.
Click Test Connection.
For detailed API key configuration, refer to API Key Guides.
If you plan to use a CRM (for example, Salesforce) as your source or target, configure the app as specified here.
Phase 2: Create a project and task
To create a new project and task, do the following:
On the platform dashboard, click Project.
Click Create.
Enter a name for the project.
Click Next.
In the Automation Tasks section, click Create.
Enter a name for the task.
Click the Select Integration Agent menu.
Select Integration Bot.
Click Configure. You are redirected to the Flow Builder page.
Phase 3: Configure the flow
To configure the flow, do the following:
Go to the Flow Builder page.
From the left panel, drag a Flow block onto the canvas.
On the Flow block, click Configure.
In the Description field, enter a name, such as AI Agent.
Ensure the Enable Flow option is selected.
Drag the Variable block under the Flow block onto the canvas. Name it Customer_Toon.
In the Variable block, drag and drop the relevant fields from the fx panel to populate Customer_Toon dynamically from your CRM.
Click Save.
Optional: If you want to pull live customer data, connect to your source CRM, such as Salesforce, at this stage.
Drag the Query block under the Flow block onto the canvas. For more information, see Query configuration.
Select the appropriate Object to retrieve the relevant customer information.
Drag the relevant fields from the fx panel to dynamically populate
Customer_Toonfrom your CRM.
Click Save.
Phase 4: Configure the AI Agent action
Drag an AI Agent block under the Variable block onto the Flow Builder canvas.
On the AI Agent block, click Configure.
In the LLM field, select the LLM configured in the Connect your LLM provider section.
In the Model field, select your preferred model.
Click Configure.
In the AI Agent field, enter the following prompt, and then press Enter.
In the Instructions field, copy and paste the prompt above if it does not match.
In the User Prompt field, replace the displayed text with the following prompt.
Customer_Toon is a dynamic variable pulled from the data stream. To insert the variable, drag Customer_Toon from the fx panel into the User Prompt field.
In the right-side panel, click 
(Settings).
Go to the Web Search section, and turn on the Web Search toggle.
To preview your output, click Preview.
Click Save & Close.
Click Save.
Phase 5: Add an output action
Drag the Email action block as a sibling of the AI Agent action block.
In the To field, enter the destination email address.
In the From field, enter the source email address.
In the Subject field, enter a relevant subject line.
In the Body field, drag AI Agent > content from the fx panel. The Body field should show {{AI_AGENT/content}}.
Click Save.
Optional: Write to a destination CRM. Instead of sending an email, you can push the AI Agent output directly into a destination system, such as Salesforce, by using a Transform and Write action, as shown in the following example.
Configure the Transform & Write block as required. For more information, see Transform & Write configuration. Ensure you map {{AI_AGENT/content}} to the field where you want to see the AI-generated content.
Verify that your flow matches the following structure:
Flow → (Optional: CRM Source) → Variable (Customer_Toon) → AI Agent Action → Email / Transform & Write.
Click 
(Run).
To monitor the execution in real time, open the Logs panel.
Check your CRM or email, based on the configuration above, for the AI-generated CSM recommendations.
Last updated