Formatting rules:
• Use
for main sections
• Use for each recommendation
• Use bullet lists for structured content
• Use bold labels for fields
• Keep paragraphs short (1–2 sentences)
• Insert spacing using
where helpful
Avoid Markdown symbols such as:
##, **, -, or numbered Markdown lists.
--------------------------------------------------
OUTPUT STRUCTURE (MANDATORY)
The output must follow this order exactly:
1. Executive Recommendation Preview
2. CSM Discovery Questions
3. Recommendations
--------------------------------------------------
EXECUTIVE RECOMMENDATION PREVIEW
This section should function as a quick briefing for the CSM.
Include all suggested recommendations in this section.
MANDATORY
Include the Bold Bet recommendation in the list as well.
Format:
Executive Recommendation Preview
-
Expansion Theme: short operational improvement
Connector / Initiative: connector name
Why this fits this customer: one sentence
Primary business benefit: one sentence
Maximum 3–4 preview items.
--------------------------------------------------
CSM DISCOVERY QUESTIONS
Include two sections.
CSM Discovery Questions
Tech Stack Discovery Questions
Rules:
• Maximum 10 questions
• Non-technical
• Focus on systems, manual processes, reporting gaps
New Connector Discovery Questions
Rules:
• Maximum 10 questions
• Focus on business pain, data flow, visibility gaps
• Do not mention connectors
--------------------------------------------------
RECOMMENDATION STRUCTURE
Each recommendation must follow this structure:
Recommendation Title
Connector: connector name
Category: Operational efficiency / Reporting & visibility / Cross-team collaboration / Process scalability & governance / Finance & time tracking
Business problem: short explanation
Why this matters now: one concise sentence
Conversation-starter questions:
- question
- question
- question
Business value: 1–2 concise sentences
CSM talking points:
--------------------------------------------------
BREVITY RULES
• Prefer short sentences
• Avoid repeating the same explanation across sections
• Eliminate unnecessary narrative
• Focus on practical conversation guidance for CSMs
Generate the output in the following format. Wrap the HTML content so it is XML-parseable. Ensure every HTML tag is escaped properly so it parses as XML.
```
{% endprompt %}
{% endstep %}
{% step %}
In the **Instructions** field, copy and paste the prompt above if it does not match.
{% endstep %}
{% step %}
In the **User Prompt** field, replace the displayed text with the following prompt.
{% prompt description="" %}
```markdown
Customer Information
---------------------
{{$Customer_Toon}}
Use this information as the primary source of truth.
Analyze the customer context and generate recommendations using the DBSync CSM recommendation framework defined in the system instructions.
```
{% endprompt %}
{% hint style="info" %}
`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.
{% endhint %}
{% endstep %}
{% step %}
In the right-side panel, click 
(Settings).
{% endstep %}
{% step %}
Go to the **Web Search** section, and turn on the **Web Search** toggle.
{% endstep %}
{% step %}
To preview your output, click **Preview**.
{% endstep %}
{% step %}
Click **Save & Close**.
{% endstep %}
{% step %}
Click **Save**.
{% endstep %}
{% endstepper %}
***
### Phase 5: Add an output action
{% stepper %}
{% step %}
Drag the **Email** action block as a sibling of the **AI Agent** action block.
{% endstep %}
{% step %}
In the **To** field, enter the destination email address.
{% endstep %}
{% step %}
In the **From** field, enter the source email address.
{% endstep %}
{% step %}
In the **Subject** field, enter a relevant subject line.
{% endstep %}
{% step %}
In the **Body** field, drag **AI Agent > content** from the **fx** panel. The **Body** field should show `{{AI_AGENT/content}}`.
{% endstep %}
{% step %}
Click **Save**.
{% endstep %}
{% step %}
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](/cloud-workflow/create-your-workflow/actions/transform-and-write.md). Ensure you map `{{AI_AGENT/content}}` to the field where you want to see the AI-generated content.
{% endstep %}
{% step %}
Verify that your flow matches the following structure:\
**Flow** → (Optional: **CRM Source)** → **Variable** (`Customer_Toon`) → **AI Agent Action** → **Email / Transform & Write**.
{% endstep %}
{% step %}
Click 
(**Run**).
{% endstep %}
{% step %}
To monitor the execution in real time, open the **Logs** panel.
{% endstep %}
{% step %}
Check your CRM or email, based on the configuration above, for the AI-generated CSM recommendations.
{% endstep %}
{% endstepper %}