diff --git a/api/src/utils/prompts/generate_sql_prompts/sql_gen_prompt.rs b/api/src/utils/prompts/generate_sql_prompts/sql_gen_prompt.rs
index f03ed815d..5c9220dfc 100644
--- a/api/src/utils/prompts/generate_sql_prompts/sql_gen_prompt.rs
+++ b/api/src/utils/prompts/generate_sql_prompts/sql_gen_prompt.rs
@@ -29,6 +29,10 @@ Generate a **single** {} query based on the provided analysis plan.
 - Format output for the specified visualization type
 - Maintain consistent data structure across requests unless changes required
 - Use explicit ordering for custom buckets/categories
+- Use NULLIF to handle division by zero
+- Use COALESCE to handle NULL values
+- Use CASE statements for conditional logic
+
 
 # TIME AND NAMING CONVENTIONS
 - Default to last 1 year if no timeframe specified
diff --git a/api/src/utils/prompts/generate_sql_prompts/sql_gen_thought_prompt.rs b/api/src/utils/prompts/generate_sql_prompts/sql_gen_thought_prompt.rs
index 3a73a3063..a6be8f9e2 100644
--- a/api/src/utils/prompts/generate_sql_prompts/sql_gen_thought_prompt.rs
+++ b/api/src/utils/prompts/generate_sql_prompts/sql_gen_thought_prompt.rs
@@ -21,6 +21,8 @@ Your goal is to generate a plan for a SQL query that best answers the user's req
    - Working with available data (no assumptions about other tables)
    - Handling data quality issues (missing values, formatting)
    - Considering column descriptions and business context
+   - Make sure to coalesce data appropriately to avoid division by zero errors
+   - Use NULLIF to handle division by zero
 
 # OUTPUT FORMAT
 Provide your response as a numbered list: