Update app.py

app.py

@@ -729,6 +729,7 @@ CRITICAL RULES:
 12. **SCALAR VS VECTORIZED:** When applying a cleaning function to DataFrame columns, use `.apply()` for element-wise operations: `df['col'].apply(clean_func)`. Do NOT pass a Series to a function expecting a single value. For a single extracted value, use `.iloc[0]` to get the scalar before processing.
 13. **COLUMN AVAILABILITY AFTER MERGE:** After merging DataFrames, only columns explicitly included in the merge will be available. If you need 'city' later, include it in the initial selection: `df[['facility_name', 'city', 'latitude']]`. Before accessing any column, verify it exists in the DataFrame or was included in the merge.
 14. **BROADCASTING SCALAR TO ALL ROWS:** To add a single value to all rows in a DataFrame, do NOT use merge. Instead, extract the scalar first, then assign directly: `value = other_df.loc[condition, 'col'].iloc[0]; df['new_col'] = value`. This broadcasts the scalar to all rows.
+15. **EXTRACT OPERATIONAL PARAMETERS FROM DATA:** For capacity, rates, or throughput values, ALWAYS extract them directly from the data rather than assuming values. Print/log the extracted value to verify it matches expectations. For ranges like "8–10", use the LOWER bound for conservative estimates in capacity planning, not the midpoint or upper bound.
 
 --- USER'S SCENARIO ---
 {user_scenario}