Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.sourcemedium.com/docs/llms.txt

Use this file to discover all available pages before exploring further.

The AI Analyst understands natural language questions about your e-commerce data. This page shows example questions organized by domain to help you get started.
Be specific about time ranges when possible. “Last 30 days” is clearer than “recently.”

​
Orders & Revenue

Questions about sales, order volume, and revenue metrics. 
What was our total revenue last month?
Show me daily revenue for the past 2 weeks
How many orders did we have yesterday?
What's our average order value this quarter vs last quarter?
Top 10 days by revenue in 2024
What was our revenue by channel last week?
How much did we discount last month?

​
Customers

Questions about customer acquisition, retention, and behavior. 
How many new customers did we acquire last month?
What's the split between new and repeat customers this year?
Show me new customer acquisition by week for the past 3 months
How many customers placed more than one order?
What's our repeat purchase rate?

​
Marketing & Ads

Questions about advertising performance and marketing spend. 
What was our ROAS by channel last month?
Show me ad spend by platform for the past 30 days
Which campaigns had the best ROAS last week?
What's our cost per acquisition by channel?
Top 10 campaigns by attributed revenue
How much did we spend on Meta ads in January?

​
Raw Data Pulls

Questions where you want the underlying rows or specific fields returned as a CSV. 
Pull order ID, order date, customer email, UTM source, UTM medium, and revenue for last week
Give me raw orders from yesterday with discount code, channel, and net revenue
Export customers acquired in March with email, first order date, and lifetime revenue
Show line items for SKU ABC-123 from the past 30 days
Pull campaign-level spend, clicks, impressions, and campaign name for TikTok last month
Raw data pulls work best when you name:
  • The time range
  • The fields or entity you want
  • Any filters, such as product, campaign, store, or channel
Use raw data pull wording when you want the data itself. If you want interpretation, ask an analysis question like “What are the trends in orders by UTM source?”

​
Email & SMS

Questions about outbound messaging performance. 
Top 10 email campaigns by attributed revenue last 30 days
What's our email open rate trend?
Which SMS campaigns drove the most orders?
Show me email performance by campaign type

​
Products

Questions about product performance and mix. 
Top 10 products by units sold this month
Which products have the highest revenue?
What's our best-selling product by channel?
Show me product performance for [specific SKU]

​
Cohorts & LTV

Questions about customer lifetime value and cohort behavior. 
What's the LTV of customers acquired in Q1?
Show me cohort retention by acquisition month
How does LTV vary by first purchase channel?

​
Definitions & Schema

Questions about what metrics mean, where data lives, and how SourceMedium works. These are answered using our documentation — no SQL required. 
What is LTV?
How do you calculate conversion rate?
What does ROAS mean?
Which table has order data?
What columns are in the orders table?
Where do I find email performance data?
How does attribution work?
What's the difference between first-click and last-click?
How do I set up UTM tracking?
What are the possible values for order_type?

​
Diagnostics

Health checks for your data and tracking. 
How is my data health?
Which tables are fresh?
Are my tables up to date?
How is my attribution health?
Why is so much traffic direct/none?

Learn about Diagnostics

Understand Data Health and Attribution Health checks in detail.

​
Thread follow-up examples

After you run analysis, you can continue in the same thread with prompts like: 
Break that down by channel.
Summarize the findings.
What should we do next?
  • In DM, ask these naturally.
  • In channels, mention the bot with @SourceMedium.

Thread continuity and follow-ups

Learn how follow-up context works and when to start a new thread.

​
Tips for Better Results

Instead of “recently” or “lately,” use specific ranges like “last 7 days,” “in January,” or “Q4 2024.”
“Revenue” is clearer than “sales.” “Orders” is clearer than “transactions.” Use the terminology from your dashboards.
Complex multi-part questions work better as separate queries. Ask “What was our revenue last month?” then “How does that compare to the previous month?”
“Pull order ID, date, UTM source, and revenue for last week” tells the AI Analyst to return rows and attach a CSV instead of writing an interpretive analysis.
“Top 10 products by revenue” is specific. “Best products” is ambiguous.