Skip to main content
For questions with specific metrics and time ranges, the AI Analyst uses Standard Analysis — a streamlined workflow that quickly retrieves your data and generates insights.

​
When Standard Analysis Is Used

Standard Analysis handles specific questions — questions that can be answered with a single SQL query against your data.

​
Examples

What was our revenue last week?
Top 10 products by units sold this month
How many new customers in January?
What's our ROAS by channel for the past 30 days?
Show me daily orders for the past 2 weeks
Which campaigns had the best performance yesterday?
These questions share key characteristics:
  • Specific metrics (revenue, orders, customers, ROAS)
  • Clear time bounds (last week, this month, past 30 days)
  • Focused scope (one dimension or ranking)

​
How It Works

Standard Analysis follows a four-step pipeline:
1

Identify Tables

The AI determines which BigQuery tables contain the data you need. For an orders question, it routes to obt_orders; for campaign metrics, it uses rpt_ad_performance_daily.
2

Generate SQL

Using your question and the relevant table schemas, the AI writes a SQL query. This includes appropriate filters, aggregations, and ordering.
3

Execute Query

The query runs against your BigQuery warehouse. Results are validated and any data quality issues are flagged.
4

Generate Response

The AI creates a natural language summary, determines if a chart would be helpful, and packages everything into a Slack response.

​
What You’ll See

During Standard Analysis, the AI shows progress through each phase:
StatusWhat’s Happening
🔍 Understanding your questionClassifying the question type
📊 Identifying relevant tablesFinding the right data sources
✍️ Writing SQL queryGenerating the query
⚡ Executing queryRunning against BigQuery
📈 Generating chartCreating visualization (if applicable)
✅ Results readyResponse complete

​
Response Components

A Standard Analysis response includes:
ComponentDescription
SummaryNatural language answer to your question
Data TableThe actual numbers, limited for readability
ChartVisual representation (when appropriate)
SQL QueryThe exact query used (downloadable)
CSV ExportFull data export (downloadable)

​
Tips for Best Results

“Last 30 days” is clearer than “recently.” The AI handles relative dates well: “yesterday,” “last week,” “past quarter,” “YTD.”
“Revenue” is clearer than “sales.” “Orders” is clearer than “transactions.” Use terminology from your dashboards.
“Top 10 products by revenue” gives a focused answer. “Best products” is ambiguous and may trigger Deep Analysis.
“What was revenue and how did AOV change?” works better as two separate questions. Keep each query focused.

​
When to Use Standard vs. Deep Analysis

Standard AnalysisDeep Analysis
What was revenue last week?How can we improve revenue?
Top 10 campaigns by ROASWhy is our marketing underperforming?
New customer count by monthWhat customer trends should we focus on?
AOV by channelHow should we optimize our channel mix?
If you phrase a question specifically, it stays in Standard Analysis. “What was our Meta ROAS last month?” is faster than “How is Meta performing?”

Deep Analysis

How open-ended questions trigger multi-perspective analysis.

Knowledge Retrieval

How definition and schema questions are handled.

​
Learn More About Your Data

Table Schemas

See what columns are available in each table.

Metrics Reference

Understand how each metric is calculated.