01
Investigate
Start with a business question, a chart, or the underlying data.
Insights
Answer business questions without rebuilding the data.
Start with the visual tools or Agent. Use SQL, Python, or notebooks when you need more control. Keep the analysis, chart, definitions, and final report connected.
Live chartsInspectable logicReports + presentations
Growth performance
Revenue by channel
Live model · refreshed 2m ago
ChartReport
Revenue
$284,910
+18.4%
ROAS
4.72×
+0.38
CAC
$41.20
−6.1%
MetaGoogleEmailOrganic
Sources and definitions attachedReport ready
One continuous workflow
From a question to an answer you can use again.
Foundry prepares the data and rules. Insights keeps the analysis, chart, and final report connected so the answer does not lose its context.
02
Model
Build reusable logic with visual tools, SQL, Python, or notebooks.
03
Visualise
Create live charts that retain their source, filters, and definitions.
04
Present
Turn the finding into a report or presentation-ready narrative.
Inside the workspace
Keep the result attached to its definitions.
A chart is easier to trust when people can see how attribution was counted, which dates it covers, when the data last updated, and what each number means.
Investigate with Agent
Same data. Logic shown.
Question
Which channels are growing revenue without increasing CAC?
SELECT
channel, revenue, cac,
revenue_growth_30d
FROM growth_performance
WHERE data_quality = 'passing'
Preview 100 rows
Foundry definitions applied
Work your way
Start visually. Ask the Agent. Open the code.
Choose the interface that fits the question and your level of control. Every method uses the same prepared data and can produce the same saved result.
Visual builder
Create common metrics, groups, and reports without starting from code.
SQL and Python
Write or refine logic directly when you need complete control.
Notebooks
Explore the same prepared, access-controlled data without exporting it to another tool.
Agent-assisted analysis
Ask a question in plain language and inspect the working behind the answer.
Scheduled models
Promote tested logic into recurring work with visible run history.
Machine learning
Build predictions and classifications, including supported BQML workflows.
Reusable output
Live when you need it. Polished when you share it.
Move from an active chart to a decision-ready report or presentation without rebuilding the numbers or losing the evidence behind them.
Weekly growth review
Live report · 6 sources
Executive summary
Revenue grew 18.4% while blended CAC fell 6.1%. Google and Email contributed the strongest efficient growth.
Recommended focus
Protect Email efficiency
Review Meta CAC
Test Google budget
Generated through the document integration
Live charts
Keep the visual connected to its model, filters, freshness, and shared metric definitions.
Decision-ready reports
Combine the finding, supporting evidence, context, and caveats in one reusable report.
Presentation-ready output
Create a polished narrative through the document integration without rebuilding the analysis.
Scenario planning
Compare spend and performance assumptions before committing budget or making a change.
From insight to action
Save the result where the business can use it.
Keep an answer as a live report, write it back as a calculated property, or send an approved output to a supported destination.
Customer properties
Scores, tiers, predictions, and calculated values.
Events and sessions
Channel groups, classifications, and attribution credit.
Accounts and tables
Reusable outputs for B2B reporting and shared analysis.
Destinations
Approved groups and properties sent to supported tools.
Starting points
Begin with a proven model.
Start from a common marketing model, then inspect and adapt its assumptions to your data rather than beginning from a blank page.
Multi-touch attribution
Compare methods and lookback windows against your own first-party data.
Predicted LTV
Estimate future customer value and make it available for reporting and groups.
Churn risk
Identify customers whose recent behavior resembles historical churn patterns.
Purchase propensity
Score purchase likelihood and create a reusable high-intent customer group.
FAQ