Causal & Impact Analysis
Causal & impact analysis runs causal-intelligence over the engagement's data to help you explore not just what the numbers are, but what drives them and what would move them. It lives in the engagement's Analysis workspace.
Who can access
Members of the engagement team.
How it works
Where a baseline or KPI tells you the current state, causal analysis explores relationships and impact — surfacing likely drivers and the effect of changing them. Findings from causal runs can be promoted into insights that feed Execute and ultimately Deliver.
Step by step
- Open Analysis → Causal & impact in the engagement.
- Start a causal run over the engagement's data.
- Review the results — explore the drivers and impacts surfaced.
- Promote insights worth carrying into Execute.
Best practices
- Ground it in good data. Causal exploration is only as reliable as the underlying data — connect and enrich sources first.
- Use it to prioritize, then verify. Treat causal findings as hypotheses to pressure-test, not final conclusions, before they reach a client.
Common errors
| Symptom | Likely cause | What to do |
|---|---|---|
| Run produces little | Sparse or disconnected data | Connect and enrich data in Data & Evidence |
| Run is still going | Causal runs are background jobs | Leave it running and return; results persist on the engagement |