# Run and read a GA4 audience export

> Tier: recipe. Operating recipe: real tool sequence, core rules, known traps.

Audience exports created, polled and read, with their diagnostics.

**Intent.** The audience's actual membership, exported and quantified.

## When to use

- Activation pipelines.
- Sizing an audience precisely.

## When not to use

- No specific contraindication beyond the preconditions below.

## Sources

Required: Google Analytics 4

## Preconditions

- The account is ticked in the dashboard, confirmed via list_accounts.

## Inputs

- `window`: Analysis window. Default: last 30 days.

## Procedure

1. Check export diagnostics and list existing exports. — tools: `ga4_get_audience_export_diagnostics`, `ga4_list_audience_exports`
2. Query the export. — tools: `ga4_query_audience_export`

## Decision rules

- **When** Export size diverges far from the UI estimate → **conclude** Estimates are modelled, exports are counted: the export is the number to ship.

## Evidence requirements

- Every figure carries its account, metric and window.
- Anything below a readable sample size is reported as unjudged, not as zero.

## Human approval boundary

- The readout changes nothing. Any change it motivates goes through Safe Writes: preview, human confirmation, then apply.

## Failure modes

- Exports are snapshots: date them, they do not update themselves.

## Output

- **Readout**: The figures, with windows and accounts named.
- **Flags**: What deserves a deeper skill or a human decision.