> For the complete documentation index, see [llms.txt](https://boundaryai.gitbook.io/boundaryai-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://boundaryai.gitbook.io/boundaryai-docs/analysing-your-feedback/reports.md).

# Reports

A **report** turns the analysis of a feedback group into a polished, shareable document: an executive summary, the themes and grouped themes, sentiment, Custom Monitoring results, and NPS, all in one place. Reports are ideal for stakeholders who do not log into BAI Analytics day to day.

Reports are **scoped to a feedback group**, so a single report can summarise everything across that group's surveys, uploads, connectors, and agents, or you can narrow it to specific sources, themes, or a time range.

***

## What's in a report

* An executive summary of the period
* Headline themes and grouped themes, with representative quotes
* A sentiment breakdown and trend
* Monitor activity: counts by category, with sample comments
* NPS and other quantitative charts, where present

Reports and the date ranges you pick for them (last month, last quarter, a custom range) filter by when the feedback actually happened, not by when it was analysed, so a report for "last month" reflects last month's experience even if some of it was only analysed afterwards.

***

## Creating a report

{% stepper %}
{% step %}

### Open the feedback group

Go to the feedback group you want to report on and find the **Reports** panel.
{% endstep %}

{% step %}

### Choose what to include

Pick the sources, themes, and time range to cover, and which sections to show.
{% endstep %}

{% step %}

### Generate or schedule

Generate the report now, or set it to run on a schedule and email itself to your recipients.
{% endstep %}
{% endstepper %}

***

## Scheduling recurring reports

You can schedule a report to run **daily, weekly, monthly, or on a custom interval** and have it emailed automatically to a list of recipients. This is the easiest way to give stakeholders a regular readout without anyone assembling it by hand.

The next scheduled run is shown on the feedback group's page, so you always know when the next report will land.

{% hint style="info" %}
Tracking feedback in periods (weeks, months, quarters)? A period-close subscription emails a report automatically whenever a tracked period ends, instead of on a fixed calendar schedule. See [Subscribing to period reports](/boundaryai-docs/analysing-your-feedback/tracking-feedback-over-time-evolution.md#subscribing-to-period-reports).
{% endhint %}

***

## Branding your reports

Every generated report can carry your own logo instead of the standard mark:

* **Upload a logo** in any report dialog (survey PDF, feedback-group report, theme or monitor PDF, scheduled reports). An upload applies to that one report only.
* **Save as default** stores the logo for you in this organisation, so every future report picks it up automatically with no re-upload.
* Add an optional **second logo** to co-brand a deliverable: the two marks render side by side.

Per logo slot, the report uses this report's upload if there is one, otherwise your saved default, otherwise the standard mark, so with nothing configured, reports look exactly as before.

***

## Per-source PDFs for review platforms

Any single source can also be exported as its own PDF from its analysis page. For review-platform sources (Google Reviews, Trustpilot, TripAdvisor, Avis Vérifiés) that PDF uses a dedicated template: the cover carries the platform's identity, a star-rating summary, and a health score, and three review-specific pages can be toggled in the customization dialog:

* **Ratings & trend**: average rating, a 5-to-1 star histogram, and how volume and rating moved vs the previous period.
* **Reviews to answer**: the period's 1-2 star reviews, newest first. The operational to-do list.
* **Customer voices**: representative quotes grouped as what to keep, what to watch, and what to improve.

***

## Exporting the underlying data

Alongside the polished report, you can export the **Raw Data** behind a theme or monitor straight to Excel. A **Columns to include** picker lets you choose exactly which fields to bring along, the comment text, sub-theme or sub-category, sentiment, and any of that source's own respondent-metadata fields, so a multi-source export can mix in each source's relevant metadata rather than a fixed set of columns.

***

## Formats

Reports can be exported as **PDF**, **HTML**, or **JSON**: PDF for sharing, HTML for embedding, and JSON for feeding the results into another system.

{% hint style="info" %}
Reports inherit the group's structure, so as your feedback grows the same report keeps working. There is no need to rebuild it each cycle.
{% endhint %}

For the groups that reports summarise, see [Feedback Groups](/boundaryai-docs/feedback-groups/feedback-groups.md). For the signals a report can highlight, see [Custom Monitoring](/boundaryai-docs/analysing-your-feedback/custom-monitoring.md).