> ## Documentation Index > Fetch the complete documentation index at: https://docs.zelto.ai/llms.txt > Use this file to discover all available pages before exploring further. # Reports > A written analysis of your voice AI operation, requested on demand and authored in rich text. A **report** is a written analysis of your voice AI operation — the kind of thing a business analyst would put together in a real BPO. Where a [finding](/docs/findings) is the durable record of one recurring *problem* and a [solution](/docs/solutions) is the record of a *fix*, a report answers an open-ended *question* about how the operation is running: "Why did our conversion go up in May?", "How are we handling the after-hours scenario?", or "What's different between agent A and agent B in the A/B test?" Reports live under **Reports** in the sidebar, scoped to your organization (not to a single agent). ## Requesting a report Press **Request report** and describe what you want to understand: | Field | What it is | | ----------- | ---------------------------------------------------------------------------------------- | | **Title** | Short headline for the report (required, up to 255 characters). | | **Request** | Free-text description of what the report should cover (optional, up to 4000 characters). | The report is created immediately and opens to its own page. The body starts empty — you (or, later, an automated job) fill in the analysis. ## Generation status Every report carries a generation **status** shown as a badge on the list and detail pages: | Status | Meaning | | -------------------------- | -------------------------------------------------------------------------------------- | | **Waiting for generation** | The default. The report has been requested but the analysis hasn't been generated yet. | | **Generating** | The analysis is being produced. | | **Ready** | The analysis is complete. | | **Failed** | Generation didn't finish. | Automated, AI-generated reports are not available yet, so a requested report sits in **Waiting for generation**. You can write the analysis by hand in the editor in the meantime — the body is fully editable regardless of status. ## Creating and editing from chat or the API You don't have to use the **Request report** button. Ask Zelto in chat — "create a report titled … about …" — and it proposes the report for you to confirm before it's saved. The same actions are available to scripts and external agents over the [MCP server](/docs/mcp) as the `create_report` and `update_report` tools (with `list_reports` / `get_report` to find and read existing ones), so an automated workflow can file a report or update its title, request, body, or status programmatically. ## Anatomy of a report | Field | What it is | | ---------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | **Title** | The report's headline, editable inline from the detail page. | | **Request** | The original free-text ask, shown as a callout on the detail page. | | **Body** | Rich text (Tiptap / ProseMirror JSON) — the same editor as [findings](/docs/findings) and [solutions](/docs/solutions), with headings, lists, diagrams, `@`-mentions of agents, findings, calls, and more, **call examples** that embed any call's recording and annotated transcript excerpt inline, **images** you upload or link by URL (with alt text and a caption), and **data widgets** (see below) that chart live numbers from your data. The body autosaves as you type. | | **Status** | The generation status (see above). | | **Requested by** | The org member who requested the report. | ## Data widgets A **data widget** turns a report from a static write-up into a live dashboard. It runs a query against your analytics store and renders the result as a table or chart that re-runs every time the report is opened, so the numbers stay current as new [calls](/docs/conversations) come in. In the report editor, type `/` and choose **Data widget**, then fill in: | Field | What it is | | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------- | | **Title** | Optional headline shown in the widget header. | | **Query** | A read-only `SELECT` over your organization's analytics tables (conversations, transcripts, analyses, findings, agents, webhooks). | | **Show as** | **Table**, or a **Bar** / **Line** / **Area** / **Pie** chart. | | **Category column** | For charts, the result column used as the X axis. | | **Value column(s)** | For charts, the comma-separated numeric columns to plot. | Press **Run** to execute it. Use the refresh button in the widget header to re-run on demand, the pencil to change the query, and the chart/table toggle to switch views. Results are capped at the first 1,000 rows. Data widgets are read-only and **scoped to your organization**: every query is automatically restricted to your org's rows on the analytics tables, and only `SELECT` / `WITH` / `DESCRIBE` / `EXPLAIN` / `SHOW` statements are allowed — writes and cross-organization access are rejected. The same querying capability is available conversationally through Ask Zelto and over the [MCP server](/docs/mcp). ## Related * [Findings](/docs/findings) — the recurring problems a report often explains. * [Solutions](/docs/solutions) — the fixes that follow from what a report uncovers. * [Agents](/docs/agents) — the agents whose behavior a report analyzes.