> For the complete documentation index, see [llms.txt](https://docs.omics.ai/products/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.omics.ai/products/workbench/variant-interpreter/reviewing-variants.md).

# Reviewing variants

The Variant Interpreter organizes findings by variant type, each on its own tab, because each type is called by a different method and evaluated with different evidence. Use the page that matches what you're reviewing:

* [Search across all variant types](/products/workbench/variant-interpreter/reviewing-variants/search.md)
* [Small variants (SNVs & indels)](/products/workbench/variant-interpreter/reviewing-variants/small-variants.md)
* [Haplotype phase (cis/trans)](/products/workbench/variant-interpreter/reviewing-variants/haplotype-phase.md)
* [Structural variants](/products/workbench/variant-interpreter/reviewing-variants/structural-variants.md)
* [Copy number](/products/workbench/variant-interpreter/reviewing-variants/copy-number.md)
* [Tandem repeats](/products/workbench/variant-interpreter/reviewing-variants/tandem-repeats.md)
* [Paralogs](/products/workbench/variant-interpreter/reviewing-variants/paralogs.md)
* [Methylation & imprinting](/products/workbench/variant-interpreter/reviewing-variants/methylation-imprinting.md)

## The tab bar

An open analysis shows these tabs, in order:

1. **Summary**: priority findings and run quality. See [The Summary tab](/products/workbench/variant-interpreter/getting-started/the-summary-tab.md).
2. **Search**: find variants of every type in the genes you name. See [Search](/products/workbench/variant-interpreter/reviewing-variants/search.md).
3. One tab per variant type in the case, for example **Small Variant**, **Structural Variant**, **Tandem Repeat**, **Copy Number Variant**, **Paralog**, and **Methylation**. Only the types present in the case appear.
4. **Report**: see [Generating a report](/products/workbench/variant-interpreter/generating-a-report.md).

Each variant tab carries a blue badge counting its priority-finding calls. The badge counts individual calls, while the Summary tab groups related calls into one finding, so the badge can be higher than the number of findings for that type on the Summary tab.

## Working with a variant table

Every variant tab shares the same pattern: a filtered variant list, with visualizations where the type benefits from them, and a detail view (the variant drawer) where you explore the affected gene, review its [annotation panels](/products/workbench/variant-interpreter/reviewing-variants/annotation-panels.md), open the [genome browser (IGV)](/products/workbench/variant-interpreter/reviewing-variants/genome-browser.md), and [classify](/products/workbench/variant-interpreter/classifying-variants.md) the variant. Classifying a variant makes it eligible for the [report](/products/workbench/variant-interpreter/generating-a-report.md).

The toolbar above each table offers:

* **Filters**: opens the filter drawer. A badge shows how many filters are active. See [Filtering & prioritization](/products/workbench/variant-interpreter/filtering-and-prioritization.md).
* **Columns**: choose which columns are shown and in what order.
* **Quick search** (**Search ID, gene, coordinate, tag…**): narrows the rows already loaded in the table. To search the whole case, use the [Search tab](/products/workbench/variant-interpreter/reviewing-variants/search.md).
* **Download**: downloads the rows you've selected. Select at least one variant first.
* **Sample**: opens the sample drawer, with the proband's details, phenotype, pedigree, and run metadata.

Some tabs add their own quick filters to the toolbar, such as **Clinically Relevant** on Tandem Repeats and Paralogs, or **Type** and **Min size** on Copy Number.

### Classification columns

The **User Classification** and **Automated Classification** columns show each classification as a coloured ACMG chip. Click a chip to filter the table to that classification.

Sorting either column orders rows by clinical severity, with Pathogenic first, rather than alphabetically. If a table has too many rows to sort by user classification, you'll be asked to narrow your filters first.

Most numeric and score columns can be sorted as well. Columns that hold several values per row, such as per-transcript annotations, and free-text columns can't be sorted.

{% hint style="info" %}
Across every variant type, the workflow has already applied a population-frequency filter so that common variants are removed before you review. How that filter is set is described in [Filtering & prioritization](/products/workbench/variant-interpreter/filtering-and-prioritization.md).
{% endhint %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.omics.ai/products/workbench/variant-interpreter/reviewing-variants.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.