> For the complete documentation index, see [llms.txt](https://docs.datalogz.io/guides/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.datalogz.io/guides/semantic-intelligence/concept-details.md).

# Concept details

Concept details opens as a side panel from the scorecard, from a search, or from a direct link on the [Metric Explorer](https://docs.datalogz.io/guides/semantic-intelligence/metric-explorer.md) tab. The header shows the concept name, its status, and how many departments, definitions and data models it spans.

The panel has two views: **Definitions** and **Lineage**.

#### Definitions

The **Reference definition** card is shown first: its department, metric name, expression, a Certified tag if its semantic model is endorsed, and a link to the data model with its report count.

Every other metric in the concept follows as a card with:

* the department and metric name
* its label (Identical, Equivalent, Divergent or Conflicting)
* how structurally similar it is to the source definition, as a percentage
* its expression, with the lines that differ from the source definition highlighted
* a link to its data model in Inventory, and the number of reports that use it

Metrics that share the same definition are grouped together.

**To compare a definition with the source definition:**

1. Click **Show expanded expression** to see the expression with every referenced metric written out in full. Two metrics that look different on the surface often turn out to call the same base metrics, and the reverse happens too.
2. Click **Compare with source** to open a side-by-side diff of the expanded source definition and the selected metric.
3. Click the data model name to open the semantic model in Inventory and find its owner.

Use **Sort metrics by** to order the cards by **Structural similarity** (least similar first), **Department** or **Workspace**. Large concepts load in pages; click **Load more metrics** to see the rest.

#### Lineage

The Lineage view draws the concept as a graph: the data model and table each definition lives in, the metric itself, and the reports, visuals and dashboards that use it. Other definitions of the concept appear as dashed nodes, colored by status, so you can see which branch of the estate runs on a different version of the metric. Click a data model or report to open it in Inventory, or a metric to open it in the Metrics Catalog.

#### Why this answer?

Click **Why this answer?** to see how the concept was formed. The formation audit lists every candidate definition Control Tower considered, ranked by combined similarity, with the departments and metrics behind each one. A dashed line marks the membership threshold: candidates above it joined the concept, and candidates below it are shown struck through with the reason they were left out.

This is useful when a metric you expected is missing from a concept, or when a concept contains something you did not expect.


---

# 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.datalogz.io/guides/semantic-intelligence/concept-details.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.
