> 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/metric-explorer.md).

# Metric Explorer

Metric Explorer is the starting page of [Semantic Intelligence](https://docs.datalogz.io/guides/semantic-intelligence.md). It shows the state of metric definitions for the selected connector and team, and lets you open any concept for the full comparison.

To open it, go to **Semantic Intelligence** in the left navigation.

<figure><img src="https://1435452537-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FI51V8nP3ZjMKt2bCO9HR%2Fuploads%2FVMo8oLWBK2jLMJ3WQ6Jo%2FScreenshot%202026-10-26%20at%2015.28.32.png?alt=media&amp;token=d8870e35-fbb6-44d0-ae06-4a6dd10f0a73" alt=""><figcaption></figcaption></figure>

#### Search business concepts

Type a concept name in **Search business concepts**. Suggestions appear as you type, each with its status, its source definition, and how many similar, drifting and conflicting definitions it has. Select a suggestion, or press **Search** to open the best match.

**Explain this** gives a plain-English answer about the concept you searched for, generated by an LLM. It requires the Semantic Intelligence AI add-on and is off by default. Without the add-on, the button is shown but disabled.

#### Key figures

| Card                                 | What it shows                                                                                                                                                                                           |
| ------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Metrics Analyzed**                 | Metrics analyzed, across how many data models, and how many of them are pass-through.                                                                                                                   |
| **Business Concepts**                | Distinct business concepts found.                                                                                                                                                                       |
| **Single-definition Concepts**       | Concepts with one distinct definition, split into those with one metric and those where several metrics share the same definition.                                                                      |
| **Standardization (2+ definitions)** | Standardized concepts divided by all concepts with two or more distinct definitions. Single-definition concepts are left out, so this figure reflects only the concepts where disagreement is possible. |
| **Drifting Concepts**                | Concepts with at least one divergent definition, plus the number of conflicting concepts.                                                                                                               |

#### Standardization scorecard

The scorecard lists one row per business concept, with the most definitions first.

| Column               | Description                                                                        |
| -------------------- | ---------------------------------------------------------------------------------- |
| **Concept**          | The concept name, with a short summary of its least aligned definition underneath. |
| **Departments**      | Number of departments with a definition of this concept.                           |
| **Consumers**        | Reports built on the data models where this concept is defined.                    |
| **# of Definitions** | Number of distinct definitions in the concept.                                     |
| **Status**           | Standardized, Drifting, Conflicting or Single definition.                          |
| **Lineage**          | Opens the concept directly in its lineage view.                                    |

Sort or filter any column. Filtering **Status** on Conflicting and sorting by **Consumers** is a quick way to find the disagreements that reach the most reports.


---

# 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/metric-explorer.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.
