> ## Documentation Index
> Fetch the complete documentation index at: https://docs.surnex.io/llms.txt
> Use this file to discover all available pages before exploring further.

# GEO topics

> Snapshot history, cited sources, and raw AI responses for a single topic.

Click a topic on [GEO → Overview](/geo/overview) to open its detail view. This is where the numbers on the overview become explicable.

## Recent Snapshots

One row per snapshot, per domain:

| Column            | What it is                                   |
| ----------------- | -------------------------------------------- |
| **Date**          | When the snapshot ran                        |
| **Domain**        | The domain measured                          |
| **Mentions**      | Times the domain was mentioned in the answer |
| **Citation Rate** | Share of answers citing it as a source       |
| **AI Volume**     | How much the topic is queried in AI search   |
| **Model**         | The AI model that produced the response      |
| **Quality**       | A quality score for the response             |

Because snapshots accumulate daily by default, this table is the trend for the topic. Read down the **Mentions** and **Citation Rate** columns — a topic where both are climbing is one you're winning.

**Model** is worth watching. Citation behaviour shifts when a platform changes model, so a step change in your numbers that coincides with a new model name is a platform change, not something you did. Checking this column first will save you investigating the wrong thing.

**Quality** flags responses that were thin or off-topic. A low-quality response with zero mentions isn't evidence of a problem — the answer itself was poor.

## Cited sources

A second table lists the sources the AI drew on:

| Column       | What it is             |
| ------------ | ---------------------- |
| **Domain**   | The cited source       |
| **Title**    | The page title         |
| **Mentions** | How often it was cited |

This is the most directly actionable table in the GEO section. It names the sources the model treats as authoritative for your topic.

Look at what's there. If the same three industry publications or comparison sites recur across topics, being covered by them is worth more than another blog post on your own site — you're trying to influence what the model reads, not what it crawls from you.

If your own domain is absent while competitors appear, compare their cited page against yours. Usually the difference is directness: their page answers the question in the first paragraph.

## LLM Response Viewer

The full text of the AI response, with its **Cited Sources** listed beneath.

Read a few of these rather than only the metrics. The response shows *how* your brand is framed — recommended, mentioned in passing, or listed as an alternative to someone else. A mention that positions you as the second-choice option counts the same in the metrics as one that recommends you outright, and they're not the same result.

It also shows how the question was interpreted. AI answers frequently address a broader question than the topic as written, which tells you what content would actually be relevant.

## Using it

1. Read the **Recent Snapshots** trend — is the topic improving?
2. Check **Model** before attributing any change to your own work.
3. Read the **cited sources** — who owns this topic?
4. Read one or two **full responses** — how are you framed, and how is the question being read?
5. Act on the sources, not just your own pages.

## Related

* [GEO overview](/geo/overview) — managing topics and the schedule
* [AI competitors](/geo/competitors) — the same picture from the competitor side
* [Citation gap](/ai/citation-gap) — a systematic comparison across keywords and competitors