Read and use a semantic map

Use this guide to open the semantic map, identify clusters, and jump to the underlying project items.

What this page covers

Interpret clusters and relationships, then move through, search, and filter the semantic map.

When to use the semantic map

The semantic map becomes useful once a project has several sources and notes. A project with one or two items will produce a sparse map that shows little structure.

Use the map when a list of sources is no longer enough to understand what the project contains or what to read next.

Steps

1. Open the semantic map for the current project.
2. Wait for items to appear.
3. Read the cluster labels or groupings to identify themes.
4. Select individual items to open them.
5. Use angle controls to reposition the map around a different concept if that option is available.

Read clusters first

Start with the largest clusters. Ask what each one represents:

• A research topic or subfield
• A shared method or approach
• A group of notes built around the same question
• A set of sources with similar evidence types

After reading the clusters, look at outliers. Items at the edge of the map may be unique sources, underexplored directions, or material that does not belong in the project.

Open items from the map

The map is a navigation surface. Select an item in the map to open the underlying source, note, or chat. Read the actual content before citing, saving, or using the item in a question.

Use the map to make decisions

Good uses for the semantic map:

• Decide which sources to read next.
• Identify duplicate or overlapping sources.
• Find gaps in topic coverage.
• Group notes that belong together before writing a synthesis.
• Choose sources for a specific comparison question.

Use semantic map controls

Semantic map controls help you explore project-level patterns across sources, notes, chats, and concepts. Unlike a source-level knowledge map, a semantic map shows how project items relate to each other.

Core elements

Spatial interpretation

Items close together are semantically related in the current projection. Distance helps you inspect a cluster, but it does not prove that an item is important or that one item caused another.

Outliers can be useful. They may represent unrelated material, a unique method, a different domain, or a source that needs review.

Angle prompts

An angle prompt changes the lens for the map. For example, the same project can be projected around "methods", "limitations", "clinical relevance", or "commercial opportunity".

Use a concrete angle when the default map is too broad. Avoid vague angles like "interesting things" unless you are intentionally exploring.

Opening items

Selecting an item should move you from the visual overview to the underlying material. The map is most useful when it helps you decide what to read, compare, or ask about next.

Semantic map versus knowledge map

Reading caution

Generated clusters and labels can be useful but imperfect. Open the underlying items before using a cluster label as a research conclusion.