The Semantic Layer is where you describe what your data means in business terms, mark the assets your team can trust, and set the rules Knowi should follow when it interprets a question. It is the governed context that sits between your raw data and the people (and AI) asking questions of it.
Two audiences rely on it:
The Semantic Layer supplements your assets; it never changes them. Source field names, query definitions, native descriptions, and data all stay exactly as they are. Everything you add here (descriptions, business terms, certification, interpretation rules) is layered on top and can be edited or removed independently.
Open Data > Semantic.

The Semantic tab sits alongside Queries, Data Sources, Widgets, Dashboards, and Documents, and it has three views:
| View | What it is for | Who can use it |
|---|---|---|
| Glossary | Define the business terms and synonyms people use, and map them to the datasets and fields that carry that meaning. | Admins create and edit terms; everyone can view. |
| Catalog | See every asset you can access, its semantic setup, and its certification status in one place, and open any asset to configure it. | Everyone (scoped to assets you can access). |
| Global Settings | Set account-wide value aliases and interpretation guidance that apply across datasets. | Admins only. |
You do not have to start in the Semantic tab. An asset's Semantic Details can be opened from wherever you are working, which is covered in Semantic Details below.
The Glossary is your shared business vocabulary. It maps the language people actually use ("customer", "bookings", "MRR") to the datasets and fields that hold that data, so a question phrased in business terms resolves correctly. It replaces account-wide field synonyms: rather than one-off synonym lists, you define a canonical term once and attach every accepted alias to it.
Open Data > Semantic > Glossary to see every term, its definition, whether it is Global or Dataset scoped, and when it was last modified. Admins select New Term to add one, or open an existing term to edit it.

A term has four parts:
| Field | Description |
|---|---|
| Name / C9QL | The plain-English phrase, or a Cloud9QL function, you want to give a shared meaning, for example Customer. |
| Definition | What the term means to your organization. Select Suggest to have AI draft a definition; it appears in the field for you to review and edit before saving, and is never saved automatically. |
| Aliases | Every other phrase people use for the same meaning, for example Client or Buyer. Type an alias and press Enter to add it. |
| Dataset mappings | The datasets, and optionally the specific fields, that carry this meaning. Choose one or more datasets; leaving the fields empty maps the whole dataset. |
Global vs Dataset terms. A Global term applies across your account. A Dataset term is scoped to one dataset and shows its source dataset in the editor. If the same word has more than one applicable meaning, Knowi surfaces the ambiguity rather than silently picking one.
To map a Cloud9QL expression or a calculation rather than a plain field, use the dataset's Synonyms in Question Interpretation instead of a glossary mapping.
The Catalog is the inventory view. It lists every asset you can access with its semantic setup and certification side by side, so you can tell at a glance what is documented and what is trusted. Open Data > Semantic > Catalog.

| Column | Meaning |
|---|---|
| Asset | The asset name and description. |
| Type | Dataset, Data source, Widget, or Dashboard. |
| Semantic setup | Set up when the asset has saved semantic details, or Not set up when it does not. |
| Certification | Certified or Not certified. |
Narrow the list with the asset-type filter, the Only certified toggle, or the search box. Select a row, or its Semantic setup or Certification status, to open that asset's Semantic Details. Large catalogs load the first 500 matching assets; use the filter or search to narrow the list.
Semantic Details is the panel where you describe and certify a single asset. The panel is identical no matter where you open it, so the experience is consistent across every asset type. You can reach it from:

Until you save anything, the panel notes that "Semantic details have not been saved yet." The sections below are the building blocks. Which ones appear depends on the asset type, summarized in What You Configure by Asset Type.
Certification marks a specific asset as reviewed and trusted. It is a human judgment, independent of AI: its purpose is to show, across the company, what has been vetted, so people can answer "has someone reviewed this, and can we reuse it?" With certification permission you switch an asset between Not certified and Certified; one authorized reviewer is enough.


This section is the plain-language explanation of what the asset is and when to use it.

Datasets have an additional section that defines the language and rules Knowi uses when it interprets natural language questions about that dataset. This is where a dataset's AI and NLP interpretation settings live (they are managed here rather than on a separate settings page). Data processing and indexing controls remain under AI Processing.

This read-only section shows how the asset relates to others. Automatic native connections (a widget using a dataset, a dashboard containing widgets) are listed separately from Governed data relationships, which capture explicit meaning such as joins, rollups, derivations, drill-through paths, lookups, and replacements. Select View full lineage to open the complete dependency graph.

The panel adapts to the asset, so the sections you see differ by type:
| Asset type | Certification | Description | Business terms | Question interpretation | Connected assets |
|---|---|---|---|---|---|
| Widget | Yes | Native description shown, plus additional semantic context | No | No | Yes (lineage) |
| Data source | Yes | Written here | Yes | No | Yes |
| Dataset | Yes | Written here | Yes | Yes (synonyms, primary date, AI instructions) and per-field display names | Yes |
| Dashboard | Yes | Native description shown, plus additional semantic context | No | No | Yes |
A few notes that follow from this:
Global Settings holds account-wide interpretation rules and is available to Admins.
California to CA. Select up to 10 account-wide sources. They apply across any dataset whose fields match a column in the reference dataset; a dataset with no matching field is skipped.
For rules that apply to a single dataset rather than the whole account, use Dataset AI instructions in that dataset's Question Interpretation.
The AI that drafts descriptions, glossary definitions, and business term suggestions is the Semantic AI model. Choose it under Settings > User Settings > AI Settings > AI Models. Until you set one, Semantic AI uses the AI Agents model. Every suggestion stays in the form for you to review; nothing is saved or published automatically.
The Semantic Layer is also available through the MCP Server, so connected AI tools and scripts can work with it programmatically. You can list and read glossary terms, create and map terms, publish them, set dataset-level semantics (synonyms, primary date, and dataset AI instructions), and resolve or explain how a question maps to assets - the same operations as the UI, subject to the same permissions. See Semantic Layer Tools for the full list.
| Action | Requires |
|---|---|
| Create and edit glossary terms; change Global Settings | Admin |
| Edit an asset's semantic details | Semantic edit access, plus native edit access to the asset |
| Certify or revoke certification | Semantic certification access, plus native edit access to the asset |
| View semantic details and certification | Access to the asset |
Permissions are enforced before an asset is shown and again before its details or data are used, so the Semantic Layer never surfaces an asset a user could not otherwise access.
When you ask a question, the Semantic Layer is the trusted context Agentic BI resolves against before it answers or builds anything:
CA).Because the Semantic Layer is the source of truth for this business metadata, it can be reviewed and governed independently while your assets keep their native names, definitions, and data throughout.