> ## Documentation Index
> Fetch the complete documentation index at: https://docs.e6data.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Pin a semantic layer and configure the project

> Bind the project to a built semantic-layer version, then set the query source, response format, tools, connectors and action policies.

export const DocMeta = ({type, applies, owner}) => {
  const LABELS = {
    tutorial: "Tutorial",
    "how-to": "How-to guide",
    explanation: "Explanation",
    reference: "Reference"
  };
  return <div className="e6-meta">
      <span className={type === "how-to" || type === "tutorial" ? "e6-eyebrow" : "e6-eyebrow e6-eyebrow--quiet"}>{LABELS[type] || type}</span>
      {applies ? <span>Applies to: {applies}</span> : null}
      {owner ? <span>Owner: {owner}</span> : null}
    </div>;
};

<DocMeta type="how-to" applies="All deployments" />

## Pin the semantic layer

1. Open the project and go to **Settings**.
2. Select the semantic layer.
3. Select the exact built version.
4. Save the binding.

Until a built version is pinned, the UI sends you back to setup. A later semantic-layer build doesn't change the project until you pin the new version.

## Optional settings

| Setting | What it controls |
| - | - |
| Query source | Built-in semantic layer, or external Cube with the `cube_load` or `cube_sql` policy and optional e6data fallback |
| Response format | Customer-defined structured fields for chat answers. See [Structure chat answers](/agentflow/ask/structured-answers). |
| Agent Tools and skills | Project extensions used by chat and workflows. See [Custom tools](/agentflow/extend/custom-tools) and [Custom skills](/agentflow/extend/custom-skills). |
| Connectors | Slack, GitHub, GreptimeDB or MCP, where enabled. See [Connectors](/agentflow/extend/connectors). |
| Action policies | Email or Slack approvers, reminders, escalation and exhaust behavior. See [Actions and approvals](/agentflow/automate/actions-and-approvals). |

The project is now ready for chat, workflows and metrics.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.