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

> ## Agent Instructions
> To search or read these docs, connect the Ringg docs MCP server at https://docs.ringg.ai/mcp (no key needed; tools search_ringg_ai and query_docs_filesystem_ringg_ai) instead of browsing pages one by one. Setup for each client: https://docs.ringg.ai/resources/mcp-server/docs-mcp-server/mcp-for-ai-assistants.md
> The dashboard labels agents "Assistants"; these docs say "agent". Both mean the same object, identified by agent_id.
> API base URL: https://prod-api.ringg.ai/ca/api/v0. Send the workspace API key in the X-API-KEY header, from server-side code only.
> Placing a call dials a real phone number and spends credits. Confirm the number with the user before calling.
> To act on a Ringg workspace (place calls, edit agents, read transcripts), use the separate Ringg workspace MCP server at https://mcp.ringg.ai/mcp: https://docs.ringg.ai/resources/mcp-server/workspace-mcp-server/overview.md

# Metrics

> Metrics hold the rubric Ringg Analytics scores calls against: one set per use case, with weighted parameters, rating scales and fatal rules.

A rubric is the list of parameters a call is scored on, grouped into categories, each with a weight. Each use case, such as EMI collections, has its own rubric per channel; every call is scored against the rubric of its use case.

In [Ringg Analytics](https://analytics.ringg.ai): **Sidebar → Metrics**. Everyone can read the metrics; only owners and admins change them.

![EMI collections use case with Quality metrics, Business metrics and Custom variables tabs, cards for 10 parameters, 100 total weight, 4 categories and 2 fatal rules, and the Call Opening category listing two Yes / No parameters of weight 5 with their descriptions](https://mintcdn.com/ringgai-0da73d20/CZ_hnbckkb2zP9lz/media/analytics-metrics/scorecard.webp?fit=max\&auto=format\&n=CZ_hnbckkb2zP9lz\&q=85\&s=c7a53c0e763801442220add9564fe370)

## Set up a rubric

**1. Create the use case**

On **Metrics**, click **New Use Case** and name it for the kind of call, for example "EMI collections".

**2. Add the parameters**

Open the use case. On **Quality metrics**, click **Add parameters** for one at a time, or **Import Sheet** to load a spreadsheet of them. **Edit Rubric** changes existing ones. Pick the channel the rubric applies to under **Channel**.

**3. Check the totals**

The cards at the top show the number of parameters, the **Total weight**, the categories and the **Fatal rules**.

> [!TIP]
>
> New calls in the use case are scored against the rubric. **Export** downloads it as a spreadsheet.

## Parameters

Each parameter has a category, a weight, a scale, and a description the AI follows when it rates a call. The call's score is the share of the total weight it earned, out of 100.

| Scale | Ratings | Points |
| - | - | - |
| Yes / No | Yes, No | Full or none |
| Yes / No / N/A | Yes, No, N/A | N/A leaves the parameter out of the score |
| Yes / Maybe / No | Yes, Maybe, No | Maybe earns half |
| 0 / 3 / 5 | 0, 3, 5 | A share of the weight |
| 0 to 5 | 0 to 5 | A share of the weight |

* **Fatal** parameters are the ones a call can't miss, such as verifying the customer's identity. Missing one sets the call's score to 0 and flags it **FATAL**.
* **Optional** parameters don't count toward the score.

**Business metrics** track outcomes such as a payment promise, and **Custom variables** declare values you send with each call; both are set per use case.

## Next steps

> **[Interactions](/analytics-platform/review-calls/interactions)**
>
> See a call's rating for each parameter.

> **[Notifications](/analytics-platform/set-up/notifications)**
>
> Alert agents on low scores or fatal misses.

> **[Report cards](/analytics-platform/coach-agents/report-cards)**
>
> Each agent's results per parameter.


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