> ## 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

# Settings and reports

> Turn disputes on, set how long agents can appeal and how fast QAs should resolve, then track appeal and overturn rates to see where the AI is weakest.

Admins turn disputes on and set two deadlines for the workspace. The dispute report then shows how often agents appeal, how often QAs change the AI's rating, and which parameters the AI gets wrong most.

In [Ringg Analytics](https://analytics.ringg.ai): **Sidebar → Settings** for the settings, **Sidebar → Analytics** for the report.

## Settings

![Appeals settings card switched On, with Appeal window 3 calendar days and QA turnaround target 2 calendar days, and a Save button](https://mintcdn.com/ringgai-0da73d20/BhQtV3gvIrxE9J2L/media/disputes-settings/settings.webp?fit=max\&auto=format\&n=BhQtV3gvIrxE9J2L\&q=85\&s=af8bb3f074c82776114a54c42393ef27)

**1. Turn appeals on**

In the **Appeals** card, turn the switch **On**. Agents can't appeal while it is off.

**2. Set the deadlines**

Both are in calendar days, from 1 to 30:

| Setting | Default | Meaning |
| - | - | - |
| **Appeal window** | 3 | How long after the AI scores a call an agent can appeal it. A change applies to calls not yet appealed. |
| **QA turnaround target** | 2 | How soon a QA should resolve an appeal. Later ones are flagged **Overdue**. A change applies to new appeals. |

**3. Save**

> [!TIP]
>
> "Saved" shows next to the button.

Only owners and admins can open **Settings**. Whether a QA sees the AI's score while reviewing is set per QA on **Team** (see [QA settings](/analytics-platform/roles-and-access#qa-settings)).

## Dispute report

The **Disputed AI scores** section at the bottom of **Analytics** covers the period you pick. Owners, admins and QAs in full view can see it.

![Disputed AI scores section with Appeal rate 15%, Overturn rate 83%, Median turnaround 20.4 h, Closed on time 100% and Open now 3, the outcomes line, and Overturn rate by parameter listing four parameters with their disputed and overturned counts](https://mintcdn.com/ringgai-0da73d20/BhQtV3gvIrxE9J2L/media/disputes-settings/report.webp?fit=max\&auto=format\&n=BhQtV3gvIrxE9J2L\&q=85\&s=9c8c73743a102696c46f24dd4072f838)

| Figure | What it measures |
| - | - |
| **Appeal rate** | Scored calls in the period that were appealed |
| **Overturn rate** | Disputed parameters a QA changed, out of all disputed parameters |
| **Median turnaround** | Time from appeal to first resolution, with the time 90% were resolved within |
| **Closed on time** | Appeals resolved by their **QA target**, and how many were corrected later |
| **Open now** | Appeals waiting or in review, and how many are overdue |
| Outcomes | Appeals **Overturned**, **Partially overturned** and **AI score upheld**, the average score change, and how often QAs changed parameters nobody disputed |
| **Overturn rate by parameter** | For each parameter: how often it was disputed and how often the QA changed it. A high rate marks a parameter the AI gets wrong. |

**Open the queue** opens **Interactions** filtered to appeals waiting for review. **Export** downloads the appeals in the period as a spreadsheet, with one sheet for the appeals, one for every disputed parameter's result, and one for their history.

## Next steps

> **[Review a dispute](/analytics-platform/disputes/review-a-dispute)**
>
> Work through the queue.

> **[Metrics](/analytics-platform/set-up/metrics)**
>
> Sharpen the descriptions of parameters the AI gets wrong.

> **[Roles and access](/analytics-platform/roles-and-access)**
>
> Set each QA's review mode.


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