> ## 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

# Disputes

> Agents dispute an AI score in Ringg Analytics; a QA re-scores the call, and the QA's score becomes the official score everywhere, with a full history.

A dispute lets an agent challenge the AI's score on one of their calls: they pick the parameters they think the AI got wrong and say why. A QA then re-scores the whole call, and once they resolve the dispute, the QA's score replaces the AI's as the call's official score.

Disputes live in [Ringg Analytics](https://analytics.ringg.ai), a separate product from the Ringg AI dashboard. In the app a dispute is called an **appeal**: agents click **Appeal this score**.

## How a dispute works

```mermaid theme={null}
flowchart LR
  A[AI scores the call] --> B[Agent appeals within the window]
  B --> C[Waiting for review]
  C --> D[QA claims it: in review]
  D --> E[QA resolves: final score]
  E --> F[Optional correction later]
```

| Status | Meaning | Who acts next |
| - | - | - |
| **Submitted** | Waiting for a QA ("Waiting for a QA to pick it up.") | Any QA, with **Start review** |
| **In review** | A QA has claimed it; other QAs see who has it | That QA resolves it, or releases it back to the queue |
| **Resolved** | The QA's score is the call's official score | A QA can still [correct](/analytics-platform/disputes/results-and-corrections#corrections) it |

Each dispute also has a **QA target**: the submission time plus the workspace's **QA turnaround target**. An open dispute past it shows **Overdue**.

## Who does what

| Role | Can |
| - | - |
| Agent | [Raise a dispute](/analytics-platform/disputes/raise-a-dispute) on their own calls and follow it to the result |
| Team lead | Follow their team's disputes and receive every dispute email in CC |
| QA | [Review](/analytics-platform/disputes/review-a-dispute) and resolve disputes, and correct resolved ones |
| Owner, admin | Everything a QA can, plus hand a dispute to another QA, and turn disputes on and set the deadlines in [Settings](/analytics-platform/disputes/settings-and-reports) |

Nobody reviews their own dispute: a QA who also takes calls can't claim or resolve an appeal on their own call.

## Rules

* **Calls only.** Emails and meetings can't be disputed.
* **Once per call.** An agent can appeal each call once, and can't edit the appeal after submitting it.
* **Inside the window.** The window starts when the AI scores the call and lasts the **Appeal window** set by an admin, in calendar days (default 3).
* **The whole call is re-scored.** The QA rates every parameter, not only the disputed ones, against the rubric as it was when the agent appealed. Weights and fatal rules are the same as the AI's.
* **No re-scoring while open.** A call with an open dispute can't be sent back through the AI. After it is resolved, reprocessing changes only the AI score shown next to it.

## Where the official score shows

Once a dispute is resolved, the QA's score is used everywhere a score appears: **Interactions** (marked with a scale icon), **Summary**, **Agents**, [report cards](/analytics-platform/coach-agents/report-cards), [notification](/analytics-platform/set-up/notifications) conditions and exports. The AI's original score stays visible on the call for comparison.

## Next steps

> **[Raise a dispute](/analytics-platform/disputes/raise-a-dispute)**
>
> Agents: appeal a score.

> **[Review a dispute](/analytics-platform/disputes/review-a-dispute)**
>
> QAs: claim, re-score and resolve.

> **[Settings and reports](/analytics-platform/disputes/settings-and-reports)**
>
> Admins: windows, deadlines and the dispute report.


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