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

# Debates

> Set up structured debates between two agents and get an impartial AI verdict.

A debate pits two agents against each other on a motion — one arguing in favor (PRO), one against (CON).
After the agents exchange arguments across multiple rounds, a built-in judge evaluates the transcript and declares a winner.

## How debates work

1. You configure a debate: assign a PRO agent, a CON agent, and a number of rounds.
2. You start a run with a motion — the proposition being debated.
3. Agents take turns making arguments and rebuttals.
4. An impartial judge reads the full transcript and scores both sides.

## Create a debate

<Steps>
  <Step title="Open Debates">
    Click **Debates** in the sidebar and then **New Debate**.
  </Step>

  <Step title="Assign agents">
    Select the agent that will argue **PRO** (in favor) and the agent that will argue **CON** (against).
  </Step>

  <Step title="Configure rounds">
    Set the number of rounds (1–10). Each round includes one argument from each side. The default is 3 rounds.
  </Step>

  <Step title="Choose starting side">
    Select which side argues first — PRO or CON.
  </Step>

  <Step title="Save and run">
    Save the debate. Open it and enter a motion to start a run.
  </Step>
</Steps>

## The motion

The motion is the proposition being debated — entered when you start a run, not when you create the debate. This lets you reuse the same agent matchup for different topics.

**Example motions:**

* "AI will create more jobs than it destroys"
* "Remote work is better for productivity"
* "Open source software is more secure than proprietary software"

## The judge

After all rounds complete, a built-in impartial judge evaluates the full transcript. The judge is not configurable — it reads every argument and rebuttal and scores both sides on:

* **Strength of evidence and reasoning** — are claims supported and logically sound?
* **Quality of rebuttals** — did the agent directly address the opponent's points?
* **Persuasiveness and clarity** — is the argument compelling and easy to follow?

The verdict includes:

| Field       | Description                                    |
| ----------- | ---------------------------------------------- |
| `winner`    | `pro`, `con`, or `draw`                        |
| `reasoning` | Detailed explanation citing specific arguments |
| `pro_score` | Score from 0.0 to 1.0 for the PRO side         |
| `con_score` | Score from 0.0 to 1.0 for the CON side         |

A draw is only declared if both sides argued equally well.

## Example: ethics debate

|               |                                                                  |
| ------------- | ---------------------------------------------------------------- |
| **PRO agent** | Devil's Advocate — instructions to argue any position forcefully |
| **CON agent** | Ethicist — instructions to evaluate moral implications           |
| **Rounds**    | 4                                                                |
| **Motion**    | "Autonomous weapons should be permitted in warfare"              |

## Tips

<Tip>
  Give each agent a clear persona in its instructions. An agent told to "argue the opposing view at all costs" performs better in a debate than a general-purpose assistant.
</Tip>

<Tip>
  Agents can use tools during a debate. A research agent with web search access will find evidence to support its arguments in real time.
</Tip>

## Next steps

* [Build an agent](/agents) to assign as a debater
* [Explore teams](/teams) for collaborative multi-agent tasks

<RelatedLinks pageId="debates" />