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

# Agents Conversations

> Learn how to initiate and manage conversations with Pawa AI agents, including context handling, multi-agent routing, and configurable parameters for generating intelligent responses.

Agents in Pawa AI can engage in rich, multi-turn conversations with users.\
Each conversation request includes the current user message, optional prior chat history, routing details, and generation parameters.

Conversations support:

* **Context memory** — preserve prior messages for coherent dialogue.
* **Routing** — use orchestration agents (e.g., a `RouterAgent`) to direct queries to specialized agents.
* **Custom instructions** — guide the agent’s reasoning and behavior.
* **Fine-tuned control** — adjust randomness, response length, and penalties for repetition.

***

## Agent Request Schema Example

| Field               | Type    | Description                                                                             |
| ------------------- | ------- | --------------------------------------------------------------------------------------- |
| `name`              | string  | Name of the agent handling the conversation.                                            |
| `description`       | string  | A brief description of the agent’s purpose.                                             |
| `instruction`       | string  | Behavioral guidance for the agent.                                                      |
| `intents`           | array   | Optional: predefined conversational styles or goals (e.g., “Be gentle”, “Be detailed”). |
| `model`             | string  | Model powering the conversation (e.g., `pawa-v1-blaze-20250318`).                       |
| `message`           | object  | The latest message from the user.                                                       |
| `agents`            | array   | IDs of other agents available for orchestration or delegation.                          |
| `memoryChat`        | array   | Conversation history for context preservation.                                          |
| `temperature`       | number  | Controls randomness of responses (default: `0.1`).                                      |
| `top_p`             | number  | Nucleus sampling threshold (default: `0.95`).                                           |
| `max_tokens`        | number  | Maximum tokens to generate in response.                                                 |
| `frequency_penalty` | number  | Penalizes repeated phrases (default: `0.3`).                                            |
| `presence_penalty`  | number  | Encourages exploration of new topics (default: `0.3`).                                  |
| `seed`              | number  | Random seed for reproducibility.                                                        |
| `stream`            | boolean | Whether to stream the response (`true`) or return once complete (`false`).              |

***

## Example Agent Chat Request

```bash theme={null}
curl -X POST "https://api.pawa-ai.com/v1/agents/chat/request" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer PAWA_AI_API_KEY" \
  -d '{
  "name": "RouterAgent",
  "description": "An orchestration agent responsible for routing user queries to the most appropriate specialist agent. If a query doesn't match any specific agent, this agent will attempt to answer the question directly.",
  "instruction": "Your primary function is to analyze user queries and determine the best agent to handle them. If the query is unrelated to any known agents or requires general router knowledge, respond directly to the user with helpful information. Prioritize efficient routing and provide clear explanations when responding directly.",
  "intents": [
    "Be gentle",
    "Be detailed"
  ],
  "model": "pawa-v1-blaze-20250318",
  "message": {
    "role": "user",
    "content": [
      {
        "type": "text",
        "text": "What was the score of Yanga in CAF 2025?"
      }
    ]
  },
  "agents": [72],
  "memoryChat": [
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "Habari yako?"
        }
      ]
    },
    {
      "role": "assistant",
      "content": [
        {
          "type": "text",
          "text": "Nzuri sana, asante. Wewe je?"
        }
      ]
    }
  ],
  "temperature": 0.1,
  "top_p": 0.95,
  "max_tokens": 4096,
  "frequency_penalty": 0.3,
  "presence_penalty": 0.3,
  "seed": 2024,
  "stream": false
}'
```

You can send, multiple agents as list if you want to implement agents orchestration, agents collaboration etc.