> For the complete documentation index, see [llms.txt](https://docs.graphlit.dev/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.graphlit.dev/api-guides/use-cases/conversations/conversation-multi-turn-with-context.md).

# Multi-Turn Conversation with Context

## User Intent

"How do I maintain context across multiple questions? Show me conversation memory."

## Operation

**SDK Method**: `promptConversation()` with conversation history\
**Use Case**: Contextual multi-turn Q\&A

***

## Code Example (TypeScript)

```typescript
import { Graphlit } from 'graphlit-client';

const graphlit = new Graphlit();

// Create conversation
const conversation = await graphlit.createConversation({
  name: "Multi-turn Q&A"
});

const conversationId = conversation.createConversation.id;

// Turn 1
const response1 = await graphlit.promptConversation({
  prompt: "What are the main features of Graphlit?",
  id: conversationId
});
console.log('Q1:', response1.message.message);

// Turn 2 - context maintained
const response2 = await graphlit.promptConversation({
  prompt: "How does it compare to competitors?",  // "it" refers to Graphlit
  id: conversationId
});
console.log('Q2:', response2.message.message);

// Turn 3 - further refinement
const response3 = await graphlit.promptConversation({
  prompt: "What pricing options are available?",
  id: conversationId
});
console.log('Q3:', response3.message.message);
```

***

## Key Features

**Context Preservation**: Conversation history maintained\
**Pronoun Resolution**: "it", "they" understood\
**Follow-up Questions**: Natural conversation flow\
**Memory**: Previous answers inform new responses

***