> Fetch clean Markdown by appending `.md` to any page URL under https://signalwire.com/docs or requesting it with the HTTP header `Accept: text/markdown`. The root index at https://signalwire.com/docs/llms.txt lists the available documentation indexes.

# setPostPrompt

> Set the post-prompt used for generating call summaries after a conversation ends.

[on-summary]: /docs/server-sdks/reference/typescript/agents/agent-base/on-summary

[set-post-prompt-url]: /docs/server-sdks/reference/typescript/agents/agent-base/set-post-prompt-url

[ref-agentbase]: /docs/server-sdks/reference/typescript/agents/agent-base

Set the post-prompt text for summary generation. After a conversation ends, the AI
uses this prompt to analyze the conversation and generate a structured summary. The
summary is delivered to your [`onSummary()`][on-summary] callback or
the [`setPostPromptUrl()`][set-post-prompt-url] endpoint.

## **Parameters**

**`text`** `string` — required

Instructions for summary generation. Tell the AI what to extract from the
conversation -- for example, caller intent, resolution status, or action items.

---

## **Returns**

[`AgentBase`][ref-agentbase] -- Returns `this` for method chaining.

## **Example**

```typescript {5}
import { AgentBase } from '@signalwire/sdk';

const agent = new AgentBase({ name: 'support', route: '/support' });
agent.setPromptText('You are a customer support agent for Acme Corp.');
agent.setPostPrompt(`
Summarize this conversation as JSON with the following fields:
- caller_intent: What the caller wanted
- resolution: Whether their issue was resolved (yes/no/partial)
- action_items: List of follow-up actions needed
- sentiment: Overall caller sentiment (positive/neutral/negative)
`);
await agent.serve();
```

> Set the post-prompt used for generating call summaries after a conversation ends.