Vercel AI SDK Integration
Learn how to integrate Vercel AI SDK agents with the Scenario testing framework
Vercel AI SDK agents work seamlessly with Scenario through the AgentAdapter[py] interface. The SDK provides a unified interface for building AI applications with streaming, tool calling, and structured outputs across multiple providers.
Basic Integration Pattern
Given a Vercel AI SDK agent:
import { openai } from '@ai-sdk/openai';
import { generateText } from 'ai';
async function myAgent(prompt: string) {
const result = await generateText({
model: openai('gpt-4-turbo'),
messages: [
{
role: 'system',
content: 'You are a helpful AI assistant.',
},
{
role: 'user',
content: prompt,
},
],
});
return result;
}You can integrate it with Scenario like this:
import scenario, { type AgentAdapter } from '@langwatch/scenario';
const createMyAgentAdapter = (): AgentAdapter => {
return {
call: async (input) => {
const result = await myAgent(input.messages.at(-1)?.content);
return result.response.messages;
},
};
};Next Steps
- Explore Scenario Basics for advanced testing patterns
- Learn about Scripted Simulations for precise control
- Check out more Agent Integration patterns for other frameworks
