Write Scenarios in Code

Quick setup? Copy the scenarios prompt into your coding agent to add simulation tests automatically.

Scenarios in code run with the open-source Scenario SDK, inside your own test suite and CI. To run scenarios from the platform against your agent’s HTTP endpoint instead, with no test code, see Connect your agent.

This guide will walk you through the basic setup required to run your first simulation and see the results in LangWatch.

For more in-depth information and advanced use cases, please refer to the official scenario library documentation.

1. Installation

First, you need to install the scenario library in your project. Choose your language below.

Python

uv add langwatch-scenario

TypeScript

npm install @langwatch/scenario

2. Configure Environment Variables

We recommend creating a .env file in the root of your project to manage your environment variables.

.env

LANGWATCH_API_KEY="your-api-key"
LANGWATCH_ENDPOINT="https://app.langwatch.ai"

You can find your LANGWATCH_API_KEY in your LangWatch project settings.

3. Create a Basic Scenario

Here’s how to create and run a simple scenario to test an agent.

First, you need to create an agent adapter that implements your agent logic. For detailed information about agent integration patterns, see the agent integration guide.

Python

import pytest
import scenario
import litellm

# Configure the default model for simulations
scenario.configure(default_model="openai/gpt-5")

@pytest.mark.agent_test
@pytest.mark.asyncio
async def test_vegetarian_recipe_agent():
    # 1. Create your agent adapter
    class RecipeAgent(scenario.AgentAdapter):
        async def call(self, input: scenario.AgentInput) -> scenario.AgentReturnTypes:
            return vegetarian_recipe_agent(input.messages)

    # 2. Run the scenario
    result = await scenario.run(
        name="dinner recipe request",
        description="""
            It's saturday evening, the user is very hungry and tired,
            but have no money to order out, so they are looking for a recipe.
        """,
        agents=[
            RecipeAgent(),
            scenario.UserSimulatorAgent(),
            scenario.JudgeAgent(criteria=[
                "Agent should not ask more than two follow-up questions",
                "Agent should generate a recipe",
                "Recipe should include a list of ingredients",
                "Recipe should include step-by-step cooking instructions",
                "Recipe should be vegetarian and not include any sort of meat",
            ])
        ],
    )

    # 3. Assert the result
    assert result.success

# Example agent implementation using litellm
@scenario.cache()
def vegetarian_recipe_agent(messages) -> scenario.AgentReturnTypes:
    response = litellm.completion(
        model="openai/gpt-5",
        messages=[
            {
                "role": "system",
                "content": """
                    You are a vegetarian recipe agent.
                    Given the user request, ask AT MOST ONE follow-up question,
                    then provide a complete recipe. Keep your responses concise and focused.
                """,
            },
            *messages,
        ],
    )
    return response.choices[0].message

TypeScript

// weather.test.ts
import { describe, it, expect } from "vitest";
import { openai } from "@ai-sdk/openai";
import scenario, { type AgentAdapter, AgentRole } from "@langwatch/scenario";
import { generateText, tool } from "ai";
import { z } from "zod";

describe("Weather Agent", () => {
  it("should get the weather for a city", async () => {
    // 1. Define the tools your agent can use
    const getCurrentWeather = tool({
      description: "Get the current weather in a given city.",
      parameters: z.object({
        city: z.string().describe("The city to get the weather for."),
      }),
      execute: async ({ city }) => `The weather in ${city} is cloudy with a temperature of 24°C.`,
    });

    // 2. Create an adapter for your agent
    const weatherAgent: AgentAdapter = {
      role: AgentRole.AGENT,
      call: async (input) => {
        const response = await generateText({
          model: openai("gpt-5"),
          system: `You are a helpful assistant that may help the user with weather information.`,
          messages: input.messages,
          tools: { get_current_weather: getCurrentWeather },
        });

        if (response.toolCalls?.length) {
          // For simplicity, we'll just return the arguments of the first tool call
          const { toolName, args } = response.toolCalls[0];
          return {
            role: "tool",
            content: [{ type: "tool-result", toolName, result: args }],
          };
        }

        return response.text;
      },
    };

    // 3. Define and run your scenario
    const result = await scenario.run({
      name: "Checking the weather",
      description: "The user asks for the weather in a specific city, and the agent should use the weather tool to find it.",
      agents: [
        weatherAgent,
        scenario.userSimulatorAgent({ model: openai("gpt-5") }),
      ],
      script: [
        scenario.user("What's the weather like in Barcelona?"),
        scenario.agent(),
        // You can use inline assertions within your script
        (state) => {
          expect(state.hasToolCall("get_current_weather")).toBe(true);
        },
        scenario.succeed("Agent correctly used the weather tool."),
      ],
    });

    // 4. Assert the final result
    expect(result.success).toBe(true);
  });
});

Once you run this code, you will see a new scenario run appear under Agent Testing > Results in your LangWatch project.

4. Grouping Your Sets and Batches

While optional, we strongly recommend setting stable identifiers for your scenarios, sets, and batches for better organization and tracking in LangWatch.

• id: A unique and stable identifier for your scenario. If not provided, it’s often generated from the name, which can be brittle if you rename the test.
• setId: Groups related scenarios into a set. The set appears under Agent Testing > Results.
• batchId: Groups all scenarios that were run together in a single execution (e.g., a single CI job). You can use a CI environment variable like process.env.GITHUB_RUN_ID for this.

Python

import os

result = await scenario.run(
    id="vegetarian-recipe-scenario",
    name="dinner recipe request",
    description="Test that the agent can provide vegetarian recipes.",
    set_id="recipe-test-suite",
    batch_id=os.environ.get("GITHUB_RUN_ID", "local-run"),
    agents=[
        RecipeAgent(),
        scenario.UserSimulatorAgent(),
        scenario.JudgeAgent(criteria=[
            "Agent should generate a recipe",
            "Recipe should be vegetarian",
        ])
    ]
)

TypeScript

const result = await scenario.run({
    id: "weather-check-scenario",
    name: "Checking the weather",
    description: "Test that the agent can check weather using tools.",
    setId: "weather-test-suite",
    batchId: process.env.GITHUB_RUN_ID ?? "local-run",
    agents: [
        weatherAgent,
        scenario.userSimulatorAgent({ model: openai("gpt-5") }),
    ],
    script: [
        scenario.user("What's the weather like in Barcelona?"),
        scenario.agent(),
        (state) => {
            expect(state.hasToolCall("get_current_weather")).toBe(true);
        },
        scenario.succeed("Agent correctly used the weather tool."),
    ],
});

5. Let the Judge Read Your Traces

When your adapter calls an agent that runs as a separate service, the judge cannot see what happens inside it. Turn on trace fetching and the judge also reads the traces your agent reports to LangWatch, one per conversation turn, before its verdict:

Python

scenario.configure(
    default_model="openai/gpt-5",
    fetch_remote_traces=True,
    trace_wait_timeout=60.0,  # seconds to wait for traces before the verdict
)

TypeScript

const result = await scenario.run({
  // ...
  fetchRemoteTraces: true,
  traceWaitTimeoutMs: 60_000,
});

Spread input.propagation_headers (Python) or input.propagationHeaders (TypeScript) onto your adapter’s outgoing HTTP request, so the remote service joins each turn’s trace. Linking your traces covers the mechanism, the wait behavior, and how to write trace-aware criteria.