🔥 DeepEval 4.0 just got released. Read the announcement.

DeepEval 5-min Quickstart

This quickstart takes you from installing DeepEval to your first passing eval in a few minutes. You'll create a small test case, choose a metric, and run it with deepeval test run.

By the end of this quickstart, you should be able to:

  • Run your first local eval with a test case, metric, and deepeval test run.
  • Add tracing when you want to evaluate an AI agent or its internal components.
  • Know where to go next for datasets, synthetic data, integrations, and the Confident AI platform.

New to DeepEval? Checkout the introduction to learn more about this framework.

Installation

In a newly created virtual environment, run:

pip install -U deepeval

deepeval runs evaluations locally on your environment. To keep your testing reports in a centralized place on the cloud, use Confident AI, an AI quality platform with observability, evals, and monitoring that DeepEval integrates with natively:

deepeval login
Configure Environment Variables

DeepEval autoloads environment files (at import time)

  • Precedence: existing process env -> .env.local -> .env
  • Opt-out: set DEEPEVAL_DISABLE_DOTENV=1

More information on env settings can be found here.

# quickstart
cp .env.example .env.local
# then edit .env.local (ignored by git)

Create Your First Test Run

Create a test file to run your first end-to-end evaluation.

An LLM test case in deepeval represents a single unit of LLM app interaction, and contains mandatory fields such as the input and actual_output (LLM generated output), and optional ones like expected_output.

LLM Test Case

Run touch test_example.py in your terminal and paste in the following code:

test_example.py
from deepeval import assert_test
from deepeval.test_case import LLMTestCase, SingleTurnParams
from deepeval.metrics import GEval

def test_correctness():
    correctness_metric = GEval(
        name="Correctness",
        criteria="Determine if the 'actual output' is correct based on the 'expected output'.",
        evaluation_params=[SingleTurnParams.ACTUAL_OUTPUT, SingleTurnParams.EXPECTED_OUTPUT],
        threshold=0.5
    )
    test_case = LLMTestCase(
        input="I have a persistent cough and fever. Should I be worried?",
        # Replace this with the actual output from your LLM application
        actual_output="A persistent cough and fever could be a viral infection or something more serious. See a doctor if symptoms worsen or don't improve in a few days.",
        expected_output="A persistent cough and fever could indicate a range of illnesses, from a mild viral infection to more serious conditions like pneumonia or COVID-19. You should seek medical attention if your symptoms worsen, persist for more than a few days, or are accompanied by difficulty breathing, chest pain, or other concerning signs."
    )
    assert_test(test_case, [correctness_metric])

Then, run deepeval test run from the root directory of your project to evaluate your LLM app end-to-end:

deepeval test run test_example.py

Congratulations! Your test case should have passed ✅ Let's breakdown what happened.

  • The variable input mimics a user input, and actual_output is a placeholder for what your application's supposed to output based on this input.
  • The variable expected_output represents the ideal answer for a given input, and GEval is a research-backed metric provided by deepeval for you to evaluate your LLM output's on any custom metric with human-like accuracy.
  • In this example, the metric criteria is correctness of the actual_output based on the provided expected_output, but not all metrics require an expected_output.
  • All metric scores range from 0 - 1, which the threshold=0.5 threshold ultimately determines if your test have passed or not.

If you run more than one test run, you will be able to catch regressions by comparing test cases side-by-side. This is also made easier if you're using deepeval alongside Confident AI (see below for video demo).

A conversational test case in deepeval represents a multi-turn interaction with your LLM app, and contains information such as the actual conversation that took place in the format of turns, and optionally the scenario of which a conversation happened.

Conversational Test Case

Run touch test_example.py in your terminal and paste in the following code:

test_example.py
from deepeval import assert_test
from deepeval.test_case import Turn, ConversationalTestCase
from deepeval.metrics import ConversationalGEval

def test_professionalism():
    professionalism_metric = ConversationalGEval(
        name="Professionalism",
        criteria="Determine whether the assistant has acted professionally based on the content.",
        threshold=0.5
    )
    test_case = ConversationalTestCase(
        turns=[
            Turn(role="user", content="What is DeepEval?"),
            Turn(role="assistant", content="DeepEval is an open-source LLM eval package.")
        ]
    )
    assert_test(test_case, [professionalism_metric])

Then, run deepeval test run from the root directory of your project to evaluate your LLM app end-to-end:

deepeval test run test_example.py

🎉 Congratulations! Your test case should have passed ✅ Let's breakdown what happened.

  • The variable role distinguishes between the end user and your LLM application, and content contains either the user’s input or the LLM’s output.
  • In this example, the criteria metric evaluates the professionalism of the sequence of content.
  • All metric scores range from 0 - 1, which the threshold=0.5 threshold ultimately determines if your test have passed or not.

If you run more than one test run, you will be able to catch regressions by comparing test cases side-by-side. This is also made easier if you're using deepeval alongside Confident AI (see below for video demo).

Save Results

It is recommended that you push your test runs to Confident AI — an AI quality platform deepeval integrates with natively for observability, evals, and monitoring.

Confident AI is an AI quality platform with observability, evals, and monitoring that deepeval integrates with natively, and helps you build the best LLM evals pipeline. Run deepeval view to view your newly ran test run on the platform:

deepeval view

The deepeval view command requires that the test run that you ran above has been successfully cached locally. If something errors, simply run a new test run after logging in with deepeval login:

deepeval login

After you've pasted in your API key, Confident AI will generate testing reports and automate regression testing whenever you run a test run to evaluate your LLM application inside any environment, at any scale, anywhere.

Watch Full Guide on Confident AI

Once you've run more than one test run, you'll be able to use the regression testing page shown near the end of the video. Green rows indicate that your LLM has shown improvement on specific test cases, whereas red rows highlight areas of regression.

Simply set the DEEPEVAL_RESULTS_FOLDER environment variable to your relative path of choice.

# linux
export DEEPEVAL_RESULTS_FOLDER="./data"

# or windows
set DEEPEVAL_RESULTS_FOLDER=.\data

Evals With LLM Tracing

While end-to-end evals treat your LLM app as a black-box, you also evaluate individual components within your LLM app through LLM tracing. This is the recommended way to evaluate AI agents.

component level evals

First, create a small dataset to evaluate against:

from deepeval.dataset import EvaluationDataset, Golden

dataset = EvaluationDataset(goldens=[Golden(input="Why is the sky blue?")])

Pick your stack below, paste the snippet, and run it. Every integration ships an Async sample (the default — runs goldens concurrently) and a Sync sample (one golden at a time, useful for debugging or rate-limited providers):

Decorate your agent and any inner functions you want to grade with @observe. Pass metrics=[...] to the inner @observe and register its test case via update_current_span(...) to score that component on every run:

main.py
import asyncio
from deepeval.tracing import observe, update_current_span, update_current_trace
from deepeval.test_case import LLMTestCase
from deepeval.metrics import AnswerRelevancyMetric
...

@observe()
async def my_ai_agent(query: str) -> str:
    chunks = await retrieve(query)
    answer = await generate(query, chunks)
    update_current_trace(input=query, output=answer)
    return answer

@observe()
async def retrieve(query: str) -> list[str]:
    return ["..."]

@observe(metrics=[AnswerRelevancyMetric()])
async def generate(query: str, chunks: list[str]) -> str:
    response = "..."  # await your LLM call here with `query` and `chunks`
    update_current_span(
        test_case=LLMTestCase(input=query, actual_output=response, retrieval_context=chunks),
    )
    return response

for golden in dataset.evals_iterator():
    task = asyncio.create_task(my_ai_agent(golden.input))
    dataset.evaluate(task)
main.py
from deepeval.evaluate import AsyncConfig
from deepeval.tracing import observe, update_current_span, update_current_trace
from deepeval.test_case import LLMTestCase
from deepeval.metrics import AnswerRelevancyMetric
...

@observe()
def my_ai_agent(query: str) -> str:
    chunks = retrieve(query)
    answer = generate(query, chunks)
    update_current_trace(input=query, output=answer)
    return answer

@observe()
def retrieve(query: str) -> list[str]:
    return ["..."]

@observe(metrics=[AnswerRelevancyMetric()])
def generate(query: str, chunks: list[str]) -> str:
    response = "..."  # call your LLM here with `query` and `chunks`
    update_current_span(
        test_case=LLMTestCase(input=query, actual_output=response, retrieval_context=chunks),
    )
    return response

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    my_ai_agent(golden.input)

Same pattern works on any @observe'd function (retrievers, tool wrappers, sub-agents).

Hook deepeval into LangChain by passing CallbackHandler() to invoke / ainvoke. Stage a metric with next_llm_span(metrics=[...]) and it'll land on the first LLM span the agent opens:

langchain_app.py
import asyncio
from langchain.agents import create_agent
from deepeval.tracing import next_llm_span
from deepeval.integrations.langchain import CallbackHandler
from deepeval.metrics import AnswerRelevancyMetric
...

def multiply(a: int, b: int) -> int:
    """Multiply two numbers."""
    return a * b

agent = create_agent(
    model="openai:gpt-4o-mini",
    tools=[multiply],
    system_prompt="Be concise.",
)

async def run_agent(prompt: str):
    with next_llm_span(metrics=[AnswerRelevancyMetric()]):
        return await agent.ainvoke(
            {"messages": [{"role": "user", "content": prompt}]},
            config={"callbacks": [CallbackHandler()]},
        )

for golden in dataset.evals_iterator():
    task = asyncio.create_task(run_agent(golden.input))
    dataset.evaluate(task)
langchain_app.py
from langchain.agents import create_agent
from deepeval.tracing import next_llm_span
from deepeval.evaluate import AsyncConfig
from deepeval.integrations.langchain import CallbackHandler
from deepeval.metrics import AnswerRelevancyMetric
...

def multiply(a: int, b: int) -> int:
    """Multiply two numbers."""
    return a * b

agent = create_agent(
    model="openai:gpt-4o-mini",
    tools=[multiply],
    system_prompt="Be concise.",
)

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    with next_llm_span(metrics=[AnswerRelevancyMetric()]):
        agent.invoke(
            {"messages": [{"role": "user", "content": golden.input}]},
            config={"callbacks": [CallbackHandler()]},
        )

Same CallbackHandler works against a compiled StateGraph. Wrap invoke / ainvoke with next_llm_span(metrics=[...]) to score the first LLM call the graph makes:

langgraph_app.py
import asyncio
from langchain.chat_models import init_chat_model
from langgraph.graph import StateGraph, MessagesState, START, END
from deepeval.tracing import next_llm_span
from deepeval.integrations.langchain import CallbackHandler
from deepeval.metrics import AnswerRelevancyMetric
...

llm = init_chat_model("openai:gpt-4o-mini")

async def chatbot(state: MessagesState):
    return {"messages": [await llm.ainvoke(state["messages"])]}

graph = (
    StateGraph(MessagesState)
    .add_node(chatbot)
    .add_edge(START, "chatbot")
    .add_edge("chatbot", END)
    .compile()
)

async def run_graph(prompt: str):
    with next_llm_span(metrics=[AnswerRelevancyMetric()]):
        return await graph.ainvoke(
            {"messages": [{"role": "user", "content": prompt}]},
            config={"callbacks": [CallbackHandler()]},
        )

for golden in dataset.evals_iterator():
    task = asyncio.create_task(run_graph(golden.input))
    dataset.evaluate(task)
langgraph_app.py
from langchain.chat_models import init_chat_model
from langgraph.graph import StateGraph, MessagesState, START, END
from deepeval.tracing import next_llm_span
from deepeval.evaluate import AsyncConfig
from deepeval.integrations.langchain import CallbackHandler
from deepeval.metrics import AnswerRelevancyMetric
...

llm = init_chat_model("openai:gpt-4o-mini")

def chatbot(state: MessagesState):
    return {"messages": [llm.invoke(state["messages"])]}

graph = (
    StateGraph(MessagesState)
    .add_node(chatbot)
    .add_edge(START, "chatbot")
    .add_edge("chatbot", END)
    .compile()
)

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    with next_llm_span(metrics=[AnswerRelevancyMetric()]):
        graph.invoke(
            {"messages": [{"role": "user", "content": golden.input}]},
            config={"callbacks": [CallbackHandler()]},
        )

Swap from openai import OpenAI for from deepeval.openai import OpenAI — every completion call now emits an LLM span. To score one, wrap it in with trace(llm_span_context=LlmSpanContext(metrics=[...]))::

openai_app.py
import asyncio
from deepeval.openai import AsyncOpenAI
from deepeval.tracing import trace, LlmSpanContext
from deepeval.metrics import AnswerRelevancyMetric
...

client = AsyncOpenAI()

async def call_openai(prompt: str):
    with trace(llm_span_context=LlmSpanContext(metrics=[AnswerRelevancyMetric()])):
        return await client.chat.completions.create(
            model="gpt-4o",
            messages=[{"role": "user", "content": prompt}],
        )

for golden in dataset.evals_iterator():
    task = asyncio.create_task(call_openai(golden.input))
    dataset.evaluate(task)
openai_app.py
from deepeval.openai import OpenAI
from deepeval.tracing import trace, LlmSpanContext
from deepeval.evaluate import AsyncConfig
from deepeval.metrics import AnswerRelevancyMetric
...

client = OpenAI()

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    with trace(llm_span_context=LlmSpanContext(metrics=[AnswerRelevancyMetric()])):
        client.chat.completions.create(
            model="gpt-4o",
            messages=[{"role": "user", "content": golden.input}],
        )

Pass DeepEvalInstrumentationSettings() to the Agent's instrument keyword. Stage a metric on the next emitted span via next_llm_span(...) (for an LLM call) or next_agent_span(...) (for the agent itself):

pydanticai_agent.py
import asyncio
from pydantic_ai import Agent
from deepeval.tracing import next_llm_span
from deepeval.integrations.pydantic_ai import DeepEvalInstrumentationSettings
from deepeval.metrics import AnswerRelevancyMetric
...

agent = Agent(
    "openai:gpt-4.1",
    system_prompt="Be concise.",
    instrument=DeepEvalInstrumentationSettings(),
)

async def run_agent(prompt: str):
    with next_llm_span(metrics=[AnswerRelevancyMetric()]):
        return await agent.run(prompt)

for golden in dataset.evals_iterator():
    task = asyncio.create_task(run_agent(golden.input))
    dataset.evaluate(task)
pydanticai_agent.py
from pydantic_ai import Agent
from deepeval.tracing import next_llm_span
from deepeval.evaluate import AsyncConfig
from deepeval.integrations.pydantic_ai import DeepEvalInstrumentationSettings
from deepeval.metrics import AnswerRelevancyMetric
...

agent = Agent(
    "openai:gpt-4.1",
    system_prompt="Be concise.",
    instrument=DeepEvalInstrumentationSettings(),
)

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    with next_llm_span(metrics=[AnswerRelevancyMetric()]):
        agent.run_sync(golden.input)

Run instrument_agentcore() once before constructing your agent (this also covers any Strands agents hosted inside AgentCore). Stage a metric for the next span with next_agent_span(...) or next_llm_span(...):

agentcore_agent.py
import asyncio
from strands import Agent
from deepeval.tracing import next_agent_span
from deepeval.integrations.agentcore import instrument_agentcore
from deepeval.metrics import TaskCompletionMetric
...

instrument_agentcore()

agent = Agent(model="amazon.nova-lite-v1:0")

async def run_agent(prompt: str):
    with next_agent_span(metrics=[TaskCompletionMetric()]):
        return await agent.invoke_async(prompt)

for golden in dataset.evals_iterator():
    task = asyncio.create_task(run_agent(golden.input))
    dataset.evaluate(task)
agentcore_agent.py
from strands import Agent
from deepeval.tracing import next_agent_span
from deepeval.evaluate import AsyncConfig
from deepeval.integrations.agentcore import instrument_agentcore
from deepeval.metrics import TaskCompletionMetric
...

instrument_agentcore()

agent = Agent(model="amazon.nova-lite-v1:0")

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    with next_agent_span(metrics=[TaskCompletionMetric()]):
        agent(golden.input)

Run instrument_strands() once at startup (skip this if you're on AgentCore — use that tab instead). next_agent_span(...) and next_llm_span(...) each stage a metric on the next span the agent emits:

strands_agent.py
import asyncio
from strands import Agent
from strands.models.openai import OpenAIModel
from deepeval.tracing import next_agent_span
from deepeval.integrations.strands import instrument_strands
from deepeval.metrics import TaskCompletionMetric
...

instrument_strands()

agent = Agent(
    model=OpenAIModel(model_id="gpt-4o-mini"),
    system_prompt="You are a helpful assistant.",
)

async def run_agent(prompt: str):
    with next_agent_span(metrics=[TaskCompletionMetric()]):
        return await agent.invoke_async(prompt)

for golden in dataset.evals_iterator():
    task = asyncio.create_task(run_agent(golden.input))
    dataset.evaluate(task)
strands_agent.py
from strands import Agent
from strands.models.openai import OpenAIModel
from deepeval.tracing import next_agent_span
from deepeval.evaluate import AsyncConfig
from deepeval.integrations.strands import instrument_strands
from deepeval.metrics import TaskCompletionMetric
...

instrument_strands()

agent = Agent(
    model=OpenAIModel(model_id="gpt-4o-mini"),
    system_prompt="You are a helpful assistant.",
)

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    with next_agent_span(metrics=[TaskCompletionMetric()]):
        agent(golden.input)

Same drop-in trick as the OpenAI tab — swap from anthropic import Anthropic for from deepeval.anthropic import Anthropic. Wrap the call in with trace(llm_span_context=LlmSpanContext(metrics=[...])): to grade its LLM span:

anthropic_app.py
import asyncio
from deepeval.anthropic import AsyncAnthropic
from deepeval.tracing import trace, LlmSpanContext
from deepeval.metrics import AnswerRelevancyMetric
...

client = AsyncAnthropic()

async def call_claude(prompt: str):
    with trace(llm_span_context=LlmSpanContext(metrics=[AnswerRelevancyMetric()])):
        return await client.messages.create(
            model="claude-sonnet-4-5",
            max_tokens=1024,
            messages=[{"role": "user", "content": prompt}],
        )

for golden in dataset.evals_iterator():
    task = asyncio.create_task(call_claude(golden.input))
    dataset.evaluate(task)
anthropic_app.py
from deepeval.anthropic import Anthropic
from deepeval.tracing import trace, LlmSpanContext
from deepeval.evaluate import AsyncConfig
from deepeval.metrics import AnswerRelevancyMetric
...

client = Anthropic()

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    with trace(llm_span_context=LlmSpanContext(metrics=[AnswerRelevancyMetric()])):
        client.messages.create(
            model="claude-sonnet-4-5",
            max_tokens=1024,
            messages=[{"role": "user", "content": golden.input}],
        )

Register deepeval's event handler against LlamaIndex's dispatcher, then wrap your agent call in with trace(agent_span_context=AgentSpanContext(metrics=[...])): (or use LlmSpanContext for an LLM-level metric). LlamaIndex's agent.run(...) is async-only, so the sync sample drives it through asyncio.run(...):

llamaindex_agent.py
import asyncio
from llama_index.llms.openai import OpenAI
from llama_index.core.agent import FunctionAgent
import llama_index.core.instrumentation as instrument
from deepeval.tracing import trace, AgentSpanContext
from deepeval.integrations.llama_index import instrument_llama_index
from deepeval.metrics import TaskCompletionMetric
...

instrument_llama_index(instrument.get_dispatcher())

def multiply(a: float, b: float) -> float:
    return a * b

agent = FunctionAgent(
    tools=[multiply],
    llm=OpenAI(model="gpt-4o-mini"),
    system_prompt="You are a helpful calculator.",
)

async def run_agent(prompt: str):
    with trace(agent_span_context=AgentSpanContext(metrics=[TaskCompletionMetric()])):
        return await agent.run(prompt)

for golden in dataset.evals_iterator():
    task = asyncio.create_task(run_agent(golden.input))
    dataset.evaluate(task)
llamaindex_agent.py
import asyncio
from llama_index.llms.openai import OpenAI
from llama_index.core.agent import FunctionAgent
import llama_index.core.instrumentation as instrument
from deepeval.tracing import trace, AgentSpanContext
from deepeval.evaluate import AsyncConfig
from deepeval.integrations.llama_index import instrument_llama_index
from deepeval.metrics import TaskCompletionMetric
...

instrument_llama_index(instrument.get_dispatcher())

def multiply(a: float, b: float) -> float:
    return a * b

agent = FunctionAgent(
    tools=[multiply],
    llm=OpenAI(model="gpt-4o-mini"),
    system_prompt="You are a helpful calculator.",
)

async def run_agent(prompt: str):
    with trace(agent_span_context=AgentSpanContext(metrics=[TaskCompletionMetric()])):
        return await agent.run(prompt)

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    asyncio.run(run_agent(golden.input))

Add DeepEvalTracingProcessor to the trace processors, then assemble your agent with deepeval's Agent and function_tool shims. Metrics attach directly: agent_metrics / llm_metrics on the Agent, plus a metrics=[...] kwarg on @function_tool for the tool span:

openai_agents_app.py
import asyncio
from agents import Runner, add_trace_processor
from deepeval.openai_agents import Agent, DeepEvalTracingProcessor, function_tool
from deepeval.metrics import TaskCompletionMetric, AnswerRelevancyMetric, GEval
from deepeval.test_case import LLMTestCaseParams
...

add_trace_processor(DeepEvalTracingProcessor())

@function_tool(metrics=[GEval(
    name="Helpful Weather Lookup",
    criteria="Output must be a clear weather summary for the requested city.",
    evaluation_params=[LLMTestCaseParams.INPUT, LLMTestCaseParams.ACTUAL_OUTPUT],
)])
def get_weather(city: str) -> str:
    return f"It's always sunny in {city}!"

agent = Agent(
    name="weather_agent",
    instructions="Answer weather questions concisely.",
    tools=[get_weather],
    agent_metrics=[TaskCompletionMetric()],
    llm_metrics=[AnswerRelevancyMetric()],
)

for golden in dataset.evals_iterator():
    task = asyncio.create_task(Runner.run(agent, golden.input))
    dataset.evaluate(task)
openai_agents_app.py
from agents import Runner, add_trace_processor
from deepeval.evaluate import AsyncConfig
from deepeval.openai_agents import Agent, DeepEvalTracingProcessor, function_tool
from deepeval.metrics import TaskCompletionMetric, AnswerRelevancyMetric, GEval
from deepeval.test_case import LLMTestCaseParams
...

add_trace_processor(DeepEvalTracingProcessor())

@function_tool(metrics=[GEval(
    name="Helpful Weather Lookup",
    criteria="Output must be a clear weather summary for the requested city.",
    evaluation_params=[LLMTestCaseParams.INPUT, LLMTestCaseParams.ACTUAL_OUTPUT],
)])
def get_weather(city: str) -> str:
    return f"It's always sunny in {city}!"

agent = Agent(
    name="weather_agent",
    instructions="Answer weather questions concisely.",
    tools=[get_weather],
    agent_metrics=[TaskCompletionMetric()],
    llm_metrics=[AnswerRelevancyMetric()],
)

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    Runner.run_sync(agent, golden.input)

agent_metrics apply on every run, including handoffs to sub-agents.

Run instrument_google_adk() once before building your LlmAgent, then stage metrics with next_agent_span(...) or next_llm_span(...). ADK only ships an async runner, so the sync sample uses asyncio.run(...):

google_adk_agent.py
import asyncio
from google.adk.agents import LlmAgent
from google.adk.runners import InMemoryRunner
from google.genai import types
from deepeval.tracing import next_agent_span
from deepeval.integrations.google_adk import instrument_google_adk
from deepeval.metrics import TaskCompletionMetric
...

instrument_google_adk()

agent = LlmAgent(model="gemini-2.0-flash", name="assistant", instruction="Be concise.")
runner = InMemoryRunner(agent=agent, app_name="deepeval-quickstart")

async def run_agent(prompt: str) -> str:
    session = await runner.session_service.create_session(
        app_name="deepeval-quickstart", user_id="demo-user",
    )
    message = types.Content(role="user", parts=[types.Part(text=prompt)])
    async for event in runner.run_async(
        user_id="demo-user", session_id=session.id, new_message=message,
    ):
        if event.is_final_response() and event.content:
            return "".join(part.text for part in event.content.parts if getattr(part, "text", None))
    return ""

async def run_with_metric(prompt: str) -> str:
    with next_agent_span(metrics=[TaskCompletionMetric()]):
        return await run_agent(prompt)

for golden in dataset.evals_iterator():
    task = asyncio.create_task(run_with_metric(golden.input))
    dataset.evaluate(task)
google_adk_agent.py
import asyncio
from google.adk.agents import LlmAgent
from google.adk.runners import InMemoryRunner
from google.genai import types
from deepeval.tracing import next_agent_span
from deepeval.evaluate import AsyncConfig
from deepeval.integrations.google_adk import instrument_google_adk
from deepeval.metrics import TaskCompletionMetric
...

instrument_google_adk()

agent = LlmAgent(model="gemini-2.0-flash", name="assistant", instruction="Be concise.")
runner = InMemoryRunner(agent=agent, app_name="deepeval-quickstart")

async def run_agent(prompt: str) -> str:
    session = await runner.session_service.create_session(
        app_name="deepeval-quickstart", user_id="demo-user",
    )
    message = types.Content(role="user", parts=[types.Part(text=prompt)])
    async for event in runner.run_async(
        user_id="demo-user", session_id=session.id, new_message=message,
    ):
        if event.is_final_response() and event.content:
            return "".join(part.text for part in event.content.parts if getattr(part, "text", None))
    return ""

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    with next_agent_span(metrics=[TaskCompletionMetric()]):
        asyncio.run(run_agent(golden.input))

Run instrument_crewai() once, then assemble your crew with deepeval's Crew, Agent, LLM, and @tool shims. Metrics attach in the obvious places: Agent → agent span, LLM → LLM span, @tool → tool span:

crewai_app.py
import asyncio
from crewai import Task
from deepeval.integrations.crewai import instrument_crewai, Crew, Agent
from deepeval.metrics import TaskCompletionMetric
...

instrument_crewai()

tutor = Agent(
    role="Math Tutor",
    goal="Answer math questions accurately and concisely.",
    backstory="An experienced tutor who explains simple math clearly.",
    metrics=[TaskCompletionMetric()],
)
answer_task = Task(
    description="{question}",
    expected_output="An accurate, concise answer.",
    agent=tutor,
)
crew = Crew(agents=[tutor], tasks=[answer_task])

for golden in dataset.evals_iterator():
    task = asyncio.create_task(crew.kickoff_async({"question": golden.input}))
    dataset.evaluate(task)
crewai_app.py
from crewai import Task
from deepeval.evaluate import AsyncConfig
from deepeval.integrations.crewai import instrument_crewai, Crew, Agent
from deepeval.metrics import TaskCompletionMetric
...

instrument_crewai()

tutor = Agent(
    role="Math Tutor",
    goal="Answer math questions accurately and concisely.",
    backstory="An experienced tutor who explains simple math clearly.",
    metrics=[TaskCompletionMetric()],
)
task = Task(
    description="{question}",
    expected_output="An accurate, concise answer.",
    agent=tutor,
)
crew = Crew(agents=[tutor], tasks=[task])

for golden in dataset.evals_iterator(async_config=AsyncConfig(run_async=False)):
    crew.kickoff({"question": golden.input})

Then run the file (python main.py, python langchain_app.py, etc.):

python main.py

🎉 Congratulations! Your eval should have run ✅ A quick recap of what happened:

  • evals_iterator() looped through your dataset, capturing one trace per golden.
  • Your integration's adapter (or @observe) created spans for the components inside the trace.
  • The metrics=[...] you attached to one of those spans scored it once the trace finished.
  • DeepEval aggregated everything into one test run.

For sub-agents, retriever scoring, span context customization, and more, see component-level evaluation.

DeepEval for Online Evals

When you do LLM tracing using deepeval, you can automatically run online evals to monitor traces, spans, and threads (conversations) in production.

You'll need to use Confident AI to provide the necessary backend infrastructure and dashboard for this.

Simply get an API key from Confident AI and set it in the CLI:

CONFIDENT_API_KEY="confident_us..."

Then add a "metric collection" to your trace:

from deepeval.tracing import observe, update_current_trace

@observe()
def ai_agent(input: str) -> str:
    output = "Your AI agent output"
    update_current_trace(metric_collection="My Online Evals",)
    return output

✅ Done. All invocations of your AI agent will now have online evals ran on it.

deepeval's LLM tracing implementation is non-instrusive, meaning it will not affect any part of your code.

Evals on traces are end-to-end evaluations, where a single LLM interaction is being evaluated.

Trace-Level Evals in Production

Spans make up a trace and evals on spans represents component-level evaluations, where individual components in your LLM app are being evaluated.

Span-Level Evals in Production

Threads are made up of one or more traces, and represents a multi-turn interaction to be evaluated.

Thread (conversation) Evals in Production

Next Steps

If your team needs shared reports, regression analysis, or production monitoring, DeepEval integrates natively with Confident AI.

FAQs

Full Example

You can find the full example here on our Github.

Comparisons

Previous Page

Vibe Coder 5-min Quickstart

Next Page

On this page

InstallationCreate Your First Test RunSave ResultsEvals With LLM TracingDeepEval for Online EvalsNext StepsFAQsFull Example