Langsmith Observability Agent Skill
LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.
Install
one command, takes just this skill from the repositorynpx skills add https://github.com/Orchestra-Research/AI-Research-SKILLs --skill langsmith-observabilityThe instruction itself
31 sections, as written by the authorLangSmith - LLM Observability Platform
Development platform for debugging, evaluating, and monitoring language models and AI applications.
When to use LangSmith
Use LangSmith when:
- Debugging LLM application issues (prompts, chains, agents)
- Evaluating model outputs systematically against datasets
- Monitoring production LLM systems
- Building regression testing for AI features
- Analyzing latency, token usage, and costs
- Collaborating on prompt engineering
Key features:
- Tracing: Capture inputs, outputs, latency for all LLM calls
- Evaluation: Systematic testing with built-in and custom evaluators
- Datasets: Create test sets from production traces or manually
- Monitoring: Track metrics, errors, and costs in production
- Integrations: Works with OpenAI, Anthropic, LangChain, LlamaIndex
Use alternatives instead:
- Weights & Biases: Deep learning experiment tracking, model training
- MLflow: General ML lifecycle, model registry focus
- Arize/WhyLabs: ML monitoring, data drift detection
Quick start
Installation
pip install langsmith
# Set environment variables
export LANGSMITH_API_KEY="your-api-key"
export LANGSMITH_TRACING=true
Basic tracing with @traceable
from langsmith import traceable
from openai import OpenAI
client = OpenAI()
@traceable
def generate_response(prompt: str) -> str:
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": prompt}]
)
return response.choices[0].message.content
# Automatically traced to LangSmith
result = generate_response("What is machine learning?")
OpenAI wrapper (automatic tracing)
from langsmith.wrappers import wrap_openai
from openai import OpenAI
# Wrap client for automatic tracing
client = wrap_openai(OpenAI())
# All calls automatically traced
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello!"}]
)
Core concepts
Runs and traces
A run is a single execution unit (LLM call, chain, tool). Runs form hierarchical traces showing the full execution flow.
from langsmith import traceable
@traceable(run_type="chain")
def process_query(query: str) -> str:
# Parent run
context = retrieve_context(query) # Child run
response = generate_answer(query, context) # Child run
return response
@traceable(run_type="retriever")
def retrieve_context(query: str) -> list:
return vector_store.search(query)
@traceable(run_type="llm")
def generate_answer(query: str, context: list) -> str:
return llm.invoke(f"Context: {context}\n\nQuestion: {query}")
Projects
Projects organize related runs. Set via environment or code:
import os
os.environ["LANGSMITH_PROJECT"] = "my-project"
# Or per-function
@traceable(project_name="my-project")
def my_function():
pass
Client API
from langsmith import Client
client = Client()
# List runs
runs = list(client.list_runs(
project_name="my-project",
filter='eq(status, "success")',
limit=100
))
# Get run details
run = client.read_run(run_id="...")
# Create feedback
client.create_feedback(
run_id="...",
key="correctness",
score=0.9,
comment="Good answer"
)
Datasets and evaluation
Create dataset
from langsmith import Client
client = Client()
# Create dataset
dataset = client.create_dataset("qa-test-set", description="QA evaluation")
# Add examples
client.create_examples(
inputs=[
{"question": "What is Python?"},
{"question": "What is ML?"}
],
outputs=[
{"answer": "A programming language"},
{"answer": "Machine learning"}
],
dataset_id=dataset.id
)
Run evaluation
from langsmith import evaluate
def my_model(inputs: dict) -> dict:
# Your model logic
return {"answer": generate_answer(inputs["question"])}
def correctness_evaluator(run, example):
prediction = run.outputs["answer"]
reference = example.outputs["answer"]
score = 1.0 if reference.lower() in prediction.lower() else 0.0
return {"key": "correctness", "score": score}
results = evaluate(
my_model,
data="qa-test-set",
evaluators=[correctness_evaluator],
experiment_prefix="v1"
)
print(f"Average score: {results.aggregate_metrics['correctness']}")
Built-in evaluators
from langsmith.evaluation import LangChainStringEvaluator
# Use LangChain evaluators
results = evaluate(
my_model,
data="qa-test-set",
evaluators=[
LangChainStringEvaluator("qa"),
LangChainStringEvaluator("cot_qa")
]
)
Advanced tracing
Tracing context
from langsmith import tracing_context
with tracing_context(
project_name="experiment-1",
tags=["production", "v2"],
metadata={"version": "2.0"}
):
# All traceable calls inherit context
result = my_function()
Manual runs
from langsmith import trace
with trace(
name="custom_operation",
run_type="tool",
inputs={"query": "test"}
) as run:
result = do_something()
run.end(outputs={"result": result})
Process inputs/outputs
def sanitize_inputs(inputs: dict) -> dict:
if "password" in inputs:
inputs["password"] = "***"
return inputs
@traceable(process_inputs=sanitize_inputs)
def login(username: str, password: str):
return authenticate(username, password)
Sampling
import os
os.environ["LANGSMITH_TRACING_SAMPLING_RATE"] = "0.1" # 10% sampling
LangChain integration
from langchain_openai import ChatOpenAI
from langchain_core.prompts import ChatPromptTemplate
# Tracing enabled automatically with LANGSMITH_TRACING=true
llm = ChatOpenAI(model="gpt-4o")
prompt = ChatPromptTemplate.from_messages([
("system", "You are a helpful assistant."),
("user", "{input}")
])
chain = prompt | llm
# All chain runs traced automatically
response = chain.invoke({"input": "Hello!"})
Production monitoring
Hub prompts
from langsmith import Client
client = Client()
# Pull prompt from hub
prompt = client.pull_prompt("my-org/qa-prompt")
# Use in application
result = prompt.invoke({"question": "What is AI?"})
Async client
from langsmith import AsyncClient
async def main():
client = AsyncClient()
runs = []
async for run in client.list_runs(project_name="my-project"):
runs.append(run)
return runs
Feedback collection
from langsmith import Client
client = Client()
# Collect user feedback
def record_feedback(run_id: str, user_rating: int, comment: str = None):
client.create_feedback(
run_id=run_id,
key="user_rating",
score=user_rating / 5.0, # Normalize to 0-1
comment=comment
)
# In your application
record_feedback(run_id="...", user_rating=4, comment="Helpful response")
Testing integration
Pytest integration
from langsmith import test
@test
def test_qa_accuracy():
result = my_qa_function("What is Python?")
assert "programming" in result.lower()
Evaluation in CI/CD
from langsmith import evaluate
def run_evaluation():
results = evaluate(
my_model,
data="regression-test-set",
evaluators=[accuracy_evaluator]
)
# Fail CI if accuracy drops
assert results.aggregate_metrics["accuracy"] >= 0.9, \
f"Accuracy {results.aggregate_metrics['accuracy']} below threshold"
Best practices
- Structured naming - Use consistent project/run naming conventions
- Add metadata - Include version, environment, user info
- Sample in production - Use sampling rate to control volume
- Create datasets - Build test sets from interesting production cases
- Automate evaluation - Run evaluations in CI/CD pipelines
- Monitor costs - Track token usage and latency trends
Common issues
Traces not appearing:
import os
# Ensure tracing is enabled
os.environ["LANGSMITH_TRACING"] = "true"
os.environ["LANGSMITH_API_KEY"] = "your-key"
# Verify connection
from langsmith import Client
client = Client()
print(client.list_projects()) # Should work
High latency from tracing:
# Enable background batching (default)
from langsmith import Client
client = Client(auto_batch_tracing=True)
# Or use sampling
os.environ["LANGSMITH_TRACING_SAMPLING_RATE"] = "0.1"
Large payloads:
# Hide sensitive/large fields
@traceable(
process_inputs=lambda x: {k: v for k, v in x.items() if k != "large_field"}
)
def my_function(data):
pass
References
- Advanced Usage - Custom evaluators, distributed tracing, hub prompts
- Troubleshooting - Common issues, debugging, performance
Resources
- Documentation: https://docs.smith.langchain.com
- Python SDK: https://github.com/langchain-ai/langsmith-sdk
- Web App: https://smith.langchain.com
- Version: 0.2.0+
- License: MIT
Other skills for the same job
different authors, same section of the catalogue
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Comprehensive healthcare AI toolkit for developing, testing, and deploying machine learning models with clinical data. This skill should be used when working with electronic health records (EHR), clinical prediction tasks (mortality, readmission, drug recommendation), medical coding systems (ICD, NDC, ATC), physiological signals (EEG, ECG), healthcare datasets (MIMIC-III/IV, eICU, OMOP), or implementing deep learning models for healthcare applications (RETAIN, SafeDrug, Transformer, GNN).
Expert performance engineer specializing in modern observability, application optimization, and scalable system performance. Masters OpenTelemetry, distributed tracing, load testing, multi-tier caching, Core Web Vitals, and performance monitoring. Handles end-to-end optimization, real user monitoring, and scalability patterns. Use PROACTIVELY for performance optimization, observability, or scalability challenges.
Master AI-powered test automation with modern frameworks, self-healing tests, and comprehensive quality engineering. Build scalable testing strategies with advanced CI/CD integration. Use PROACTIVELY for testing automation or quality assurance.
Internet Court adapter for GenLayer Intelligent Contract supervision. Use to specify agent-performance rubrics, evidence schemas, decision outputs, and ERC-7710 connector expectations, while delegating actual GenLayer contract writing, linting, testing, deployment, and CLI interaction to the official GenLayer skills at https://skills.genlayer.com/.
> Suggests using Microsoft Testing Platform (MTP) hot reload to iterate fixes on failing tests without rebuilding. Use when user says "hot reload tests", "iterate on test fix", "run tests without rebuilding", "speed up test loop", "fix test faster", or needs to set up MTP hot reload to rapidly iterate on test failures. Covers setup (NuGet package, environment variable, launchSettings.json) and the iterative workflow for fixing tests. normally with dotnet test (use run-tests), applying test filters, producing TRX reports, CI/CD pipeline configuration, or Visual Studio Test Explorer hot reload (which is a different feature).
Build production Apache Airflow DAGs with best practices for operators, sensors, testing, and deployment. Use when creating data pipelines, orchestrating workflows, or scheduling batch jobs.
Build production-grade Azure Cosmos DB NoSQL services following clean code, security best practices, and TDD principles.
How to use it
Take orchestra-research/langsmith-observability from the repository into ~/.claude/skills for personal
use, or into .claude/skills inside a project.
The agent identifies a skill by the name field in its header. Two skills with the
same name cannot sit side by side — one of them will be ignored.
The instructions reference pip.
Without those the skill loads but fails at the first command.