LangSmith
LangSmith is a developer platform for tracing, debugging, testing, evaluating, and monitoring applications built with language models and AI agents.
Grokking AI Applications
LangSmith is a development and monitoring platform for tracing, evaluating, and debugging language-model applications.
- How it is used
- Supports observability, debugging, and improvement of language-model applications, especially agents coordinating multiple tools.
- How deep it goes
- Explains setup, environment configuration, trace inspection, and practical debugging, but does not detail LangSmith internals.
- Examples
- Uses the HungryTraveler agent, travel and recipe tools, email delivery, and a LangSmith execution trace.
- What you can do after
- Diagnose/debug with it by inspecting an agent’s traced tool calls and identifying workflow behavior.
AI Agents and Applications
LangSmith is a development and observability platform for tracing, debugging, evaluating, monitoring, and refining language-model applications.
- How it is used
- Traces Q&A chains and tool-based agents so developers can inspect execution, troubleshoot deviations, and monitor LLM applications.
- How deep it goes
- Walks through tracing configuration and trace inspection; describes evaluators, datasets, and production feedback without a worked evaluation procedure.
- Examples
- Uses a document Q&A chatbot trace and an agent trace showing LLM calls, tool invocations, and message flow.
- What you can do after
- Operate/configure it to capture runs and inspect Q&A or agent execution when behavior differs from expectations.
Related concepts
- trajectoryused by · A trajectory is an ordered sequence of states, actions, events, or operations that records or describes progression through successive steps or over time.
- evaluationuses · Evaluation is the systematic assessment of a system, result, or approach against relevant criteria, evidence, or objectives.
- observabilityimplements · Observability is the ability to infer a system’s internal state and behavior from its externally available outputs, such as logs, metrics, and traces.
- monitoringuses · Monitoring is the ongoing observation and measurement of a system’s behavior, state, or operational signals to assess its condition and detect changes or problems.
These guides are generated from the text of Manning books by Manning's knowledge graph and link to the sections they draw on. The full books are available on liveBook and at manning.com.