LangSmith

As explained in Grokking AI Applications

LangSmith is a development and monitoring platform for tracing, evaluating, and debugging language-model applications.

LangSmith makes a language-model application’s behavior visible. When an agent coordinates several tools, it records the steps so you can understand what happened, troubleshoot failures, and improve the workflow. section 8.3

A practical LangSmith workflow follows these stages:

• Connect the application by signing up, creating an API key, and setting the required project and environment variables. section 8.3
• Run the agent and inspect its trace to see how it selected and coordinated tools. section 8.3
• Use the visible execution path to debug, troubleshoot, and improve multi-agent workflows. section 8.3

Tracing HungryTraveler

HungryTraveler™ supervises travel and recipe agents exposed through an MCP server, then sends the result by email. LangSmith displays the trace of those calls, allowing the orchestration to be checked after a successful run. section 8.3

Figure 8.23 This LangSmith trace shows how HungryTraveler operated—and it did well!

Inspect the trace visualization for the HungryTraveler workflow. section 8.3

How Grokking AI Applications covers it

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 it assumes

Assumes a working agent-and-tool workflow and teaches observability setup through API keys and environment variables.

What you can do after

Diagnose/debug with it by inspecting an agent’s traced tool calls and identifying workflow behavior.

How it connects

Connects observability with agents, tools, MCP servers, debugging, API keys, and environment variables.

liveBookmanning.com

Read Grokking AI Applications on liveBook Get the book at manning.com

Also explained in

• 

  liveBookmanning.com
  AI Agents and ApplicationsLangSmith is a development and observability platform for tracing, debugging, evaluating, monitoring, and refining language-model applications.

Compare how 2 books explain LangSmith →

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.

This explainer was generated by Manning's knowledge graph from the text of Grokking AI Applications. The section links point to the parts of the book it draws on.