Alpha Notice: These docs cover the v1-alpha release. Content is incomplete and subject to change.For the latest stable version, see the v0 LangChain Python or LangChain JavaScript docs.
- Unit tests exercise small, deterministic pieces of your agent in isolation using in-memory fakes so you can assert exact behavior quickly and deterministically.
- Integration tests test the agent using real network calls to confirm that components work together, credentials and schemas line up, and latency is acceptable.
Integration Testing
Many agent behaviors only emerge when using a real LLM, such as which tool the agent decides to call, how it formats responses, or whether a prompt modification affects the entire execution trajectory. LangChain’sagentevals
package provides evaluators specifically designed for testing agent trajectories with live models.
AgentEvals lets you easily evaluate the trajectory of your agent (the exact sequence of messages, including tool calls) by performing a trajectory match or by using an LLM judge:
Trajectory match
Hard-code a reference trajectory for a given input and validate the run via a step-by-step comparison.Ideal for testing well-defined workflows where you know the expected behavior. Use when you have specific expectations about which tools should be called and in what order. This approach is deterministic, fast, and cost-effective since it doesn’t require additional LLM calls.
LLM-as-judge
Use a LLM to qualitatively validate your agent’s execution trajectory. The “judge” LLM reviews the agent’s decisions against a prompt rubric (which can include a reference trajectory).More flexible and can assess nuanced aspects like efficiency and appropriateness, but requires an LLM call and is less deterministic. Use when you want to evaluate the overall quality and reasonableness of the agent’s trajectory without strict tool call or ordering requirements.
Installing AgentEvals
Trajectory Match Evaluator
AgentEvals offers thecreateTrajectoryMatchEvaluator
function to match your agent’s trajectory against a reference trajectory. There are four modes to choose from:
Mode | Description | Use Case |
---|---|---|
strict | Exact match of messages and tool calls in the same order | Testing specific sequences (e.g., policy lookup before authorization) |
unordered | Same tool calls allowed in any order | Verifying information retrieval when order doesn’t matter |
subset | Agent calls only tools from reference (no extras) | Ensuring agent doesn’t exceed expected scope |
superset | Agent calls at least the reference tools (extras allowed) | Verifying minimum required actions are taken |
Strict match
Strict match
The
strict
mode ensures trajectories contain identical messages in the same order with the same tool calls, though it allows for differences in message content. This is useful when you need to enforce a specific sequence of operations, such as requiring a policy lookup before authorizing an action.Unordered match
Unordered match
The
unordered
mode allows the same tool calls in any order, which is helpful when you want to verify that specific information was retrieved but don’t care about the sequence. For example, an agent might need to check both weather and events for a city, but the order doesn’t matter.Subset and superset match
Subset and superset match
The
superset
and subset
modes match partial trajectories. The superset
mode verifies that the agent called at least the tools in the reference trajectory, allowing additional tool calls. The subset
mode ensures the agent did not call any tools beyond those in the reference.You can also set the
toolArgsMatchMode
property and/or toolArgsMatchOverrides
to customize how the evaluator considers equality between tool calls in the actual trajectory vs. the reference. By default, only tool calls with the same arguments to the same tool are considered equal. Visit the repository for more details.LLM-as-Judge Evaluator
You can also use an LLM to evaluate the agent’s execution path with thecreateTrajectoryLLMAsJudge
function. Unlike the trajectory match evaluators, it doesn’t require a reference trajectory, but one can be provided if available.
Without reference trajectory
Without reference trajectory
With reference trajectory
With reference trajectory
If you have a reference trajectory, you can add an extra variable to your prompt and pass in the reference trajectory. Below, we use the prebuilt
TRAJECTORY_ACCURACY_PROMPT_WITH_REFERENCE
prompt and configure the reference_outputs
variable:For more configurability over how the LLM evaluates the trajectory, visit the repository.
LangSmith Integration
For tracking experiments over time, you can log evaluator results to LangSmith, a platform for building production-grade LLM applications that includes tracing, evaluation, and experimentation tools. First, set up LangSmith by setting the required environment variables:evaluate
function.
Using vitest/jest integration
Using vitest/jest integration
Using the evaluate function
Using the evaluate function
Alternatively, you can create a dataset in LangSmith and use the Results will be automatically logged to LangSmith.
evaluate
function:To learn more about evaluating your agent, see the LangSmith docs.
Recording & Replaying HTTP Calls
Integration tests that call real LLM APIs can be slow and expensive, especially when run frequently in CI/CD pipelines. We recommend using a library for recording HTTP requests and responses, then replaying them in subsequent runs without making actual network calls. You can usenock
to achieve this. Request/responses are recorded in cassettes, which are then used to mock the real network calls in subsequent runs.
When you modify prompts, add new tools, or change expected trajectories, delete the corresponding cassette files and rerun the tests to record fresh interactions.