Create Trace

POSThttps://api.confident-ai.com/v2/traces

Creates a trace in your Confident AI project, with the spans it contains, and returns its uuid. Send metricCollection to evaluate the trace online, threadId to group it into a conversation, userId to attribute it to an end user, or testRunId with metricCollection to record it as a test case of an in-progress test run. Values that are not UUIDs are hashed into one, and the returned uuid is the hashed value.

POST/v2/traces

curl -X POST "https://api.confident-ai.com/v2/traces" \
  -H "CONFIDENT_API_KEY: <PROJECT-API-KEY>" \
  -H "Content-Type: application/json" \
  -d '{
  "uuid": "<TRACE-UUID>",
  "name": "Geography QA",
  "input": "What is the capital of France?",
  "output": "The capital of France is Paris.",
  "startTime": "2025-01-15T10:30:00Z",
  "endTime": "2025-01-15T10:30:05Z",
  "status": "SUCCESS",
  "environment": "production",
  "metadata": {
    "client": "acme-corp"
  },
  "tags": [
    "geography"
  ],
  "threadId": "thread-42",
  "thread": {
    "id": "thread-42",
    "metadata": {
      "client": "acme-corp",
      "agentId": "geography-agent"
    },
    "tags": [
      "vip"
    ]
  },
  "userId": "end-user-42",
  "metricCollection": "Collection Name",
  "testRunId": "<TEST-RUN-ID>",
  "testCaseId": "<TEST-CASE-ID>",
  "turnId": "<TURN-ID>",
  "retrievalContext": [
    "Paris is the capital and most populous city of France."
  ],
  "context": [
    "Paris is the capital of France."
  ],
  "expectedOutput": "Paris",
  "toolsCalled": [
    {
      "name": "get_landmark_info",
      "type": "FUNCTION",
      "description": "This tool gives information about a mountain.",
      "inputParameters": {
        "mountain": "Everest"
      },
      "output": "8,848 metres",
      "reasoning": "The user asked for the height of a mountain."
    }
  ],
  "expectedTools": [
    {
      "name": "get_landmark_info",
      "type": "FUNCTION",
      "description": "This tool gives information about a mountain.",
      "inputParameters": {
        "mountain": "Everest"
      },
      "output": "8,848 metres",
      "reasoning": "The user asked for the height of a mountain."
    }
  ],
  "spans": [
    {
      "uuid": "<SPAN-UUID>",
      "type": "LLM",
      "name": "OpenAI Call",
      "model": "gpt-4o",
      "provider": "OpenAI",
      "integration": "LangChain",
      "input": "What is the capital of France?",
      "output": "The capital of France is Paris.",
      "startTime": "2025-01-15T10:30:00Z",
      "endTime": "2025-01-15T10:30:02Z"
    }
  ],
  "metricsData": [
    {
      "name": "Answer Relevancy",
      "score": 0.95,
      "success": true,
      "threshold": 0.5,
      "strictMode": false,
      "flaky": false,
      "reason": "The answer directly states the capital of France.",
      "evaluationModel": "gpt-4o",
      "evaluationCost": 0.0004,
      "error": null,
      "errorType": "AI_CONNECTION_ERROR",
      "verboseLogs": null
    }
  ],
  "attachments": {
    "doc-1": {
      "mimeType": "application/pdf",
      "dataBase64": "JVBERi0xLjQK"
    }
  }
}'

200

{
  "success": true,
  "data": {
    "uuid": "<TRACE-UUID>"
  },
  "link": "https://app.confident-ai.com/project/<PROJECT-ID>/observatory/traces/<TRACE-ID>",
  "deprecated": false
}

Headers

CONFIDENT_API_KEYstringRequired
The API key of your Confident AI project.

Request body

uuidstringRequired
The unique identifier of the trace, generated by your application. Values that are not UUIDs are hashed into one, and the hashed uuid is what the response and every later lookup use.
namestring
This is the name of the trace.
inputany
This is the input to the trace, as a string or any JSON value.
outputany
This is the output of the trace, as a string or any JSON value.
startTimestringRequired
This is the time the trace started, as an ISO 8601 datetime.
endTimestringRequired
This is the time the trace ended, as an ISO 8601 datetime.
statusenum
This represents the error status of a trace or span: SUCCESS when it completed, ERRORED when it failed.
Show 2 enum valuesHide 2 enum values
- SUCCESS
- ERRORED
environmentenum
This is the environment where your trace was posted, which helps with separating and debugging traces from different environments on the Confident AI platform.
Show 4 enum valuesHide 4 enum values
- production
- development
- staging
- testing
metadataobject
This is any additional metadata associated with the trace.
tagslist of strings
This is any tags associated with the trace, which helps with grouping traces and filtering them on the Confident AI platform.
threadIdstring
This is the unique identifier of the thread associated with the trace, which groups traces in the same thread into a conversation.
threadobject
Thread-level fields applied to the thread record. id is an alternate way to specify the thread and must match top-level threadId if both are provided. metadata and tags only take effect when a thread id is resolvable; successive ingestions merge metadata keys, while tags replace any prior value.
Show 3 propertiesHide 3 properties
- idstring
  The thread id. Equivalent to top-level threadId; if both are set they must match.
- metadataobject | null
  Custom key/value metadata to attach to the thread. Values can be any JSON-serializable type and are stringified server-side. Successive ingestions for the same thread merge metadata keys.
- tagsarray | null
  Tags to set on the thread. Replaces any previously stored tags.
userIdstring
This is the unique identifier for your end user for the trace.
metricCollectionstring
This is the metric collection you wish to use to evaluate the trace.
testRunIdstring
This is the unique identifier of the test run to associate the trace with. When set, the trace becomes one test case in that test run and metricCollection is required. It cannot be combined with testCaseId.
testCaseIdstring
The id of an existing test case to attach the trace to, when the trace was produced while evaluating that test case.
turnIdstring
The id of the conversational test case turn to attach the trace to, when the trace was produced while evaluating that turn.
retrievalContextlist of strings
This is the retrieval context of your trace, which is to be used for evaluation.
contextlist of strings
This is the ideal retrieval context of your trace, which is to be used for evaluation.
expectedOutputstring
This is the expected output of your trace, which is the ideal actual output and to be used for evaluation.
toolsCalledlist of objects
This is the tools called by your trace, which is to be used for evaluation.
Show 6 propertiesHide 6 properties
- namestringRequired
  This is the name of the tool.
- typeenum
  The type of the tool call, either a function or an MCP tool.
  Show 2 enum valuesHide 2 enum values
  - FUNCTION
  - MCP
- descriptionstring
  This is the description of the tool.
- inputParametersobject | null
  This is the input parameters that are passed to the tool.
- outputany
  This is the output of the tool.
- reasoningstring
  This is the reasoning your LLM provided for the tool call.
expectedToolslist of objects
This is the expected tools to be called by the trace, which is to be used for evaluation.
Show 6 propertiesHide 6 properties
- namestringRequired
  This is the name of the tool.
- typeenum
  The type of the tool call, either a function or an MCP tool.
  Show 2 enum valuesHide 2 enum values
  - FUNCTION
  - MCP
- descriptionstring
  This is the description of the tool.
- inputParametersobject | null
  This is the input parameters that are passed to the tool.
- outputany
  This is the output of the tool.
- reasoningstring
  This is the reasoning your LLM provided for the tool call.
spanslist of object | object | object | object | object
This is the list of spans in the trace. Each span's type decides which fields it accepts.
Show 5 variantsHide 5 variants
- Base Spanobject
  A plain span with no model, retriever, tool or agent detail.
  Show 19 propertiesHide 19 properties
  - typeenum
    The type of the span. Omit it, or send SPAN, for a plain span.
    Show 1 enum valueHide 1 enum value
    SPAN
  - uuidstringRequired
    The unique identifier of the span, generated by your application. Values that are not UUIDs are hashed into one.
  - namestringRequired
    This is the name of the span.
  - inputany
    This is the input to the span, as a string or any JSON value.
  - outputany
    This is the output of the span, as a string or any JSON value.
  - errorstring
    This is the error message, if an error occurred inside the span.
  - statusenum
    This represents the error status of a trace or span: SUCCESS when it completed, ERRORED when it failed.
    Show 2 enum valuesHide 2 enum values
    SUCCESS
    ERRORED
  - startTimestringRequired
    This is the time the span started, as an ISO 8601 datetime.
  - endTimestringRequired
    This is the time the span ended, as an ISO 8601 datetime.
  - parentUuidstring
    This is the unique identifier of the span's parent span. Omit it for a root span.
  - metadataobject
    This is any additional metadata associated with the span.
  - metricCollectionstring
    This is the metric collection to be used for evaluating the span.
  - retrievalContextlist of strings
    This is the retrieval context of your span, which is to be used for evaluation.
  - contextlist of strings
    This is the ideal retrieval context of your span, which is to be used for evaluation.
  - expectedOutputstring
    This is the expected output of your span, which is the ideal actual output and to be used for evaluation.
  - toolsCalledlist of objects
    This is the tools called by your span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - expectedToolslist of objects
    This is the expected tools to be called by the span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - integrationstring
    This is the integration associated with the span.
  - metricsDatalist of objects
    Metric results you already computed for this span, recorded as-is instead of being evaluated by Confident AI.
    Show 12 propertiesHide 12 properties
    namestringRequired
    The name of the metric.
    scorenumber | null
    The metric score, typically between 0 and 1.
    successboolean | null
    Whether the metric passed its threshold.
    thresholdnumber | null
    The threshold the metric was scored against.
    strictModeboolean
    Whether the metric ran in strict mode, which outputs a binary score of 0 or 1.
    flakyboolean
    Whether the metric's verdict was non-deterministic across runs.
    reasonstring | null
    The reason for the metric score.
    evaluationModelstring | null
    The model used to evaluate the metric.
    evaluationCostnumber | null
    The cost of running the evaluation in USD.
    errorstring | null
    The error message if the evaluation failed.
    errorTypeenum | null
    Why an evaluation errored: the AI connection or a transformer failed, the evaluation model failed, the test case lacked the parameters the metric needs, or an internal error occurred.
    Show 5 enum valuesHide 5 enum values
    AI_CONNECTION_ERROR
    TRANSFORMER_ERROR
    EVALUATION_MODEL_ERROR
    INVALID_TEST_CASE_PARAMETERS
    INTERNAL_ERROR
    verboseLogsstring | null
    Detailed logs from the evaluation.
- OR
- LLM Spanobject
  A span recording a call to a language model, with its model, token counts, costs and the prompt it used.
  Show 30 propertiesHide 30 properties
  - typeenumRequired
    The type of the span, always LLM for an LLM span.
    Show 1 enum valueHide 1 enum value
    LLM
  - uuidstringRequired
    The unique identifier of the span, generated by your application. Values that are not UUIDs are hashed into one.
  - namestringRequired
    This is the name of the span.
  - inputany
    This is the input to the span, as a string or any JSON value.
  - outputany
    This is the output of the span, as a string or any JSON value.
  - errorstring
    This is the error message, if an error occurred inside the span.
  - statusenum
    This represents the error status of a trace or span: SUCCESS when it completed, ERRORED when it failed.
    Show 2 enum valuesHide 2 enum values
    SUCCESS
    ERRORED
  - startTimestringRequired
    This is the time the span started, as an ISO 8601 datetime.
  - endTimestringRequired
    This is the time the span ended, as an ISO 8601 datetime.
  - parentUuidstring
    This is the unique identifier of the span's parent span. Omit it for a root span.
  - metadataobject
    This is any additional metadata associated with the span.
  - metricCollectionstring
    This is the metric collection to be used for evaluating the span.
  - retrievalContextlist of strings
    This is the retrieval context of your span, which is to be used for evaluation.
  - contextlist of strings
    This is the ideal retrieval context of your span, which is to be used for evaluation.
  - expectedOutputstring
    This is the expected output of your span, which is the ideal actual output and to be used for evaluation.
  - toolsCalledlist of objects
    This is the tools called by your span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - expectedToolslist of objects
    This is the expected tools to be called by the span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - integrationstring
    This is the integration associated with the span.
  - metricsDatalist of objects
    Metric results you already computed for this span, recorded as-is instead of being evaluated by Confident AI.
    Show 12 propertiesHide 12 properties
    namestringRequired
    The name of the metric.
    scorenumber | null
    The metric score, typically between 0 and 1.
    successboolean | null
    Whether the metric passed its threshold.
    thresholdnumber | null
    The threshold the metric was scored against.
    strictModeboolean
    Whether the metric ran in strict mode, which outputs a binary score of 0 or 1.
    flakyboolean
    Whether the metric's verdict was non-deterministic across runs.
    reasonstring | null
    The reason for the metric score.
    evaluationModelstring | null
    The model used to evaluate the metric.
    evaluationCostnumber | null
    The cost of running the evaluation in USD.
    errorstring | null
    The error message if the evaluation failed.
    errorTypeenum | null
    Why an evaluation errored: the AI connection or a transformer failed, the evaluation model failed, the test case lacked the parameters the metric needs, or an internal error occurred.
    Show 5 enum valuesHide 5 enum values
    AI_CONNECTION_ERROR
    TRANSFORMER_ERROR
    EVALUATION_MODEL_ERROR
    INVALID_TEST_CASE_PARAMETERS
    INTERNAL_ERROR
    verboseLogsstring | null
    Detailed logs from the evaluation.
  - modelstring
    This is the LLM model used in the span.
  - providerstring
    This is the provider of the generation model used in the span.
  - endpointstring
    This is the API endpoint the model was called through, for providers that expose more than one.
  - costPerInputTokennumber
    This is the cost per input token of the LLM model.
  - costPerOutputTokennumber
    This is the cost per output token of the LLM model.
  - inputTokenCountinteger
    This is the number of input tokens passed to the LLM model.
  - outputTokenCountinteger
    This is the number of output tokens generated by the LLM model.
  - promptAliasstring
    This is the alias of your prompt which is stored on Confident AI.
  - promptVersionstring
    This is the version assigned to your prompt on Confident AI.
  - promptLabelstring
    This is the label assigned to a specific version of prompt on the Confident AI platform.
  - promptCommitHashstring
    This is the hash of the current prompt being logged in the llm span.
- OR
- Retriever Spanobject
  A span recording a knowledge-base lookup, with the embedder and retrieval settings it used.
  Show 22 propertiesHide 22 properties
  - typeenumRequired
    The type of the span, always RETRIEVER for a retriever span.
    Show 1 enum valueHide 1 enum value
    RETRIEVER
  - uuidstringRequired
    The unique identifier of the span, generated by your application. Values that are not UUIDs are hashed into one.
  - namestringRequired
    This is the name of the span.
  - inputany
    This is the input to the span, as a string or any JSON value.
  - outputany
    This is the output of the span, as a string or any JSON value.
  - errorstring
    This is the error message, if an error occurred inside the span.
  - statusenum
    This represents the error status of a trace or span: SUCCESS when it completed, ERRORED when it failed.
    Show 2 enum valuesHide 2 enum values
    SUCCESS
    ERRORED
  - startTimestringRequired
    This is the time the span started, as an ISO 8601 datetime.
  - endTimestringRequired
    This is the time the span ended, as an ISO 8601 datetime.
  - parentUuidstring
    This is the unique identifier of the span's parent span. Omit it for a root span.
  - metadataobject
    This is any additional metadata associated with the span.
  - metricCollectionstring
    This is the metric collection to be used for evaluating the span.
  - retrievalContextlist of strings
    This is the retrieval context of your span, which is to be used for evaluation.
  - contextlist of strings
    This is the ideal retrieval context of your span, which is to be used for evaluation.
  - expectedOutputstring
    This is the expected output of your span, which is the ideal actual output and to be used for evaluation.
  - toolsCalledlist of objects
    This is the tools called by your span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - expectedToolslist of objects
    This is the expected tools to be called by the span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - integrationstring
    This is the integration associated with the span.
  - metricsDatalist of objects
    Metric results you already computed for this span, recorded as-is instead of being evaluated by Confident AI.
    Show 12 propertiesHide 12 properties
    namestringRequired
    The name of the metric.
    scorenumber | null
    The metric score, typically between 0 and 1.
    successboolean | null
    Whether the metric passed its threshold.
    thresholdnumber | null
    The threshold the metric was scored against.
    strictModeboolean
    Whether the metric ran in strict mode, which outputs a binary score of 0 or 1.
    flakyboolean
    Whether the metric's verdict was non-deterministic across runs.
    reasonstring | null
    The reason for the metric score.
    evaluationModelstring | null
    The model used to evaluate the metric.
    evaluationCostnumber | null
    The cost of running the evaluation in USD.
    errorstring | null
    The error message if the evaluation failed.
    errorTypeenum | null
    Why an evaluation errored: the AI connection or a transformer failed, the evaluation model failed, the test case lacked the parameters the metric needs, or an internal error occurred.
    Show 5 enum valuesHide 5 enum values
    AI_CONNECTION_ERROR
    TRANSFORMER_ERROR
    EVALUATION_MODEL_ERROR
    INVALID_TEST_CASE_PARAMETERS
    INTERNAL_ERROR
    verboseLogsstring | null
    Detailed logs from the evaluation.
  - embedderstringRequired
    This is the embedder model used in the span.
  - topKinteger
    This is the top K chunks retrieved from your knowledge base.
  - chunkSizeinteger
    This is the chunk size of each retrieved context.
- OR
- Tool Spanobject
  A span recording a tool call.
  Show 20 propertiesHide 20 properties
  - typeenumRequired
    The type of the span, always TOOL for a tool span.
    Show 1 enum valueHide 1 enum value
    TOOL
  - uuidstringRequired
    The unique identifier of the span, generated by your application. Values that are not UUIDs are hashed into one.
  - namestringRequired
    This is the name of the span.
  - inputany
    This is the input to the span, as a string or any JSON value.
  - outputany
    This is the output of the span, as a string or any JSON value.
  - errorstring
    This is the error message, if an error occurred inside the span.
  - statusenum
    This represents the error status of a trace or span: SUCCESS when it completed, ERRORED when it failed.
    Show 2 enum valuesHide 2 enum values
    SUCCESS
    ERRORED
  - startTimestringRequired
    This is the time the span started, as an ISO 8601 datetime.
  - endTimestringRequired
    This is the time the span ended, as an ISO 8601 datetime.
  - parentUuidstring
    This is the unique identifier of the span's parent span. Omit it for a root span.
  - metadataobject
    This is any additional metadata associated with the span.
  - metricCollectionstring
    This is the metric collection to be used for evaluating the span.
  - retrievalContextlist of strings
    This is the retrieval context of your span, which is to be used for evaluation.
  - contextlist of strings
    This is the ideal retrieval context of your span, which is to be used for evaluation.
  - expectedOutputstring
    This is the expected output of your span, which is the ideal actual output and to be used for evaluation.
  - toolsCalledlist of objects
    This is the tools called by your span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - expectedToolslist of objects
    This is the expected tools to be called by the span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - integrationstring
    This is the integration associated with the span.
  - metricsDatalist of objects
    Metric results you already computed for this span, recorded as-is instead of being evaluated by Confident AI.
    Show 12 propertiesHide 12 properties
    namestringRequired
    The name of the metric.
    scorenumber | null
    The metric score, typically between 0 and 1.
    successboolean | null
    Whether the metric passed its threshold.
    thresholdnumber | null
    The threshold the metric was scored against.
    strictModeboolean
    Whether the metric ran in strict mode, which outputs a binary score of 0 or 1.
    flakyboolean
    Whether the metric's verdict was non-deterministic across runs.
    reasonstring | null
    The reason for the metric score.
    evaluationModelstring | null
    The model used to evaluate the metric.
    evaluationCostnumber | null
    The cost of running the evaluation in USD.
    errorstring | null
    The error message if the evaluation failed.
    errorTypeenum | null
    Why an evaluation errored: the AI connection or a transformer failed, the evaluation model failed, the test case lacked the parameters the metric needs, or an internal error occurred.
    Show 5 enum valuesHide 5 enum values
    AI_CONNECTION_ERROR
    TRANSFORMER_ERROR
    EVALUATION_MODEL_ERROR
    INVALID_TEST_CASE_PARAMETERS
    INTERNAL_ERROR
    verboseLogsstring | null
    Detailed logs from the evaluation.
  - descriptionstring
    This is the description of the tool used in the span.
- OR
- Agent Spanobject
  A span recording an agent step, with the tools and handoffs available to it.
  Show 21 propertiesHide 21 properties
  - typeenumRequired
    The type of the span, always AGENT for an agent span.
    Show 1 enum valueHide 1 enum value
    AGENT
  - uuidstringRequired
    The unique identifier of the span, generated by your application. Values that are not UUIDs are hashed into one.
  - namestringRequired
    This is the name of the span.
  - inputany
    This is the input to the span, as a string or any JSON value.
  - outputany
    This is the output of the span, as a string or any JSON value.
  - errorstring
    This is the error message, if an error occurred inside the span.
  - statusenum
    This represents the error status of a trace or span: SUCCESS when it completed, ERRORED when it failed.
    Show 2 enum valuesHide 2 enum values
    SUCCESS
    ERRORED
  - startTimestringRequired
    This is the time the span started, as an ISO 8601 datetime.
  - endTimestringRequired
    This is the time the span ended, as an ISO 8601 datetime.
  - parentUuidstring
    This is the unique identifier of the span's parent span. Omit it for a root span.
  - metadataobject
    This is any additional metadata associated with the span.
  - metricCollectionstring
    This is the metric collection to be used for evaluating the span.
  - retrievalContextlist of strings
    This is the retrieval context of your span, which is to be used for evaluation.
  - contextlist of strings
    This is the ideal retrieval context of your span, which is to be used for evaluation.
  - expectedOutputstring
    This is the expected output of your span, which is the ideal actual output and to be used for evaluation.
  - toolsCalledlist of objects
    This is the tools called by your span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - expectedToolslist of objects
    This is the expected tools to be called by the span, which is to be used for evaluation.
    Show 6 propertiesHide 6 properties
    namestringRequired
    This is the name of the tool.
    typeenum
    The type of the tool call, either a function or an MCP tool.
    Show 2 enum valuesHide 2 enum values
    FUNCTION
    MCP
    descriptionstring
    This is the description of the tool.
    inputParametersobject | null
    This is the input parameters that are passed to the tool.
    outputany
    This is the output of the tool.
    reasoningstring
    This is the reasoning your LLM provided for the tool call.
  - integrationstring
    This is the integration associated with the span.
  - metricsDatalist of objects
    Metric results you already computed for this span, recorded as-is instead of being evaluated by Confident AI.
    Show 12 propertiesHide 12 properties
    namestringRequired
    The name of the metric.
    scorenumber | null
    The metric score, typically between 0 and 1.
    successboolean | null
    Whether the metric passed its threshold.
    thresholdnumber | null
    The threshold the metric was scored against.
    strictModeboolean
    Whether the metric ran in strict mode, which outputs a binary score of 0 or 1.
    flakyboolean
    Whether the metric's verdict was non-deterministic across runs.
    reasonstring | null
    The reason for the metric score.
    evaluationModelstring | null
    The model used to evaluate the metric.
    evaluationCostnumber | null
    The cost of running the evaluation in USD.
    errorstring | null
    The error message if the evaluation failed.
    errorTypeenum | null
    Why an evaluation errored: the AI connection or a transformer failed, the evaluation model failed, the test case lacked the parameters the metric needs, or an internal error occurred.
    Show 5 enum valuesHide 5 enum values
    AI_CONNECTION_ERROR
    TRANSFORMER_ERROR
    EVALUATION_MODEL_ERROR
    INVALID_TEST_CASE_PARAMETERS
    INTERNAL_ERROR
    verboseLogsstring | null
    Detailed logs from the evaluation.
  - availableToolslist of stringsRequired
    This is the list of names of available tools to be used in the span.
  - agentHandoffslist of stringsRequired
    This is the list of potential agent handoffs in the span.
metricsDatalist of objects
Metric results you already computed for this trace, recorded as-is instead of being evaluated by Confident AI.
Show 12 propertiesHide 12 properties
- namestringRequired
  The name of the metric.
- scorenumber | null
  The metric score, typically between 0 and 1.
- successboolean | null
  Whether the metric passed its threshold.
- thresholdnumber | null
  The threshold the metric was scored against.
- strictModeboolean
  Whether the metric ran in strict mode, which outputs a binary score of 0 or 1.
- flakyboolean
  Whether the metric's verdict was non-deterministic across runs.
- reasonstring | null
  The reason for the metric score.
- evaluationModelstring | null
  The model used to evaluate the metric.
- evaluationCostnumber | null
  The cost of running the evaluation in USD.
- errorstring | null
  The error message if the evaluation failed.
- errorTypeenum | null
  Why an evaluation errored: the AI connection or a transformer failed, the evaluation model failed, the test case lacked the parameters the metric needs, or an internal error occurred.
  Show 5 enum valuesHide 5 enum values
  - AI_CONNECTION_ERROR
  - TRANSFORMER_ERROR
  - EVALUATION_MODEL_ERROR
  - INVALID_TEST_CASE_PARAMETERS
  - INTERNAL_ERROR
- verboseLogsstring | null
  Detailed logs from the evaluation.
attachmentsobject
Map of attachment ids to payloads for all [DEEPEVAL:IMAGE:…] and [DEEPEVAL:PDF:…] markers in this trace. Define attachments at the trace level with the same ids for the same instances.

Response

Create Trace succeeded.

successboolean
Indicates if the request was successful.
dataobject
Show 1 propertyHide 1 property
- uuidstring
  This is the uuid of the trace. It is the uuid you sent, or its UUID hash when the value you sent was not a UUID.
linkstring
This is the URL of the resource on the Confident AI platform.
deprecatedboolean
Indicates if this endpoint is deprecated.

Built byConfident AI