Logo

Criteria

Criteria define the evaluation rules used to assess candidate applications in Semantikmatch. They specify what to evaluate, how to evaluate it, and what values are considered successful. On this page, we'll explore the different criteria endpoints you can use to manage criteria programmatically.

The Criteria Model

The criteria model contains all the information about evaluation criteria, including the type, query, value to compare, and more.

Example Criteria

{ "id": "74", "criteria_type": "evaluate", "query": "Check if the calculated percentages across all subjects indicate a failing grade below 50%.", "metric": "Grades", "value": "50", "operator": "lower", "custom_name": "Low Performance Check", "mandatory": true, "agg_job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "custom_prompt": "Analyze the student's academic transcript and identify if there are failing grades (below 50%) in any subjects.", "custom_model": "gpt-4", "tools_list": ["web_search"] }

Properties

  • Name
    id
    Type
    string
    Description

    Unique identifier for the criteria.

  • Name
    criteria_type
    Type
    string
    Description

    Type of criteria, such as "evaluate", "extract", "match", etc.

  • Name
    query
    Type
    string
    Description

    The query or instruction for this criteria evaluation.

  • Name
    metric
    Type
    string
    Description

    The metric to measure or extract.

  • Name
    value
    Type
    string
    Description

    The value to compare against.

  • Name
    operator
    Type
    string
    Description

    The comparison operator (e.g., "higher", "lower", "equal").

  • Name
    custom_name
    Type
    string
    Description

    A custom name for the criteria.

  • Name
    mandatory
    Type
    boolean
    Description

    Whether this criteria is mandatory.

  • Name
    agg_job_id
    Type
    string
    Description

    The associated job ID.

  • Name
    custom_prompt
    Type
    string
    Description

    Custom prompt for AI evaluation.

  • Name
    custom_model
    Type
    string
    Description

    The AI model to use for evaluation.

  • Name
    tools_list
    Type
    array
    Description

    List of tools to use for evaluation.

Criteria Result Properties

  • Name
    id
    Type
    string
    Description

    Unique identifier for the criteria result.

  • Name
    criteria_id
    Type
    string
    Description

    Reference to the criteria.

  • Name
    result
    Type
    boolean
    Description

    The result of the evaluation.

  • Name
    score
    Type
    string
    Description

    Score assigned during evaluation.

  • Name
    score_justification
    Type
    string
    Description

    Explanation for the score.

  • Name
    status
    Type
    string
    Description

    Status of the evaluation (e.g., "finished", "pending").

  • Name
    application_id
    Type
    string
    Description

    The associated application ID.

  • Name
    job_id
    Type
    string
    Description

    The associated job ID.

  • Name
    confidence
    Type
    string
    Description

    Confidence level in the evaluation.

  • Name
    confidence_justification
    Type
    string
    Description

    Explanation for the confidence level.

  • Name
    payload
    Type
    object
    Description

    Additional data extracted during evaluation.

GET/api/criteria

List All Criteria

This endpoint allows you to retrieve all criteria across all jobs. It returns a comprehensive list of all criteria defined in the system.

List All Criteria

curl https://api.semantikmatch.com/api/criteria \ -H "Authorization: Bearer YOUR_API_KEY"

Response

[ { "id": "74", "criteria_type": "evaluate", "query": "Check if the calculated percentages across all subjects indicate a failing grade below 50%.", "input_1": null, "input_2": null, "metric": "Grades", "value": "50", "operator": "lower", "custom_name": "Low Performance Check", "mandatory": true, "agg_job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "status": null, "archived": false, "custom_prompt": "Analyze the student's academic transcript and identify if there are failing grades (below 50%) in any subjects.", "custom_model": "gpt-4", "tools_list": ["web_search"] }, { "id": "71", "criteria_type": "extract", "query": "Extract the number of subjects where the student received a grade of 14 or above.", "input_1": null, "input_2": null, "metric": "High Grades Count", "value": "0", "operator": "higher", "custom_name": "Strong Performance Count", "mandatory": false, "agg_job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "status": null, "archived": false, "custom_prompt": null, "custom_model": null, "tools_list": [] } ]
GET/api/criteria/job/{jobId}

Get Criteria for a Job

This endpoint allows you to retrieve all criteria for a specific job.

Parameters

  • Name
    jobId
    Type
    string
    Description

    The job ID to retrieve criteria for.

Get Criteria for a Job

curl "https://api.semantikmatch.com/api/criteria/job/e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c" \ -H "Authorization: Bearer YOUR_API_KEY"

Response

[ { "id": "74", "criteria_type": "evaluate", "query": "Check if the calculated percentages across all subjects indicate a failing grade below 50%.", "metric": "Grades", "value": "50", "operator": "lower", "custom_name": "Low Performance Check", "mandatory": true, "agg_job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "status": null, "archived": false, "custom_prompt": "Analyze the student's academic transcript and identify if there are failing grades (below 50%) in any subjects.", "custom_model": "gpt-4", "tools_list": ["web_search"] }, { "id": "71", "criteria_type": "extract", "query": "Extract the number of subjects where the student received a grade of 14 or above.", "metric": "High Grades Count", "value": "0", "operator": "higher", "custom_name": "Strong Performance Count", "mandatory": false, "agg_job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "status": null, "archived": false, "custom_prompt": null, "custom_model": null, "tools_list": [] } ]
GET/api/criteria/id/{criteriaId}

Get Criteria by ID

This endpoint allows you to retrieve a specific criteria by its ID.

Parameters

  • Name
    criteriaId
    Type
    string
    Description

    The criteria ID to retrieve.

Get Criteria by ID

curl "https://api.semantikmatch.com/api/criteria/id/74" \ -H "Authorization: Bearer YOUR_API_KEY"

Response

{ "id": "74", "criteria_type": "evaluate", "query": "Check if the calculated percentages across all subjects indicate a failing grade below 50%.", "input_1": null, "input_2": null, "metric": "Grades", "value": "50", "operator": "lower", "custom_name": "Low Performance Check", "mandatory": true, "agg_job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "status": null, "archived": false, "custom_prompt": "Analyze the student's academic transcript and identify if there are failing grades (below 50%) in any subjects.", "custom_model": "gpt-4", "tools_list": ["web_search"] }
POST/api/criteria

Create a Criteria

This endpoint allows you to create a new criteria. The criteria can be used to evaluate applications for a specific job.

Required Parameters

  • Name
    criteria_type
    Type
    string
    Description

    Type of criteria (e.g., "evaluate", "extract").

  • Name
    agg_job_id
    Type
    string
    Description

    The job ID to associate this criteria with.

Optional Parameters

  • Name
    query
    Type
    string
    Description

    The query or instruction for this criteria.

  • Name
    metric
    Type
    string
    Description

    The metric to measure or extract.

  • Name
    value
    Type
    string
    Description

    The value to compare against.

  • Name
    operator
    Type
    string
    Description

    The comparison operator.

  • Name
    custom_name
    Type
    string
    Description

    A custom name for this criteria.

  • Name
    mandatory
    Type
    boolean
    Description

    Whether this criteria is mandatory.

  • Name
    custom_prompt
    Type
    string
    Description

    Custom prompt for AI evaluation.

  • Name
    custom_model
    Type
    string
    Description

    The AI model to use for evaluation.

  • Name
    tools_list
    Type
    array
    Description

    List of tools to use for evaluation.

Create a Criteria

curl "https://api.semantikmatch.com/api/criteria" \ -X POST \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "criteria_type": "evaluate", "query": "Check if the student has any failing grades (below 50%) in core subjects.", "metric": "Failing Grades", "value": "50", "operator": "lower", "custom_name": "Core Subject Performance", "mandatory": true, "agg_job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "custom_prompt": "Analyze the student's transcript and identify if there are any failing grades (below 50%) in core subjects (Math, Science, Languages).", "custom_model": "gpt-4", "tools_list": ["web_search"] }'

Response

{ "id": "75", "criteria_type": "evaluate", "query": "Check if the student has any failing grades (below 50%) in core subjects.", "input_1": null, "input_2": null, "metric": "Failing Grades", "value": "50", "operator": "lower", "custom_name": "Core Subject Performance", "mandatory": true, "agg_job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "status": null, "archived": false, "custom_prompt": "Analyze the student's transcript and identify if there are any failing grades (below 50%) in core subjects (Math, Science, Languages).", "custom_model": "gpt-4", "tools_list": ["web_search"], "created_at": "2025-05-07T15:30:00.000Z" }
DELETE/api/criteria/{criteriaId}

Delete a Criteria

This endpoint allows you to delete a specific criteria. This will remove the criteria and all its associated results.

Parameters

  • Name
    criteriaId
    Type
    string
    Description

    The criteria ID to delete.

Delete a Criteria

curl "https://api.semantikmatch.com/api/criteria/74" \ -X DELETE \ -H "Authorization: Bearer YOUR_API_KEY"

Response

// No content (HTTP 204)
GET/api/criteria/results/job/{jobId}

Get Criteria Results for a Job

This endpoint allows you to retrieve all criteria results for a specific job. This includes all evaluation results across all applications for the job.

Parameters

  • Name
    jobId
    Type
    string
    Description

    The job ID to retrieve criteria results for.

Get Criteria Results for a Job

curl "https://api.semantikmatch.com/api/criteria/results/job/e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c" \ -H "Authorization: Bearer YOUR_API_KEY"

Response

[ { "id": "584", "criteria_id": "74", "result": false, "evaluated_at": "2025-05-05T08:13:20.658Z", "score": "100", "score_justification": "The total TOEIC score of 930 is higher than 500, thus meeting the criterion.", "citations": ["TOTAL SCORE: 930"], "status": "finished", "application_id": "c4501559-a55d-4457-99ac-64030879cf0c", "job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "section": "1729782567464", "confidence": "100", "confidence_justification": "The agent correctly extracted the TOEIC Total Score as 930, which is indeed higher than 500.", "payload": { "extracted_value": "930" }, "scorecard_score": 2, "has_scorecard_result": true }, { "id": "585", "criteria_id": "71", "result": true, "evaluated_at": "2025-05-05T08:13:34.003Z", "score": "100", "score_justification": "The student has 3 subjects with grades of 14 or above.", "citations": ["Mathematics: 15/20", "English: 17/20", "Physics: 14/20"], "status": "finished", "application_id": "c4501559-a55d-4457-99ac-64030879cf0c", "job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "section": "1729782567464", "confidence": "100", "confidence_justification": "The transcript clearly shows 3 subjects with grades above 14.", "payload": { "extracted_value": "3" }, "scorecard_score": 2, "has_scorecard_result": true } ]
GET/api/criteria/results/{resultId}

Get Criteria Result by ID

This endpoint allows you to retrieve a specific criteria result by its ID. This returns the detailed evaluation result including score, justification, and any extracted data.

Parameters

  • Name
    resultId
    Type
    string
    Description

    The criteria result ID to retrieve.

Get Criteria Result by ID

curl "https://api.semantikmatch.com/api/criteria/results/584" \ -H "Authorization: Bearer YOUR_API_KEY"

Response

{ "id": "584", "criteria_id": "74", "result": false, "evaluated_at": "2025-05-05T08:13:20.658Z", "score": "100", "score_justification": "The total TOEIC score of 930 is higher than 500, thus meeting the criterion.", "citations": ["TOTAL SCORE: 930"], "status": "finished", "application_id": "c4501559-a55d-4457-99ac-64030879cf0c", "job_id": "e0395dae-e4b7-4b28-ae9c-52b5c6fc6b1c", "section": "1729782567464", "confidence": "100", "confidence_justification": "The agent correctly extracted the TOEIC Total Score as 930, which is indeed higher than 500.", "payload": { "extracted_value": "930" }, "criteria": { "id": "74", "criteria_type": "evaluate", "query": "Check if the calculated percentages across all subjects indicate a failing grade below 50%.", "metric": "Grades", "value": "50", "operator": "lower", "custom_name": "Low Performance Check" } }
DELETE/api/criteria/results/{resultId}

Delete a Criteria Result

This endpoint allows you to delete a specific criteria result. This will trigger a re-evaluation of the corresponding criteria for the application.

Parameters

  • Name
    resultId
    Type
    string
    Description

    The criteria result ID to delete.

Delete a Criteria Result

curl "https://api.semantikmatch.com/api/criteria/results/584" \ -X DELETE \ -H "Authorization: Bearer YOUR_API_KEY"

Response

// No content (HTTP 204)

Was this page helpful?