Skip to main content
POST
/
v1
/
criteria
/
generate
Generate screening criteria
curl --request POST \
  --url https://embed.nova.dweet.com/v1/criteria/generate \
  --header 'Authorization: Bearer <token>' \
  --header 'Content-Type: application/json' \
  --header 'X-Tenant-Id: <x-tenant-id>' \
  --data '
{
  "jobContext": {
    "jobId": "<string>",
    "jobTitle": "<string>",
    "companyName": "<string>",
    "jobDescription": "<string>",
    "additionalInfo": "<string>",
    "applicationQuestions": [
      {}
    ],
    "language": "English"
  }
}
'
{
  "jobId": "<string>",
  "criteria": [
    {
      "id": "<string>",
      "text": "<string>",
      "importance": "MUST_HAVE"
    }
  ],
  "status": "active",
  "createdAt": "2023-11-07T05:31:56Z"
}
Replaces existing criteria: If this job already has criteria, they will be replaced with the newly generated set. Version history is tracked internally for audit purposes - all historical scores retain their original criteria for traceability.

​
When to Use

Generate criteria once per job posting, typically when the job is finalized. This endpoint:
  • Analyzes the job description to identify key requirements
  • Creates structured screening criteria with importance levels
  • Stores the criteria server-side for automatic use during scoring

​
With or Without Questions

Recommended for best results. Requires a prior call to Generate Questions.Clarification answers help calibrate:
  • Which skills are MUST_HAVE vs PREFERRED
  • The target seniority level
  • Any context not captured in the job description

​
Latency

10-20 seconds (synchronous) The AI analyzes the job context to generate contextually relevant criteria. This is a one-time operation per job posting.

​
Next Step

After generating criteria, you’re ready to Score Candidates. Just pass the jobId - Nova loads the criteria automatically.

Authorizations

​
Authorization
string
header
required

API key authentication. Use your environment-specific API key (sk_test_* for sandbox, sk_live_* for production).

Headers

​
X-Tenant-Id
string
required

Your customer/tenant identifier. Used for data isolation and per-customer metrics. Tenants are created automatically on first request.

Body

application/json
​
jobContext
object
required
​
questionSetId
string

Required if answers are provided. The questionSetId from /v1/criteria/questions.

​
answers
object[]

Answers to clarification questions. Partial answers allowed.

Response

Criteria generated and stored successfully. Use GET /v1/jobs/{jobId}/criteria to retrieve them later.

​
jobId
string
required

Your job ID (echoed from request)

​
criteria
object[]
required

Generated screening criteria (typically 5-8 criteria). Stored server-side for automatic use during scoring.

​
status
enum<string>

Criteria status (always 'active' after generation)

Available options:
active
​
createdAt
string<date-time>

When the criteria were created