Skip to content

Job Classify API

POST /api/v1/job/classify

Use this endpoint when an application needs one standardized O*NET occupation for job text rather than a ranked list of candidates.

This is the compact classification endpoint for product flows that need a single occupation code and title from a noisy job title or description. It is useful for normalization, enrichment, routing, search filters, analytics joins, and workflows where one best O*NET 30.3-grounded result is enough.

Complete executable examples belong in the AvelinLabs API examples repository.

Base URL: https://api.avelinlabs.com

Requires a runtime API key:

Authorization: Bearer <runtime-api-key>

Type: string

Required: Yes

Meaning: Job title or short role label to classify.

Type: string

Required: No

Meaning: Job description or other skill-bearing text. More complete text can improve the quality of evidence.

Type: boolean

Required: No

Meaning: Optional diagnostic flag. Public integrations should not depend on debug-only fields.

{
"title": "Help Desk Technician",
"description": "Resolve user support issues, troubleshoot hardware and software problems, document incidents, and escalate complex tickets.",
"debug": false
}

See the public example payload: payloads/job-classify.json.

Illustrative beta response snippet:

{
"occupation": {
"onet_code": "15-1232.00",
"title": "Computer User Support Specialists"
},
"confidence": 0.88,
"trust_score": 0.82,
"confidence_level": "HIGH",
"job_signals": ["support", "troubleshooting"],
"uncertainty": {
"total": 0.18
},
"decision": {
"decision": "AUTO_ACCEPT",
"reason": "Confidence and uncertainty meet the configured decision threshold."
}
}

See the public example response: responses/job-classify.example.json.

Meaning: Top classified occupation object.

Meaning: O*NET occupation code for the top result.

Meaning: Occupation title for the top result.

Meaning: Top-level confidence signal for the classification. Use as decision support, not absolute truth.

Meaning: Raw or pre-adjusted confidence signal where present.

Meaning: Trust-oriented score for the classification.

Meaning: Uncertainty signals. See output interpretation.

Meaning: Optional routing recommendation.

Meaning: Categorical confidence label.

Meaning: Broad inferred task or role category when available.

Meaning: Signals detected from the input.

Meaning: Signal for how strongly the input fits the supported domain.

Meaning: Ambiguity flags for domain or overall result interpretation.

weak_signal_detected and weak_signal_reason

Section titled “weak_signal_detected and weak_signal_reason”

Meaning: Indicates sparse or weak evidence when present.

Use this endpoint when your workflow needs one best occupation suggestion. Use confidence, uncertainty, trust_score, ambiguity fields, weak-signal fields, and decision to decide whether the result can be accepted, displayed with caveats, or routed for review.

For cross-endpoint guidance, read output interpretation and standard error responses.