HrFlow background
HR-Native Classifiers for Taxonomies & Facets

Tagging API

The Tagging API enriches profiles and job descriptions with searchable tags and database-ready categories (e.g., seniority, roles, industries, skills, education level, work authorization, work mode, and contract type). Powered by Hiring Superintelligence, it automatically classifies HR data across 43+ languages, giving you deterministic labels to power your faceted search and workflows.

Read the Docs
+97% accuracy
43+ languages
17+ built-in Taggers
GDPR-ready & EU AI Act
99.99% uptime
output.json
{
  "parsing": {
    "model": "hrflow-file-v2.1",
    "confidence": 0.92,
  },
  "profile": {
    "name": "John Smith",
    "title": "Data Scientist",
    "skills": ["ML", "Python"]
  }
}

Trusted by Customers, Partners & the AI Ecosystem

ManpowerLogo
CritLogo
EuropeanUnionLogo
SanofiLogo
EnhanceCVLogo
TeamtailorLogo
API RESPONSE

Searchable Tags & Deterministic Categories

Get filterable labels, searchable facets, indexable tags, and analytics-ready categories to enrich your single source of truth. Submit any HR text and return Top-K tags with likelihood scores to prefill forms and automate routing without JSON drift. No JSON drift. No hallucinations. Only deterministic output values.

Select Parsing Type

Submit a job description, work experience, education, or any text + choose a Taxonomy → returns Top K tags + Likelihood Scores.

Explore

Try Live DemoAPI Docs

Top Tagging Taxonomies

Inferred Skills

hard skills, soft skills

Contract Type

permanent, fixed-term, contractor, internship

Education Level

high school, bachelor's, master's, PhD

Seniority Level

intern, junior, mid, senior, lead, manager

O*NET

occupations, job families, tasks, skills, knowledge, abilities, work activities, tools & technology

ESCO

occupations, skills & competences (incl. knowledge + transversal + language skills), qualifications

France Travail ROME

job families, subfamilies, categories, titles

Custom Taxonomy

your company labels, work authorization, work mode, industries, sectors, functions, and more

response.json
 1{
 2  "code": 200,
 3  "message": "Tagging Text finished in 0.39 seconds.",
 4  "data": [
 5    {
 6      "ids": [
 7        "D"
 8      ],
 9      "predictions": [
10        0.8631865382195
11      ],
12      "tags": [
13        "Commerce, Vente et Grande distribution"
14      ]
15    },
16    {
17      "ids": [
18        "I"
19      ],
20      "predictions": [
21        0.8621634840965
22      ],
23      "tags": [
24        "Installation et Maintenance"
25      ]
26    }
27  ]
28}
🎯 MODEL SELECTOR

Tagging Algorithms by Use Case

Pick the right API and model version for your needs— by use case, speed, precision, and cost.

Programmatic Taggers

The Dynamic Tagger (ZeroShot) enables on-the-fly taxonomy classification.

Canonical Taggers

Standard Taggers (ESCO, O*NET, ROME) provide prebuilt normalization against widely used labor-market taxonomies. RAG Taggers enable taxonomy classification grounded in your own knowledge base.

AlgorithmDataUse CaseSpeedPrecisionLanguagesTaxonomy Size
DynamicTextThis Tagger can classify any HR text according to any input Taxonomy or list on the fly. Best for: when you have your own internal taxonomy.2s/requestA+43 languages*Max. 50
Contract TypeTextThis Tagger can classify job descriptions, profiles, and work experiences into 6 standard contract types from HrFlow.ai Taxonomy. Best for: no internal taxonomy.100ms/requestAEN, FR6
SeniorityTextThis Tagger can classify job descriptions, profiles, and work experiences into 6 standard seniority levels from HrFlow.ai Taxonomy. Best for: no internal taxonomy.100ms/requestBEN, FR6
DegreeTextThis Tagger can classify job descriptions, profiles, and education sections into 7 standard degree levels from HrFlow.ai Taxonomy. Best for: no internal taxonomy.100ms/requestBEN, FR7
Rome4 FamilyTextThis Tagger can classify job descriptions, profiles, and education sections into 14 Job families of the French National Labour Taxonomy (ROME 4.0). Best for: no internal taxonomy.100ms/requestBEN, FR14
Rome4 Sub-familyTextThis Tagger can classify job descriptions, profiles, and education sections into 110 job sectors of the French National Labour Taxonomy (ROME 4.0). Best for: no internal taxonomy.100ms/requestBEN, FR110
Rome4 CategoryTextThis Tagger can classify job descriptions, profiles, and education sections into 1,056 job categories of the French National Labour Taxonomy (ROME 4.0). Best for: no internal taxonomy.100ms/requestBEN, FR1056
Rome4 Job-titleTextThis Tagger can classify job descriptions, profiles, and education sections into 12,107 job titles of the French National Labour Taxonomy (ROME 4.0). Best for: no internal taxonomy.100ms/requestCEN, FR12107
CUSTOMER STORIES

Don't take our word for it!

Trusted by fast-growing HR Tech and Global Enterprise

“

No more hallucinated tags

vs. OpenAI
Before HrFlow.ai

We tried tagging with an LLM and prompts to prefill candidates’ forms, but labels drifted over time, and we still got occasional hallucinated tags.

After HrFlow.ai

HrFlow.ai Tagging gives deterministic categories with likelihood scores, so our database and search index stay stable in production.

“

Less DevOps than an in-house tagger

vs. In-house ML
Before HrFlow.ai

Our in-house classifier looked good on day one, but retraining, drift monitoring, and taxonomy updates became a full-time job.

After HrFlow.ai

HrFlow.ai Tagging shipped production-grade taggers (ZeroShot/RAG/Trained) with consistent schema and <100ms latency—so we could focus on product, not ML ops.

“

No more mapping-table maintenance

vs. Textkernel
Before HrFlow.ai

We spent too much time maintaining mapping tables and exceptions to keep tags consistent.

After HrFlow.ai

HrFlow.ai Tagging understands semantics, and returns normalized labels with scores—so we stopped babysitting edge cases and got predictable outputs across regions.

“

No more hallucinated tags

vs. OpenAI
Before HrFlow.ai

We tried tagging with an LLM and prompts to prefill candidates’ forms, but labels drifted over time, and we still got occasional hallucinated tags.

After HrFlow.ai

HrFlow.ai Tagging gives deterministic categories with likelihood scores, so our database and search index stay stable in production.

“

Less DevOps than an in-house tagger

vs. In-house ML
Before HrFlow.ai

Our in-house classifier looked good on day one, but retraining, drift monitoring, and taxonomy updates became a full-time job.

After HrFlow.ai

HrFlow.ai Tagging shipped production-grade taggers (ZeroShot/RAG/Trained) with consistent schema and <100ms latency—so we could focus on product, not ML ops.

“

No more mapping-table maintenance

vs. Textkernel
Before HrFlow.ai

We spent too much time maintaining mapping tables and exceptions to keep tags consistent.

After HrFlow.ai

HrFlow.ai Tagging understands semantics, and returns normalized labels with scores—so we stopped babysitting edge cases and got predictable outputs across regions.

“

No more hallucinated tags

vs. OpenAI
Before HrFlow.ai

We tried tagging with an LLM and prompts to prefill candidates’ forms, but labels drifted over time, and we still got occasional hallucinated tags.

After HrFlow.ai

HrFlow.ai Tagging gives deterministic categories with likelihood scores, so our database and search index stay stable in production.

“

Less DevOps than an in-house tagger

vs. In-house ML
Before HrFlow.ai

Our in-house classifier looked good on day one, but retraining, drift monitoring, and taxonomy updates became a full-time job.

After HrFlow.ai

HrFlow.ai Tagging shipped production-grade taggers (ZeroShot/RAG/Trained) with consistent schema and <100ms latency—so we could focus on product, not ML ops.

“

No more mapping-table maintenance

vs. Textkernel
Before HrFlow.ai

We spent too much time maintaining mapping tables and exceptions to keep tags consistent.

After HrFlow.ai

HrFlow.ai Tagging understands semantics, and returns normalized labels with scores—so we stopped babysitting edge cases and got predictable outputs across regions.

“

No more hallucinated tags

vs. OpenAI
Before HrFlow.ai

We tried tagging with an LLM and prompts to prefill candidates’ forms, but labels drifted over time, and we still got occasional hallucinated tags.

After HrFlow.ai

HrFlow.ai Tagging gives deterministic categories with likelihood scores, so our database and search index stay stable in production.

“

Less DevOps than an in-house tagger

vs. In-house ML
Before HrFlow.ai

Our in-house classifier looked good on day one, but retraining, drift monitoring, and taxonomy updates became a full-time job.

After HrFlow.ai

HrFlow.ai Tagging shipped production-grade taggers (ZeroShot/RAG/Trained) with consistent schema and <100ms latency—so we could focus on product, not ML ops.

“

No more mapping-table maintenance

vs. Textkernel
Before HrFlow.ai

We spent too much time maintaining mapping tables and exceptions to keep tags consistent.

After HrFlow.ai

HrFlow.ai Tagging understands semantics, and returns normalized labels with scores—so we stopped babysitting edge cases and got predictable outputs across regions.

“

Dynamic taxonomy and programmatic mapping

vs. Lightcast
Before HrFlow.ai

Lightcast is built on very broad public data, but it didn’t let us build and use our own taxonomy from our company’s profile and job data, plus our competitors’ job posts.

After HrFlow.ai

HrFlow.ai let us create a dynamic internal taxonomy and tag against it through the Tagging API programmatically, so our labels matched our business reality.

“

One API, multiple taggers & taxonomies

vs. Affinda
Before HrFlow.ai

Affinda felt like a ‘tag the whole profile’ box. We needed a reusable layer to tag each section—work experience, education, skills—with different taxonomies for higher precision.

After HrFlow.ai

HrFlow.ai’s tagger marketplace let us apply the right tagger to each section, making our fields and facets far more accurate.

“

Multilingual tagging that covers our countries

vs. DaXtra
Before HrFlow.ai

We receive resumes in many languages, and DaXtra couldn’t cover all the languages we needed.

After HrFlow.ai

HrFlow.ai Tagging supported 43+ languages with normalized labels, so our search filters stayed consistent globally.

“

Dynamic taxonomy and programmatic mapping

vs. Lightcast
Before HrFlow.ai

Lightcast is built on very broad public data, but it didn’t let us build and use our own taxonomy from our company’s profile and job data, plus our competitors’ job posts.

After HrFlow.ai

HrFlow.ai let us create a dynamic internal taxonomy and tag against it through the Tagging API programmatically, so our labels matched our business reality.

“

One API, multiple taggers & taxonomies

vs. Affinda
Before HrFlow.ai

Affinda felt like a ‘tag the whole profile’ box. We needed a reusable layer to tag each section—work experience, education, skills—with different taxonomies for higher precision.

After HrFlow.ai

HrFlow.ai’s tagger marketplace let us apply the right tagger to each section, making our fields and facets far more accurate.

“

Multilingual tagging that covers our countries

vs. DaXtra
Before HrFlow.ai

We receive resumes in many languages, and DaXtra couldn’t cover all the languages we needed.

After HrFlow.ai

HrFlow.ai Tagging supported 43+ languages with normalized labels, so our search filters stayed consistent globally.

“

Dynamic taxonomy and programmatic mapping

vs. Lightcast
Before HrFlow.ai

Lightcast is built on very broad public data, but it didn’t let us build and use our own taxonomy from our company’s profile and job data, plus our competitors’ job posts.

After HrFlow.ai

HrFlow.ai let us create a dynamic internal taxonomy and tag against it through the Tagging API programmatically, so our labels matched our business reality.

“

One API, multiple taggers & taxonomies

vs. Affinda
Before HrFlow.ai

Affinda felt like a ‘tag the whole profile’ box. We needed a reusable layer to tag each section—work experience, education, skills—with different taxonomies for higher precision.

After HrFlow.ai

HrFlow.ai’s tagger marketplace let us apply the right tagger to each section, making our fields and facets far more accurate.

“

Multilingual tagging that covers our countries

vs. DaXtra
Before HrFlow.ai

We receive resumes in many languages, and DaXtra couldn’t cover all the languages we needed.

After HrFlow.ai

HrFlow.ai Tagging supported 43+ languages with normalized labels, so our search filters stayed consistent globally.

“

Dynamic taxonomy and programmatic mapping

vs. Lightcast
Before HrFlow.ai

Lightcast is built on very broad public data, but it didn’t let us build and use our own taxonomy from our company’s profile and job data, plus our competitors’ job posts.

After HrFlow.ai

HrFlow.ai let us create a dynamic internal taxonomy and tag against it through the Tagging API programmatically, so our labels matched our business reality.

“

One API, multiple taggers & taxonomies

vs. Affinda
Before HrFlow.ai

Affinda felt like a ‘tag the whole profile’ box. We needed a reusable layer to tag each section—work experience, education, skills—with different taxonomies for higher precision.

After HrFlow.ai

HrFlow.ai’s tagger marketplace let us apply the right tagger to each section, making our fields and facets far more accurate.

“

Multilingual tagging that covers our countries

vs. DaXtra
Before HrFlow.ai

We receive resumes in many languages, and DaXtra couldn’t cover all the languages we needed.

After HrFlow.ai

HrFlow.ai Tagging supported 43+ languages with normalized labels, so our search filters stayed consistent globally.

🔗 INTEGRATIONS

Works with the tools you use

Integrate 200+ tools with the flip of a switch.

Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
Integration 0
Integration 1
Integration 2
Integration 3
Integration 4
Integration 5
Integration 6
Integration 7
Integration 8
Integration 9
Integration 10
Integration 11
HrFlow.ai Data Studio

HrFlow.ai Data Studio

HR-native ETL with 200+ connectors plus Webhooks to ingest, normalise, and sync jobs & profiles across your stack—reliable pipelines with unified schemas.

Zapier ETL

Zapier ETL

No-code automation platform with 8,000+ app integrations to move data between tools using triggers + actions.

Make.com ETL

Make.com ETL

Visual automation platform to extract/transform/route data across 3,000+ apps (plus HTTP modules for any API).

Microsoft Flow ETL

Microsoft Flow ETL

Microsoft Power Automate—workflow automation with 1,000+ API connectors (and support for custom connectors).

Workato ETL

Workato ETL

Enterprise iPaaS/automation platform with 1,200+ pre-built connectors for orchestrating integrations and data workflows at scale.

Salesforce Flow Automation

Salesforce Flow Automation

Salesforce's low-code workflow automation tool; extended via AppExchange with 7,000+ apps to add integrations and capabilities.

🚀 KEY FEATURES

State-of-the-art HR Taxonomy Classification & Inference

HrFlow.ai Tagging combines Deep Learning Classifiers with retrieval-based labeling (RAG) to predict normalized HR taxonomy labels. It supports pretrained taggers (HrFlow.ai, ESCO, ROME, O*NET, Opensource) and custom taggers (ZeroShot, RAG, Trained), returning Top-K predictions with likelihood scores at low latency for production-grade search and automation.

Tutorial Video3:45

🔒 ENTERPRISE-READY

Trust & Security

Built for sensitive HR data—secure by default, enterprise-ready.

01

Encryption

TLS in transit + encryption at rest to protect documents and extracted data.

02

Retention control

Minimal storage by default, with configurable retention policies to match your compliance needs.

03

AI-Act / GDPR / DPA ready

Built for sensitive HR data—secure by default, enterprise-ready. AI Act– and GDPR-ready processing, with documented controls for data handling and compliance.

04

Location / Region

Data processing and storage can be aligned with your required region (e.g., EU or US) depending on your deployment.

Visit Trust Center→
📊 FEATURE COMPARISON

HrFlow.ai Tagging is the fastest, most scalable mapping engine for private and public HR taxonomies

Feature
HrFlow.ai Tagging
HrFlow.ai Tagging
Lightcast
Lightcast
OpenAI/Gemini LLMs
OpenAI/Gemini LLMs
OpenAI/Gemini LLMs
Textkernel
Textkernel
Daxtra
Daxtra
Affinda
Affinda
Deployment & Trust
Foundation
2016
1999
2015
2001
2002
2012
🇺🇸 USA & 🇪🇺 EU Servers
Built-in
config
config
Built-in
Built-in
Headquarters
🇫🇷 France, 🇺🇸 USA
🇺🇸 USA
🇺🇸 USA
🇳🇱 Netherlands
🇬🇧 UK
🇦🇺 Australia
GDPR / AI-Act
By design
config
By design
By design
HR Compliance (Safety & Guardrails)
Built-in
Built-in
Built-in
Built-in
Built-in
Pretraining Data
HQ HR Data
Web Job Data
Noisy & Biased Web Data
HQ HR Data
HQ HR Data
Web Job Data
HR-Focused
Input Security (Prompt injection)
Unified output object (JSON drift)
Deterministic output values (hallucination)
Pricing model
per request
per taxonomy
per input+output tokens (expensive)
per request
per request
per request
Speed (avg seconds / 1 request)
~100ms
~500ms
~2s/30 labels
~1s
~1s
~1s
Batch Processing
Limited
DevOps burden (production scale)
Lowest
Medium
High
High
High
High
Core Technology Benchmark
Technology
Deep NLP / LLM / RAG
Dense Vectors / Heuristics
LLM
Dense Vectors / Heuristics
Heuristics / Static Ontologies
Dense Vectors / Lightcast
Multilingual
43 lang
15 lang
40 lang
10 lang
10 lang
56 lang
Custom Taxonomies
✓ tagger-hrflow-dynamic
Limited (prompt)
Limited (mapping table)
Limited (mapping table)
Labour-Market Taxonomies (ROME, O*NET, ISCO/ESCO)
Built-in
ISCO/ESCO, O*NET
ISCO/ESCO, O*NET
ESCO
Custom Taxonomies Size
>10k labels
Limited (mapping table)
< 30 labels
Limited (mapping table)
Limited (mapping table)
Custom Taxonomy Accuracy
High
Medium
Medium
Low
Low
HR Stack integrations (add-ons)
Resume, CV, Job parsers
Built-in (Parsing API)
Config
Built-in
Built-in
Built-in
HR data enrichment & taxonomies
Built-in (Asking/Linking APIs)
Built-in
Built-in
Built-in
Built-in
Search Engine Add-on
Built-in (Searching API)
Built-in
Built-in
Recommender System Add-on
Built-in (Scoring API)
Jobboards / ATS / HCM / HRIS connectors
200+ connectors (Data Studio)
Candidate & Recruiter UI
Widgets (App Studio)
❓ COMMON QUESTIONS

Frequently Asked Questions

Everything you need to know about the Tagging API

🧩 COMPLETE API SUITE

Go beyond the Tagging API

Our APIs are designed to complement each other and unlock your data's full potential

Full Extraction API Suite

Transform HR documents into structured, enriched Talent & Workforce Data — powering every layer of Hiring Intelligence.

API Overview
94%82%71%58%

Ranking API Suite

Unlock Hiring Superintelligence at scale — with transparent, fair, and explainable ranking across every Talent signal.

API Overview

GET STARTED

Ready to transform your HR data?

Start parsing resumes and job postings in minutes with our powerful API.

Start for free→Talk to sales

HrFlow.ai is an API-first company and the leading AI-powered HR data automation platform.

The company helps +1000 customers (HR software vendors, Staffing agencies, large employers, and headhunting firms) to thrive in a high-volume and high-frequency labor market.

The platform provides a complete and fully integrated suite of HR data processing products based on the analysis of hundreds of millions of career paths worldwide -- such as Parsing API, Tagging API, Embedding API, Searching API, Scoring API, and Upskilling API. It also offers a catalog of +200 connectors to build custom scenarios that can automate any business logic.

GDPR Compliant badgeCapterra 4.8 rating badge

SOLUTIONS

PRODUCT

RESOURCES

COMPANY