
The Linking API is an HR-first knowledge graph that expands raw keywords into HR-grade synonyms and variants, linking them to normalized HR concepts (titles, skills, certifications, tools). Powered by Hiring Superintelligence, it ensures your databases, search, matching, and analytics stay consistent without manual taxonomy updates.
{ "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

Send a raw keyword and get structured, normalized HR concepts (Titles, Skills, Certifications, Tools) with synonym expansion. Returns Top K-NN concepts with similarity scores to power your databases, search engines, matching, and talent analytics.
Send a raw keyword → returns Top K-NN Concepts + Similarity Scores
Titles
job-titles, degrees
Skills
hard-skills, soft-skills
Certifications
professional, compliance/safety, vendor
Tools
software tools, SaaS platforms, frameworks & libraries, equipment, machines, instruments, devices, vehicles
1{
2 "code": 200,
3 "message": "Linking results",
4 "data": [
5 [
6 "pattern_recognition",
7 0.8787475228309631
8 ],
9 [
10 "artificial_intelligence",
11 0.8637734055519104
12 ],
13 [
14 "computer_vision",
15 0.8614324331283569
16 ],
17 [
18 "data_mining",
19 0.8590985536575317
20 ],
21 [
22 "algorithms",
23 0.8408169746398926
24 ]
25 ]
26}Trusted by HrTech & HR Professional Leaders
We tried prompt-based synonym expansion with OpenAI/Gemini, but results weren’t deterministic and were hard to productionize.
HrFlow.ai Linking gives stable Top-K concepts + scores, so HR query expansion is consistent and relevant.
Job titles were killing our analytics—same role, dozens of spellings, multiple languages.
With HrFlow.ai Linking we normalize titles and degrees into canonical concepts, and our filters and reporting stopped drifting.
A single typo like ‘pyhton’ or a shorthand like ‘sr dev’ used to zero out results.
Linking fixes noisy inputs automatically and maps them to the right concepts, so we don’t lose candidates to spelling.
We tried prompt-based synonym expansion with OpenAI/Gemini, but results weren’t deterministic and were hard to productionize.
HrFlow.ai Linking gives stable Top-K concepts + scores, so HR query expansion is consistent and relevant.
Job titles were killing our analytics—same role, dozens of spellings, multiple languages.
With HrFlow.ai Linking we normalize titles and degrees into canonical concepts, and our filters and reporting stopped drifting.
A single typo like ‘pyhton’ or a shorthand like ‘sr dev’ used to zero out results.
Linking fixes noisy inputs automatically and maps them to the right concepts, so we don’t lose candidates to spelling.
We tried prompt-based synonym expansion with OpenAI/Gemini, but results weren’t deterministic and were hard to productionize.
HrFlow.ai Linking gives stable Top-K concepts + scores, so HR query expansion is consistent and relevant.
Job titles were killing our analytics—same role, dozens of spellings, multiple languages.
With HrFlow.ai Linking we normalize titles and degrees into canonical concepts, and our filters and reporting stopped drifting.
A single typo like ‘pyhton’ or a shorthand like ‘sr dev’ used to zero out results.
Linking fixes noisy inputs automatically and maps them to the right concepts, so we don’t lose candidates to spelling.
We tried prompt-based synonym expansion with OpenAI/Gemini, but results weren’t deterministic and were hard to productionize.
HrFlow.ai Linking gives stable Top-K concepts + scores, so HR query expansion is consistent and relevant.
Job titles were killing our analytics—same role, dozens of spellings, multiple languages.
With HrFlow.ai Linking we normalize titles and degrees into canonical concepts, and our filters and reporting stopped drifting.
A single typo like ‘pyhton’ or a shorthand like ‘sr dev’ used to zero out results.
Linking fixes noisy inputs automatically and maps them to the right concepts, so we don’t lose candidates to spelling.
We had regex rules, vendor taxonomies, and inconsistent IDs across products.
HrFlow.ai Linking became our single normalization layer—database, search, scoring, and analytics all speak the same concept language now.
Daxtra’s taxonomy felt static and limited for multilingual hiring—we kept patching synonyms manually.
HrFlow.ai Linking is multilingual and continuously updated from labor market data, so new titles, skills, and variants show up without us maintaining endless keyword lists.
Certifications were a mess—BLS vs CPR, local variants, vendor names, outdated labels—and tools/equipment were just as inconsistent (forklifts, CNC, SAP, TensorFlow).
HrFlow.ai Linking normalizes certs and tools (software + physical) into canonical concepts with scores, so eligibility rules, search filters, and matching stay precise and consistent across regions.
We had regex rules, vendor taxonomies, and inconsistent IDs across products.
HrFlow.ai Linking became our single normalization layer—database, search, scoring, and analytics all speak the same concept language now.
Daxtra’s taxonomy felt static and limited for multilingual hiring—we kept patching synonyms manually.
HrFlow.ai Linking is multilingual and continuously updated from labor market data, so new titles, skills, and variants show up without us maintaining endless keyword lists.
Certifications were a mess—BLS vs CPR, local variants, vendor names, outdated labels—and tools/equipment were just as inconsistent (forklifts, CNC, SAP, TensorFlow).
HrFlow.ai Linking normalizes certs and tools (software + physical) into canonical concepts with scores, so eligibility rules, search filters, and matching stay precise and consistent across regions.
We had regex rules, vendor taxonomies, and inconsistent IDs across products.
HrFlow.ai Linking became our single normalization layer—database, search, scoring, and analytics all speak the same concept language now.
Daxtra’s taxonomy felt static and limited for multilingual hiring—we kept patching synonyms manually.
HrFlow.ai Linking is multilingual and continuously updated from labor market data, so new titles, skills, and variants show up without us maintaining endless keyword lists.
Certifications were a mess—BLS vs CPR, local variants, vendor names, outdated labels—and tools/equipment were just as inconsistent (forklifts, CNC, SAP, TensorFlow).
HrFlow.ai Linking normalizes certs and tools (software + physical) into canonical concepts with scores, so eligibility rules, search filters, and matching stay precise and consistent across regions.
We had regex rules, vendor taxonomies, and inconsistent IDs across products.
HrFlow.ai Linking became our single normalization layer—database, search, scoring, and analytics all speak the same concept language now.
Daxtra’s taxonomy felt static and limited for multilingual hiring—we kept patching synonyms manually.
HrFlow.ai Linking is multilingual and continuously updated from labor market data, so new titles, skills, and variants show up without us maintaining endless keyword lists.
Certifications were a mess—BLS vs CPR, local variants, vendor names, outdated labels—and tools/equipment were just as inconsistent (forklifts, CNC, SAP, TensorFlow).
HrFlow.ai Linking normalizes certs and tools (software + physical) into canonical concepts with scores, so eligibility rules, search filters, and matching stay precise and consistent across regions.
Integrate 200+ tools with the flip of a switch.
















































HR-native ETL with 200+ connectors plus Webhooks to ingest, normalize, and sync jobs & profiles across your stack—reliable pipelines with unified schemas.
No-code automation platform with 8,000+ app integrations to move data between tools using triggers + actions.
Visual automation platform to extract/transform/route data across 3,000+ apps (plus HTTP modules for any API).
Microsoft Power Automate—workflow automation with 1,000+ API connectors (and support for custom connectors).
Enterprise iPaaS/automation platform with 1,200+ pre-built connectors for orchestrating integrations and data workflows at scale.
Salesforce's low-code workflow automation tool; extended via AppExchange with 7,000+ apps to add integrations and capabilities.
HrFlow.ai Linking combines deep Natural Language Processing with a powerful RAG engine to expand and link raw keywords to normalized HR concepts at blazing speed. Trained on billions of HR data points, it delivers multilingual, typo-tolerant synonym expansion and consistent entities (titles, skills, certifications, tools) for production-grade search, matching, and analytics.
Built for sensitive HR data—secure by default, enterprise-ready.
TLS in transit + encryption at rest to protect documents and extracted data.
Minimal storage by default, with configurable retention policies to match your compliance needs.
Built for sensitive HR data—secure by default, enterprise-ready. AI Act– and GDPR-ready processing, with documented controls for data handling and compliance. A Data Processing Agreement (DPA) is available on request.
Data processing and storage can be aligned with your required region (e.g., EU or US) depending on your deployment.
| Feature | |||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
| Deployment & Trust | |||||||||||
| Foundation | 2016 | 1999 | 2015 | 2001 | 2002 | ||||||
| Headquarters | 🇫🇷 France, 🇺🇸 USA | 🇺🇸 USA | 🇺🇸 USA | 🇳🇱 Netherlands | 🇬🇧 UK | ||||||
| 🇺🇸 USA & 🇪🇺 EU Servers | Built-in | config | config | Built-in | Built-in | ||||||
| GDPR / AI-Act | By design | config | By design | By design | |||||||
| HR Compliance (Safety & Guardrails) | 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 | ||||||
| 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 | ||||||
| Speed (avg seconds / 1 request) | ~100ms | ~500ms | ~2s | ~1s | ~1s | ||||||
| Core Technology | |||||||||||
| Technology | Deep NLP / LLM / RAG | Dense Vectors | LLM | Dense Vectors | Dictionary | ||||||
| Multilingual | 43 lang | 15 lang | 40 lang | 10 lang | 10 lang | ||||||
| Dynamic Update | Labor Market | Labor Market | General Web | Labor Market | Static | ||||||
| Accuracy | High | Medium | High | Low | Low | ||||||
| HR Stack integrations (add-ons) | |||||||||||
| Resume, CV, Job parsers | Built-in (Parsing API) | Built-in | Config | Built-in | Built-in | ||||||
| HR data enrichment & taxonomies | Built-in (Asking/Tagging APIs) | Config | |||||||||
| 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) | ||||||||||
Everything you need to know about the Linking API
Our APIs are designed to complement each other and unlock your data's full potential
Transform HR documents into structured, enriched Talent & Workforce Data — powering every layer of Hiring Intelligence.
API OverviewUnlock Hiring Superintelligence at scale — with transparent, fair, and explainable ranking across every Talent signal.
API Overview
GET STARTED
Start parsing resumes and job postings in minutes with our powerful API.
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.