Hireability icon
developer-tools

Hireability

Strong resume-to-JSON parsing on standard and messy single-column PDFs, but two-column layouts can break the result schema.

Resume parsing APIIndian contact supportLayout-sensitiveFree trial
TL;DR — our verdictUpdated August 2026 · 7 test artifacts

Capable on standard resumes, risky on multi-column layouts

Where it wins
  • Your resumes are mostly single-column or otherwise standardized PDFs.
  • You need Indian phone numbers, Indian addresses, and LinkedIn captured automatically.
  • You want structured JSON with certifications, hobbies, and other extra fields.
Main limitation
  • Your resumes are two-column or sidebar-heavy and schema routing must be exact.
Pricing (verified plans)
Free Trial Free, no credit card requiredPre-paid packages Volume-basedCustom Annual Custom quote
Strongest test artifacts
OUTPUT →Resume Parsing, Classification, and Structured Export →Identity and Contact Extraction →

Feature scores on this page: 7.0/10 (1 scored feature)

Our take

Hireability returns structured JSON and handles Indian contact formats, messy single-column resumes, certifications, LinkedIn, and hobbies well enough to be useful. The big caveat is layout sensitivity: the two-column Priya Sharma resume was misclassified as a Job Order, and the skills output was noisy enough that it would need cleanup before ranking or downstream automation.

Download video: Demo video
Hireability demo walkthrough video

In-Depth Review

Our detailed analysis of Hireability — features, performance, and real-world testing.

AD
AI Demos Team
Expert Reviewer
Verified Review

Feature-by-Feature Breakdown

Resume Parsing, Classification, and Structured Export
Strong on clean resumes, but can drop visible contact blocks on multi-column layouts.
7/10
▾
Test Summary
Feature tested: Resume Parsing, Classification, and Structured Export
Result: Failed (7/10) — Strong on clean resumes, but can drop visible contact blocks on multi-column layouts.

Feature tested: Resume Parsing, Classification, and Structured Export

Result: Failed (7/10)

Verdict: Strong on clean resumes, but can drop visible contact blocks on multi-column layouts.

Expected behavior: Parses uploaded resume PDFs into structured machine-readable outputs such as JSON and HR-XML, while classifying/routing the document into the appropriate schema. The cards exercise it on clean single-column, messy no-header, and two-column resumes, including cases where a two-column input was routed to a Job Order-style response.

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): INPUT — Input 3 Messy resume for JOHN KUMAR.png

Observed output: Output artifact (Text prompt): RESULT

Input artifact: Input artifact (Image): INPUT — Input 3 Messy resume for JOHN KUMAR.png

Output artifact: Output artifact (Text prompt): RESULT

What changed: Image transformed into Text prompt

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): INPUT — Input 1 Rugved Nichite clean PDF resume.png

Observed output: Output artifact (Image): The source resume grouped skills into Languages, AI/ML, Cloud, Frameworks, and Databases, but the parsed output flattened that structure into a single competency list. — hireability_task1_categorized-skills-not-preserved.png

Input artifact: Input artifact (Image): INPUT — Input 1 Rugved Nichite clean PDF resume.png

Output artifact: Output artifact (Image): The source resume grouped skills into Languages, AI/ML, Cloud, Frameworks, and Databases, but the parsed output flattened that structure into a single competency list. — hireability_task1_categorized-skills-not-preserved.png

What changed: Image transformed into Image

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Rugved Nichite resume source — hireability-image-11-293923438eb5.png

Observed output: Output artifact (Text prompt): Experience extraction summary

Input artifact: Input artifact (Image): Rugved Nichite resume source — hireability-image-11-293923438eb5.png

Output artifact: Output artifact (Text prompt): Experience extraction summary

What changed: Image transformed into Text prompt

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): John Kumar resume source — image-3.png

Observed output: Output artifact (Text prompt): Skills extraction summary

Input artifact: Input artifact (Image): John Kumar resume source — image-3.png

Output artifact: Output artifact (Text prompt): Skills extraction summary

What changed: Image transformed into Text prompt

Test case: Artifact → Image

Input type: Artifact

Input used: Input artifact (Artifact): The clean single-column resume parsed into structured JSON, but the name was split into GivenName 'Dev' and FamilyName 'loper' because the PDF text layer merged the name with the subtitle.

Observed output: Output artifact (Image): Output — hireability_task1_name-split-dev-loper.png

Input artifact: Input artifact (Artifact): The clean single-column resume parsed into structured JSON, but the name was split into GivenName 'Dev' and FamilyName 'loper' because the PDF text layer merged the name with the subtitle.

Output artifact: Output artifact (Image): Output — hireability_task1_name-split-dev-loper.png

What changed: Artifact transformed into Image

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Input — Input 3 Messy resume for JOHN KUMAR.png

Observed output: Output artifact (Text prompt): Output

Input artifact: Input artifact (Image): Input — Input 3 Messy resume for JOHN KUMAR.png

Output artifact: Output artifact (Text prompt): Output

What changed: Image transformed into Text prompt

Test case: Artifact → Image

Input type: Artifact

Input used: Input artifact (Artifact): The two-column Priya Sharma resume was misclassified as a Job Order, so the parser returned job-style fields instead of a resume profile.

Observed output: Output artifact (Image): Output — hireability_task2_job-order-misclassification.png

Input artifact: Input artifact (Artifact): The two-column Priya Sharma resume was misclassified as a Job Order, so the parser returned job-style fields instead of a resume profile.

Output artifact: Output artifact (Image): Output — hireability_task2_job-order-misclassification.png

What changed: Artifact transformed into Image

Why it matters / Conclusion: Identity extraction is reliable on straightforward resumes, but it is not safe to trust on the two-column input.

Parses uploaded resume PDFs into structured machine-readable outputs such as JSON and HR-XML, while classifying/routing the document into the appropriate schema. The cards exercise it on clean single-column, messy no-header, and two-column resumes, including cases where a two-column input was routed to a Job Order-style response.

image
Input artifact for "Resume Parsing, Classification, and Structured Export" test: INPUT, Input 3 Messy resume for JOHN KUMAR.png
↓
OUTPUT
The messy resume still preserved the objective and first work experience correctly, including ABC Tech Solutions and the 2021 start date.
image
Input artifact for "Resume Parsing, Classification, and Structured Export" test: INPUT, Input 1 Rugved Nichite clean PDF resume.png
↓
image
Output artifact for "Resume Parsing, Classification, and Structured Export" test: The source resume grouped skills into Languages, AI/ML, Cloud, Frameworks, and Databases, but the parsed output flattened that structure into a single competency list., hireability_task1_categorized-skills-not-preserved.png
The source resume grouped skills into Languages, AI/ML, Cloud, Frameworks, and Databases, but the parsed output flattened that structure into a single competency list.
image
Input artifact for "Resume Parsing, Classification, and Structured Export" test: Rugved Nichite resume source, hireability-image-11-293923438eb5.png
↓
OUTPUT
Rugved's resume returned two complete experience entries: AI Research Analyst at FutureSmart AI and Software Developer Intern at TechSolutions Pvt. Ltd., with dates and bullet descriptions preserved.
image
Input artifact for "Resume Parsing, Classification, and Structured Export" test: John Kumar resume source, image-3.png
↓
OUTPUT
The messy John Kumar resume still returned 15 skills, including Python, Java, HTML, CSS, JavaScript, MySQL, MongoDB, Git, Linux, Docker, AWS, Problem Solving, and Team Player.
image
The clean single-column resume parsed into structured JSON, but the name was split into GivenName 'Dev' and FamilyName 'loper' because the PDF text layer merged the name with the subtitle.
↓
image
Output artifact for "Resume Parsing, Classification, and Structured Export" test: Output, hireability_task1_name-split-dev-loper.png
image
Input artifact for "Resume Parsing, Classification, and Structured Export" test: Input, Input 3 Messy resume for JOHN KUMAR.png
↓
OUTPUT
The messy John Kumar resume parsed successfully without crashing; the report says the structured output recovered the candidate record, work history, education, skills, and hobbies.
image
The two-column Priya Sharma resume was misclassified as a Job Order, so the parser returned job-style fields instead of a resume profile.
↓
image
Output artifact for "Resume Parsing, Classification, and Structured Export" test: Output, hireability_task2_job-order-misclassification.png
Bottom Line
Identity extraction is reliable on straightforward resumes, but it is not safe to trust on the two-column input.
From our researchParse resumes into structured data using an APIearlier research
Identity and Contact Extraction
Good header parsing when layout is simple.
▾
Test Summary
Feature tested: Identity and Contact Extraction
Result: Partial — Good header parsing when layout is simple.

Feature tested: Identity and Contact Extraction

Result: Partial

Verdict: Good header parsing when layout is simple.

Expected behavior: Pulls header identity/contact fields from resumes, including GivenName/FamilyName, email, phone, address, and LinkedIn. It was exercised on clean, messy, and two-column resume inputs, with mixed success when the name or contact block was split or missing.

Test case: Artifact → Image

Input type: Artifact

Input used: Input artifact (Artifact): The contact block was visibly present in the source, but the parsed output left GivenName, FamilyName, Email, Phone, LinkedIn, and Address empty.

Observed output: Output artifact (Image): Output — hireability_task2_contact-fields-missing.png

Input artifact: Input artifact (Artifact): The contact block was visibly present in the source, but the parsed output left GivenName, FamilyName, Email, Phone, LinkedIn, and Address empty.

Output artifact: Output artifact (Image): Output — hireability_task2_contact-fields-missing.png

What changed: Artifact transformed into Image

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Input — Input 3 Messy resume for JOHN KUMAR.png

Observed output: Output artifact (Text prompt): Output

Input artifact: Input artifact (Image): Input — Input 3 Messy resume for JOHN KUMAR.png

Output artifact: Output artifact (Text prompt): Output

What changed: Image transformed into Text prompt

Why it matters / Conclusion: Straightforward headers are handled well, but merged text and multi-column layouts can wipe out the contact block.

Pulls header identity/contact fields from resumes, including GivenName/FamilyName, email, phone, address, and LinkedIn. It was exercised on clean, messy, and two-column resume inputs, with mixed success when the name or contact block was split or missing.

image
The contact block was visibly present in the source, but the parsed output left GivenName, FamilyName, Email, Phone, LinkedIn, and Address empty.
↓
image
Output artifact for "Identity and Contact Extraction" test: Output, hireability_task2_contact-fields-missing.png
image
Input artifact for "Identity and Contact Extraction" test: Input, Input 3 Messy resume for JOHN KUMAR.png
↓
OUTPUT
John Kumar's name, email, +91 phone, Mumbai location, and LinkedIn were extracted correctly on the messy resume.
Bottom Line
Straightforward headers are handled well, but merged text and multi-column layouts can wipe out the contact block.
From our researchParse resumes into structured data using an API
Work Experience and Education Extraction
Mostly reliable, with a merge bug in later job rows.
▾
Test Summary
Feature tested: Work Experience and Education Extraction
Result: Partial — Mostly reliable, with a merge bug in later job rows.

Feature tested: Work Experience and Education Extraction

Result: Partial

Verdict: Mostly reliable, with a merge bug in later job rows.

Expected behavior: Extracts work history rows and education entries from resume text, including roles, employers, dates, institutions, and grades/scores. The member card shows it recovering the main blocks but sometimes merging later rows or omitting extra schooling entries.

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Input — i3_p3_education_missing.png

Observed output: Output artifact (Text prompt): Output

Input artifact: Input artifact (Image): Input — i3_p3_education_missing.png

Output artifact: Output artifact (Text prompt): Output

What changed: Image transformed into Text prompt

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Input — image-11.png

Observed output: Output artifact (Text prompt): Output

Input artifact: Input artifact (Image): Input — image-11.png

Output artifact: Output artifact (Text prompt): Output

What changed: Image transformed into Text prompt

Why it matters / Conclusion: Core experience and education data are recoverable, but later rows and extra schooling entries can be lost or merged.

Extracts work history rows and education entries from resume text, including roles, employers, dates, institutions, and grades/scores. The member card shows it recovering the main blocks but sometimes merging later rows or omitting extra schooling entries.

image
Input artifact for "Work Experience and Education Extraction" test: Input, i3_p3_education_missing.png
↓
OUTPUT
Only the B.E. education row was extracted from the messy John Kumar resume; the 12th Science and 10th standard entries visible in the source were missed.
image
Input artifact for "Work Experience and Education Extraction" test: Input, image-11.png
↓
OUTPUT
The clean Rugved resume returned both work experiences and the B.E. Computer Engineering education row, with the CGPA captured as a string.
Bottom Line
Core experience and education data are recoverable, but later rows and extra schooling entries can be lost or merged.
From our researchParse resumes into structured data using an API
Skills Extraction and Normalization
High recall, but too noisy for downstream ranking.
▾
Test Summary
Feature tested: Skills Extraction and Normalization
Result: Failed — High recall, but too noisy for downstream ranking.

Feature tested: Skills Extraction and Normalization

Result: Failed

Verdict: High recall, but too noisy for downstream ranking.

Expected behavior: Extracts skills into PersonCompetency records from resume text. The tested output flattened categorized skills into one list, assigned uniform beginner levels, and sometimes introduced non-skill noise or blank level fields.

Test case: Artifact → Image

Input type: Artifact

Input used: Input artifact (Artifact): The original Languages / AI-ML / Cloud / Frameworks / Databases grouping was flattened into a single skills list.

Observed output: Output artifact (Image): Output — hireability_task1_categorized-skills-not-preserved.png

Input artifact: Input artifact (Artifact): The original Languages / AI-ML / Cloud / Frameworks / Databases grouping was flattened into a single skills list.

Output artifact: Output artifact (Image): Output — hireability_task1_categorized-skills-not-preserved.png

What changed: Artifact transformed into Image

Test case: Image → Image

Input type: Image

Input used: Input artifact (Image): Input — image-8.png

Observed output: Output artifact (Image): The skills panel listed competencies but left the Level fields blank. — hireability_task2_competency-levels-blank.png

Input artifact: Input artifact (Image): Input — image-8.png

Output artifact: Output artifact (Image): The skills panel listed competencies but left the Level fields blank. — hireability_task2_competency-levels-blank.png

What changed: Image transformed into Image

Why it matters / Conclusion: The parser finds many skills, but the output is too noisy and too normalized for ranking without cleanup.

Extracts skills into PersonCompetency records from resume text. The tested output flattened categorized skills into one list, assigned uniform beginner levels, and sometimes introduced non-skill noise or blank level fields.

image
The original Languages / AI-ML / Cloud / Frameworks / Databases grouping was flattened into a single skills list.
↓
image
Output artifact for "Skills Extraction and Normalization" test: Output, hireability_task1_categorized-skills-not-preserved.png
image
Input artifact for "Skills Extraction and Normalization" test: Input, image-8.png
↓
image
Output artifact for "Skills Extraction and Normalization" test: The skills panel listed competencies but left the Level fields blank., hireability_task2_competency-levels-blank.png
The skills panel listed competencies but left the Level fields blank.
Bottom Line
The parser finds many skills, but the output is too noisy and too normalized for ranking without cleanup.
From our researchParse resumes into structured data using an API
Additional Profile Field Extraction
Useful extras, but certification normalization is weak.
▾
Test Summary
Feature tested: Additional Profile Field Extraction
Result: Partial — Useful extras, but certification normalization is weak.

Feature tested: Additional Profile Field Extraction

Result: Partial

Verdict: Useful extras, but certification normalization is weak.

Expected behavior: Extracts extra resume profile fields such as certifications, hobbies, and LinkedIn. The card shows certifications coming through on a clean resume but getting merged with other text in a messy resume, while hobbies were still separated.

Test case: Image → Text prompt

Input type: Image

Input used: Input artifact (Image): Input — image-11.png

Observed output: Output artifact (Text prompt): Output

Input artifact: Input artifact (Image): Input — image-11.png

Output artifact: Output artifact (Text prompt): Output

What changed: Image transformed into Text prompt

Test case: Artifact → Image

Input type: Artifact

Input used: Input artifact (Artifact): John Kumar's messy resume, CertificationName merged the certification text with 'good communication' and 'References available on request' instead of keeping certifications separate.

Observed output: Output artifact (Image): CertificationName merged the certification text with 'good communication' and 'References available on request' instead of keeping certifications separate. — hireability_task3_certs-merged.png

Input artifact: Input artifact (Artifact): John Kumar's messy resume, CertificationName merged the certification text with 'good communication' and 'References available on request' instead of keeping certifications separate.

Output artifact: Output artifact (Image): CertificationName merged the certification text with 'good communication' and 'References available on request' instead of keeping certifications separate. — hireability_task3_certs-merged.png

What changed: Artifact transformed into Image

Test case: File → Text prompt

Input type: File

Input used: Input artifact (File): Input — Input 3: Messy resume for JOHN KUMAR

Observed output: Output artifact (Text prompt): Output

Input artifact: Input artifact (File): Input — Input 3: Messy resume for JOHN KUMAR

Output artifact: Output artifact (Text prompt): Output

What changed: File transformed into Text prompt

Why it matters / Conclusion: Useful extra fields are available, but certification extraction is unreliable when the source mixes free text with credential lines.

Extracts extra resume profile fields such as certifications, hobbies, and LinkedIn. The card shows certifications coming through on a clean resume but getting merged with other text in a messy resume, while hobbies were still separated.

image
Input artifact for "Additional Profile Field Extraction" test: Input, image-11.png
↓
OUTPUT
The clean Rugved resume extracted AWS Cloud Practitioner Essentials and Python for Data Science and AI as separate certifications.
image
John Kumar's messy resume, CertificationName merged the certification text with 'good communication' and 'References available on request' instead of keeping certifications separate.
↓
image
Output artifact for "Additional Profile Field Extraction" test: CertificationName merged the certification text with 'good communication' and 'References available on request' instead of keeping certifications separate., hireability_task3_certs-merged.png
CertificationName merged the certification text with 'good communication' and 'References available on request' instead of keeping certifications separate.
image
Input artifact for "Additional Profile Field Extraction" test: Input, Input 3: Messy resume for JOHN KUMAR
↓
OUTPUT
The messy John Kumar resume also produced a dedicated hobbies field with cricket, reading, travelling, and cooking separated out.
Bottom Line
Useful extra fields are available, but certification extraction is unreliable when the source mixes free text with credential lines.
From our researchParse resumes into structured data using an API

Pricing & Access

Partially tested free trial; no public dollar figures were listed.

TESTED
Free Trial
Free, no credit card required
30 parses; valid for 30 days
Pre-paid packages
Volume-based
Paid in advance; valid 1 year from payment; unused credits expire after 12 months
Custom Annual
Custom quote
Fixed-price arrangement via sales contact

Pricing was checked in August 2026 and described as usage/volume-based.

✓ Use This If
●Your resumes are mostly single-column or otherwise standardized PDFs.
●You need Indian phone numbers, Indian addresses, and LinkedIn captured automatically.
●You want structured JSON with certifications, hobbies, and other extra fields.
●You can post-process noisy competency levels and skill normalization downstream.
✕ Skip This If
●Your resumes are two-column or sidebar-heavy and schema routing must be exact.
●You need preserved skill categories or trustworthy proficiency levels for ranking.
●You need strict separation between certifications, skills, and references.
●You need every employer/title pair to be perfectly separated in messy work histories.
developer-toolsapisotherOther
Not in this test set. The Priya Sharma two-column resume was misclassified as a Job Order, which meant the parser returned job-style fields instead of a candidate profile and left the contact block empty.
No. On the Rugved Nichite resume, the categorized skills block was flattened into one PersonCompetency list, so the original Languages / AI-ML / Cloud / Frameworks / Databases structure was not preserved.
Not consistently. The clean resume returned 29 competencies, but every entry was labeled beginner, and the two-column resume showed blank competency levels.
Yes on the clean and messy single-column resumes. The report says it extracted +91 phone numbers and Indian city/state data correctly, but the multi-column resume lost those contact fields.
A free trial with 30 parses and no credit card, pre-paid volume packages, and custom annual quotes. The report did not list public dollar figures.

Banner Preview

How the embed badge will look on your site

Hireability featured on AI Demos

Embed HTML

Copy this code to your website source

<a target="_blank" href="https://aidemos.com/tools/hireability?utm_source=hireability_embed" style="width: 250px; height: 80px; border-radius:4px;" width="250" height="80"> <img src="https://aidemos-website-images.s3.amazonaws.com/featured.png" alt="Hireability | Featured on AI Demos" style="width: 250px; height: 80px; border-radius:4px;" width="250" height="80"> </a>

Quick Integration Guide

  • 1Copy the HTML code block above.
  • 2Paste it into your site's HTML or CMS editor.
  • 3Banner appears instantly on your page.
  • 4Links back to your tool profile here.
Similar Tools

Similar Tools

Discover more AI tools like Hireability to enhance your workflow.

🤖
Affinda
Affinda Review: AI Resume Parser Tested Across Resume Formats (2026)
AI Tool
🤖
Airparser
Parses clean, multi-column, and messy resumes into structured JSON, but email, title, and skill formatting still need validation.
AI Tool
🤖
Extracta.ai
AI Tool
🤖
Skima AI
Fast PDF resume parsing with dependable core fields and experience-year calculation, but weak structured output and supplemental coverage.
AI Tool
🤖
LlamaParse
Reliable PDF-to-Markdown conversion for hybrid reports, with strong hierarchy and table capture but weaker preservation of complex table semantics and embedded visuals.
AI Tool
🤖
Parseur
Template-driven resume parsing that returns predictable JSON after one-time setup.
AI Tool
🤖
HrFlow
HrFlow Review: AI Resume Parsing API Tested (2026)
AI Tool
🤖
OpenResume
Free browser resume parser that is handy for quick manual review on clean PDFs, but brittle field mapping and no JSON export make it unsuitable for API pipelines.
AI Tool
🤖
CVParserPro
Parses resume PDFs into structured candidate profiles quickly, but experience totals and education dates need manual review.
AI Tool
🤖
Docparser
Template-based resume parsing that works on one fixed layout, but breaks on varied resumes.
AI Tool
🤖
ResumeParser
AI Tool

Comments (0)

Please Log in to join the discussion.

Built by FutureSmart AI — the team behind AI Demos

Need a custom AI solution for this use case?

If you are looking to build a custom resume parsing, PDF extraction, or candidate data structuring system for your business or internal workflow, email us at contact@futuresmart.ai.

Get a custom build

Found something inaccurate or missing? We try to keep our AI research accurate and useful. If you found outdated information, an issue, or have a suggestion, email us at collaborate@aidemos.com.

Back to Top