Feature Information

How does AI Skills Matching Work?

The AI Skills Matching feature utilises a large language model (LLM) generative AI system to assess a job applicant’s suitability by comparing their resume or CV against a job description.

This evaluation is performed through a two-step process:

1. The AI system analyses the job description to extract relevant skills, assigning importance weightings based on AI inference. Users have the option to review and modify the skills inferred from the job description and adjust the importance weightings before candidates are matched.
2. When a candidate applies, the AI system analyses their resume in a single operation that simultaneously extracts the candidate's skills and maps them against the job's skills. Matching is evidence-based: a candidate skill is only mapped to a job skill when there is clear, specific evidence in the resume. A deterministic scoring algorithm then calculates the overall match score, applying weighted tiers that prioritise the most critical job skills. The system also generates a short narrative summarising the candidate's skills fit for the role. Candidates are classified into one of five outcomes: Excellent Match, Good Match, Potential Match, Poor Match, and Not a Match.

Separation of concerns

The LLM is strictly used as a semantic extraction engine to identify skills within a job description and a resume. It does not calculate the match or make the final suitability decision.

Deterministic scoring

The actual match score is computed by a deterministic mathematical algorithm, not a predictive AI model. Because this scoring logic is code-based and rules-driven, it does not suffer from training-data overfitting. The logic remains consistent and repeatable across all candidates.

Constraints and guardrails

The AI Skills Matching feature is constrained to map candidate skills to job skills only when explicit, text-based evidence is present in the resume.

What are appropriate ways of using AI Skills Matching?

It is important to note that LLMs are fundamentally probabilistic and can produce variable results. The AI Skills Matching feature is intended solely as an evaluative tool to support our customer’s recruiters and hiring managers during the recruitment process. The classifications produced by the AI Skills matching feature are limited to the job skills matched against the resume skills, and do not take into account other factors used in human decision-making.

The AI Skills Matching evaluation should not be used as the sole basis or most important factor for making decisions about a job applicant's recruitment, and should not be used to overrule human decision-making.

LLM Model

The AI Skills Matching feature is built on AWS’s Amazon Bedrock LLM (Anthropic based models). Amazon Bedrock doesn't store or log prompts and completions, and doesn't use prompts and completions to train any AWS models and doesn't distribute them to third parties. AWS is a current PageUp subprocessor.

Independent AI Assurance

PageUp engages Warden AI as an independent third-party to provide continuous assurance over the AI Skills Matching feature. The program includes monthly bias audits covering sex bias, race/ethnicity bias, and intersectional (sex × race/ethnicity) bias, post-market monitoring, and transparent reporting. Current audit results, including PageUp's NYC Local Law 144 bias audit report, are available on PageUp's Warden AI assurance dashboard at https://trust.warden-ai.com/pageup. 

Australia

Automated Decision Making

From 10 December 2026, entities regulated by the Australian Privacy Act 1988 and the Australian Privacy Principles ("APPs"), must ensure their privacy policies contain information about automated decision making which may significantly affect individuals’ rights or interests. This requirement extends to computer programs which do a thing that is substantially and directly related to making such a decision.

PageUp's AI Skills Matching feature utilizes an applicant's personal information – CVs/resumes – to aid our customers in making hiring or recruitment decisions. Consequently, this process may fall under the scope of APPs 1.7 and 1.8, referred to as the "Automated Decisions APPs".

PageUp offers the following information to assist customers align their privacy policies with the requirements of the Automated Decisions APPs.

Personal Information Used by AI Skills Matching

The AI Skills Matching feature may utilize personal information found in resumes and CVs. This could include:

• Name
• Employment history
• Educational history
• Professional and educational certifications
• Interests and hobbies
• Current and former address
• Email address
• Phone number.

Decisions Supported by AI Skills Matching

Our customers are assisted by the AI Skills Matching feature in making decisions, including:

• Recruitment process decisions
• Hiring decisions
• Remuneration decisions
• Promotion decisions.

Europe

United Kingdom

The United Kingdom does not currently have a standalone AI Act. Regulation is managed through a sector-specific approach, where existing regulators apply established legal principles to the use of emerging technologies.

European Union

We are tracking the implementation of the EU AI Act to inform our global best practices, ensuring our customers benefit from the robust safety and transparency measures established by this leading international framework.

United States of America

California

From 1 Oct 2025, new regulations take effect to address employers' lawful use of artificial intelligence and automated-decision systems under California's Fair Employment and Housing Act.

We note that it is unlawful for an employer or other covered entity to use an automated-decision system or selection criteria (including a qualification standard, employment test, or proxy) that discriminates against an applicant or employee or a class of applicants or employees on the basis of a protected characteristic.

The results of PageUp's continuous independent anti-bias testing — see Independent AI Assurance above — may be relevant to potential claims or defences available under the regulations. Customers may also request the underlying audit reports. 

Colorado

From 1 January 2027, Colorado's Automated Decision Making Technology ("ADMT") Act imposes obligations on a "Developer" of a covered ADMT. As a potential Developer of a covered ADMT, PageUp makes the following documentation available to its customers who may be classified as a "Deployer" of a covered ADMT.

PageUp will notify customers of material updates, intentional and substantial modifications, and changes to intended use, limitations, or risk mitigation for the AI Skills Matching feature within a reasonable time, via PageUp’s Knowledge Portal.

Statutory Statement on Uses and Harms of the AI Skills Matching Feature

The AI Skills Matching feature is intended solely as an evaluative tool to support our customers’ recruiters and hiring managers during the recruitment process. The classifications produced by the AI Skills Matching feature are limited to the job skills matched against the resume skills, and do not take into account other factors used in human decision-making.

The AI Skills Matching evaluation should not be used as the sole basis or most important factor for making decisions about a job applicant's recruitment, and should not be used to overrule human decision-making.

Known inappropriate uses of the AI Skills Matching feature include: using the classification as a sole or determinative factor in a recruitment decision; using it to overrule recruiter or hiring manager judgement; and using it outside of recruitment triage (for example, for remuneration setting, performance management, or termination decisions). 

Statutory Disclosure on Training Data, Limitations, Purpose, and Intended Uses of the AI Skills Matching Feature

The AI Skills Matching feature is built using pre-trained Large Language Models via AWS Bedrock; PageUp does not use customer data to train or fine-tune these models. PageUp relies on AWS Bedrock's published model documentation; training-data categories beyond that are not disclosed by the foundation-model providers. Customer data processed by the feature, such as information from resumes or job descriptions, is not stored, logged, or used by AWS to train its underlying models. 

The AI Skills Matching feature works with objective, job-related characteristics, such as relevant career experience, skills, and qualifications, to generate a qualitative evaluation which aims to predict how a given applicant fits the job skills criteria. This helps recruiters and hiring managers to triage applicant profiles when deciding whether or not to move a candidate forward in a recruitment process. When used correctly, the AI Skills Matching feature can increase recruitment process efficiency and reduce recruitment costs for employers. The AI Skills Matching feature does not replace human decision making and cannot make informed hiring decisions.

The AI Skills Matching evaluation is applied to all candidates equally, regardless of their demographic or other protected characteristics; no candidate demographic or biometric information is used by the feature to generate its evaluation.

Illinois

From 1 Jan 2026, amendments to the Illinois Human Rights Act (HB 3773) take effect to address employers' lawful use of artificial intelligence in employment decisions. We note that it is unlawful for an employer to use artificial intelligence that has the effect of subjecting applicants or employees to discrimination on the basis of protected classes, or to use zip codes as a proxy for protected classes. 

The amendment also requires employers to provide notice to candidates when artificial intelligence is being used for recruitment or hiring purposes. PageUp customers meeting the statutory definition of "employer" in Illinois are responsible for providing the required notice to candidates regarding the use of the AI Skills Matching feature. To support compliance with the anti-discrimination provisions, the AI Skills Matching feature evaluates candidates based strictly on objective, job-related skills and does not process candidate demographic information, biometric data, or geographic indicators such as zip codes. 

We advise customers to independently monitor the Illinois Department of Human Rights' ongoing rulemaking process, as specific regulatory requirements regarding the circumstances, timing, and means of providing this notice are currently in development.

New York City

New York City Local Law 144 (LL 144) prohibits employers and employment agencies from using an automated employment decision tool (AEDT) to substantially assist decision making unless conditions are met. To "substantially assist" decision making is defined by the regulation to mean the AEDT is used as the sole, overriding or most important factor in decision making.

PageUp recommends against using the AI Skills Matching feature as the sole, or most important factor when making recruitment decisions, or using the AI Skills Match to overrule human decision making.