Sector · HR & skills matching

A skills matching platform that helps supply and demand truly understand what skills mean.

We build custom skills-matching platforms for organisations that want to take matching between people, roles, projects and learning paths seriously: large employers with an internal talent marketplace, staffing agencies and recruiters who want to go beyond keyword matching, training institutes that want to link learning pathways to the labour market, and sector-specific labour market platforms for healthcare, engineering and construction. Built around ESCO and O*NET taxonomies, AI-driven, compliant with the EU AI Act, and with code ownership that stays with your organisation.

Use caseInternal talent marketplace
Use caseAI-driven recruitment
Use caseSkills gap & learning pathways
Use caseSector labour market platforms

The skills economy in numbers.

~14.000
Skills in the ESCO taxonomy (the EU standard for skills)
~17.000
Occupations in O*NET with underlying skill profiles
~70%
Of employers in EU studies report persistent skill gaps in core technologies
HIGH-RISK
AI Act classification for AI in recruitment and selection (Annex III, Art. 6)

Source: European Commission ESCO classification, U.S. Department of Labor O*NET, World Economic Forum Future of Jobs, Regulation (EU) 2024/1689 (AI Act).

Keyword matching was designed for yesterday's labour market.

Most matching systems in the Dutch market — both the large ATS packages and the in-house systems HR has built up over the years — still rely on some form of keyword matching: the CV contains the word "Python", the vacancy asks for "Python", and there's a hit. Anyone who has heard a hiring manager complain that the system produces too much noise knows the problem. The software doesn't understand that Pandas is part of Python, that data analysis in R is a closely related competence, or that five years as a senior data engineer at a SaaS scale-up implies a deeper skill set than a CV on which "Python" appears ten times.

On the other side of the market, the same problem plays out in mirror image. An internal employee on a talent marketplace receives no suggestions that match their actual skill profile, only roles that repeat the exact words from their CV. A learner at an education institute sees no learning pathways that fit their intended role. A care worker on a sector labour market platform sees no alternative positions at another care provider, even though their skill set overlaps seventy per cent with that role.

The other extreme — a large AI vendor such as Eightfold, Gloat or a comparable international player — requires you to fit your organisation into their template. Their taxonomy, their matching algorithm, their audit trail. Code ownership sits with them, your data too, and if the contract is breached your operation grinds to a halt. Since 2026 a complication has been added: AI in recruitment and selection is classified under the AI Act as HIGH-RISK, with documentation, bias-testing and audit obligations that you as the deployer must be able to demonstrate — not the vendor.

A custom skills-matching platform takes a different approach: the system follows your skills taxonomy, your ontology, your matching criteria and your audit requirements. We build that layer on top of proven taxonomies such as ESCO and O*NET, with a custom ontology layer where your organisation-specific roles, positions and projects have a place. For the AI layer, we draw on custom AI development and the custom LLM integrations we have delivered for other clients: vector embeddings for skill similarity, RAG for context-rich matches and a classic text-matching layer as a fallback.

Skills-matching software that suits every context.

Each context has a different audience, different taxonomy choices and different audit requirements. Below, per use case, is what we typically build — from internal talent marketplace to sector labour market platform.

Internal talent marketplace at large employers

At a large employer with multiple business units, locations or international departments, internal mobility is an underused channel. The vacancy is advertised externally while someone in another department already has exactly the required skill profile, but nobody knows it, because talent data is scattered across an HRIS, a learning platform, performance reviews and a few loose Excel files. An internal talent marketplace brings that data together around a skills layer: an enriched profile for each employee, a skills requirement for each open role or project, and an AI-driven match score with explainable reasoning in between.

Our module set for internal marketplaces is built around an employee skills profile that is enriched from the HRIS, learning platform, certifications and the employee's own self-assessment; an open role feed in which department managers publish vacancies and projects; and a match engine that proposes a prioritised list for each employee, with the option for the employee to explore anonymously or tentatively first. For the marketplace layer itself, we draw on our experience of building a marketplace platform: two-sided flows, moderation flows and transparent ranking.

What sets us apart from the Eightfolds and Gloats of this world: the system does not make the choice for the employee. It makes the choice visible, supports the manager with a well-founded shortlist, and leaves the employee in control. We build an audit trail of match decisions that records which skills were taken into account, what weight the algorithm assigned and which decision a human made. This keeps the organisation compliant with the AI Act and allows a rejected candidate to understand, at a later stage, why they did not progress.

  • Skills profile from multiple sourcesHRIS, learning platform, certifications, self-assessment: no more standalone forms.
  • Open role and project feedDepartment managers publish directly, with no detour via central HR.
  • Anonymous exploration modeEmployees look around first without the manager knowing who is looking.
  • Explainable match scoreEach match shows which skills count and with what weight.
  • Audit trail per decisionAI Act-compliant documentation of match and rejection decisions.

The skills-matching platforms we typically build.

The world of skills matching extends well beyond recruitment alone, and this is reflected in the types of platforms we deliver for clients. For one large employer, an internal talent marketplace is central: employees explore roles and projects across the group, department managers receive a well-founded shortlist from within the company before a vacancy is advertised externally, and HR gets, for the first time, an overview of where skills sit within the organisation and where the shortages are. These are often joined by secondment and project staffing flows, in which an employee temporarily works in another business unit without changing employer, and the system keeps track of recharging, the return route and skills development.

For staffing agencies, temp employment firms and recruitment agencies, we build an AI-driven matching platform between candidates and clients. Here the skills-matching layer meets the broader recruitment context, and we draw on our experience of building recruitment software to take it further. The candidate pool is larger, matching happens more often and speed matters more: a recruiter wants a prioritised shortlist within seconds of a vacancy coming in. This is where vector embedding architecture comes into its own. A CV and a vacancy text are translated into vectors in a semantic space, and their cosine similarity gives a richer picture of match relevance than any keyword search.

A skills-matching platform often works alongside an existing ATS: the recruiter keeps working in their ATS but receives a match score per candidate directly, with an explainable rationale and an audit trail for the AI Act. For clients with an established ATS stack, such as Bullhorn, Connexys, Recruitee or Homerun, we connect the matching platform through standard interfaces and keep the workflows in the ATS in charge. The skills layer enriches the ATS; it does not replace it.

A third group is training institutes and learning providers. Here the match is not about vacancies but about learning paths: given a target role or target skills profile, which modules will get the learner there fastest? Which certifications demonstrably carry weight in the labour market, and which modules are already mandatory for an occupational group under a collective labour agreement or statutory qualification requirements? We build these platforms so that a learner receives a skills gap analysis for each learning pathway, a recommended route and ongoing feedback. For institutes with a reintegration or retraining role, we link the gap analysis to a labour market feed: which jobs are opening up in a region that match this learning path?

A fourth group is sectoral labour market platforms and guilds. In healthcare, technical trades and construction, public-private platforms are emerging to tackle staff shortages at sector level. Here we work with multiple employers at once, a labour market fund that co-finances the work, a sectoral collective labour agreement that sets standards for roles and certifications, and an ambition to combine career changers, returners and internal progression. For healthcare, there is an NEN 7510 layer on top, and in many sectors an eIDAS signature flow for training certificates.

A final group is employer branding pages and talent communities. An employer builds an open community where professionals register with a skills profile, receive content that matches their career direction and, at a later stage, are matched to vacancies. The common thread: the software follows your taxonomy and your decision rules. Vendor-independent, AI Act-compliant, with code ownership sitting with your organisation.

Built within the laws that apply to matching, AI and HR data.

Skills matching touches several frameworks at once: the AI Act, the GDPR, sector-specific compliance and information security. We work within those frameworks from the first sprint, not as a last audit round before go-live.

AI Act: HIGH-RISK

Recruitment and talent matching under Annex III

The EU AI Regulation classifies AI used in recruitment, selection, task allocation and worker monitoring as HIGH-RISK (Annex III, Article 6 of Regulation (EU) 2024/1689). For you as a deployer, this means a risk management system, a data governance policy, technical documentation, logging, human oversight, transparency towards the candidate and a conformity assessment before production. We build that documentation layer in as an integral part of the system. See also our approach to custom AI development.

GDPR

Privacy by design for CV and skills data

CVs, skills, performance data and learning history are personal data, and their combination quickly amounts to profiling under Article 22 of the GDPR. We deliver a DPIA for each project, separate training and production data, minimise to the necessary fields, and build data subject rights (access, rectification, restriction, erasure) as first-class flows. Automated decisions without human involvement are prohibited under the GDPR; our platforms are built by default so that a human makes the final decision.

Bias evaluation

Structural testing for fairness and disparate impact

A matching algorithm trained on historical data risks reproducing historical inequality. We help build a bias evaluation pipeline that measures, with each release, whether the algorithm produces substantially different outcomes across groups: gender, age, surname origin and educational background. Where that is the case, we reweight features, revise training data or escalate to a manual decision. A build step in the release pipeline, not an ad hoc audit afterwards.

ESCO & O*NET

International skills taxonomies as a foundation

We use the European ESCO classification as the source taxonomy for the European labour market, and the US O*NET database as a rich supplement for competencies, tasks and related occupations. On top of that we add our own ontology layer, in which your organisation's specific job functions, roles, certifications and project types have a place, linked to ESCO/O*NET where possible. This provides multilingual support and alignment with public labour market platforms.

eIDAS

Qualified electronic signatures on certificates

For training institutes and sector platforms that issue certificates and statements of competence, we integrate eIDAS-compliant electronic signatures: qualified where the law requires it, advanced where that is sufficient. Certificates are stored in a machine-readable format, so they can be directly considered as evidence of a skill in a later matching process.

NEN 7510

Information security for healthcare contexts

For sector labour market platforms in healthcare, NEN 7510 is the framework for information security. We design within that framework: role separation, authorised access, logging where applicable, and readiness for certification at handover. For financial institutions and government, we align with ISO 27001.

Employee monitoring

No continuous assessment under the radar

The GDPR and the Dutch Works Councils Act are clear: continuous monitoring of employee performance is only permissible under strict conditions, with the consent of the works council and a well-founded legal basis. Our internal marketplaces only measure skills that are actively submitted and publicly visible performance data, and make it visible to the employee when their profile is enriched.

Ownership & source code handover

The taxonomy, models and data remain with your organisation

We deliver code, skills ontology and matching models in a repository managed by your IT organisation, which continues to exist without Appfront. No mandatory licences, no hidden hosting lock-ins on the embeddings store, no binding maintenance contract. We can handle hosting and fine-tuning — your choice.

Seamlessly connected to your HR, ATS and learning stack.

We integrate with the systems your organisation already uses. The skills-matching layer complements them and rarely replaces them. HRIS, ATS and learning platforms remain the sources of truth.

AFAS Profit
HRIS & payroll
Workday
Talent & HR
SAP SuccessFactors
HXM platform
Bullhorn
Recruitment ATS
Connexys
Recruitment ATS
Recruitee
Hiring platform
Homerun
Hiring & ATS
ESCO API
EU skills taxonomy
O*NET Database
Occupations & competences
OpenAI / Mistral
LLMs & embeddings
LinkedIn Talent API
External talent pool
Cornerstone / Moodle
Learning & LMS

Standard integrations, no project-specific connections.

We have standardised the integrations listed above across several skills-matching projects. For a new engagement, we set up the integration with the same abstraction layer: fewer bugs at the interfaces, a faster build phase, and a data architecture your own IT team can maintain. The integration layer is a mappable adapter, so a migration from Workday to SAP, or from Bullhorn to Recruitee, is a configuration change at the interface rather than a rebuild of the matching platform. For details, see our page on smart API integrations.

For the AI and embeddings layer we work model-agnostically: OpenAI, Mistral, Anthropic or a self-hosted open-source LLM. The choice depends on data residency requirements, cost profile and latency. For healthcare and government, a self-hosted model is often the right choice; for commercial recruiters, a hosted API often offers better value for money. For the embeddings store we work with pgvector, Pinecone or Weaviate, depending on data residency and your existing infrastructure. For broader context, our approach is set out on the page custom LLM integrations.

What sets us apart from the large AI vendors: wherever possible, the model weights, API credentials, embeddings store and taxonomy belong to your organisation. We configure and build, but we don't make Appfront indispensable in the chain. If your IT partner or LLM vendor changes, no hidden account runs on in the background, and the fine-tuning of the matching model moves with you to the new environment.

From taxonomy workshop to go-live, in clear steps.

A skills-matching project has its own rhythm. Five phases that are recognisable for every client, whether it concerns an internal talent marketplace, a staffing agency or a sector-wide platform.

01 · Audit

Taxonomy and data mapping

Workshops with HR, recruitment and the business: which skills matter, which roles exist, which data sources are available, which ESCO/O*NET mapping fits, and which organisation-specific ontology extensions are needed.

02 · Design

Model architecture and bias baseline

Which LLM, which embeddings store, which fallback path if the AI fails, and which bias tests are already part of the baseline. Plus: AI Act documentation structure, DPIA template and audit-trail schema.

03 · Build

Short sprints, demo every sprint

Each sprint we deliver a working flow that recruiters, talent managers and compliance officers can test. The first working match demo is up and running within a few sprints.

04 · Cutover

Pilot with one business unit or vacancy type

First one department or one role type, then broaden. At each rollout: training for recruiters and hiring managers, communication to employees and candidates, and handover to your functional management.

05 · Maintenance

Ongoing adaptation

We adapt the system with every ESCO update, AI Act guidance or new sector collective agreement. Ongoing bias monitoring, retraining on new data, and first-line support within the same working day.

What the sector says about AI-driven skills matching.

European Commission — ESCO

"The European skills, competences and qualifications classification ESCO provides a common language that strengthens mobility between sectors, countries and providers of education and employment — a foundation for digital matching applications on the European labour market."

World Economic Forum — Future of Jobs

"Half of all employees worldwide will need reskilling or upskilling in the coming years; organisations that seriously set up internal talent marketplaces and connect them to a skills graph retain more control over their position in the labour market."

AI Act — Regulation (EU) 2024/1689

"AI systems used for recruitment and selection, task allocation based on performance and monitoring of employees are classified as high-risk, with accompanying requirements for risk management, data governance, technical documentation and human oversight for the deployer."

Answers for the HR or talent director considering a custom solution.

The questions we hear most often from HR directors, talent managers and sector labour market platforms — answered from the practice of our own projects.

Why not a off-the-shelf package such as Eightfold, Gloat or a comparable international player?
For an organisation with a straightforward use case and few sector-specific rules, a SaaS vendor is often the right answer. We come into the picture when complexity increases: multiple business units with their own job-family structures, a sector-specific collective labour agreement with particular certification requirements, an internal ontology that doesn't fit ESCO, or an AI Act audit requirement that the vendor does not adequately cover. A second reason is ownership: with custom development, the code, the taxonomy, the embeddings and the hosting remain with your organisation. With a SaaS vendor, they sit on the vendor's side, including everything you build in terms of model fine-tuning on your historical data.
Can you integrate with our existing HRIS, ATS or learning platform?
Yes. We have standardised adapters for AFAS Profit, Workday, SAP SuccessFactors, Bullhorn, Connexys, Recruitee, Homerun and most common learning platforms. For less common systems, we build an adapter case by case. A later migration between vendors is a configuration change at the interface, not a rebuild. See also smart API integrations and, specifically, ATS system integrations.
How do you ensure the system complies with the AI Act?
AI in recruitment and selection is classified under the AI Act as HIGH-RISK (Annex III). For you as the deployer, this means a risk management system, a data governance policy, technical documentation, logging of decisions, human oversight and transparency towards the candidate. We build that documentation layer in as an integral part of the system: for each match decision, an audit trail showing which skills were weighed, which features the algorithm used and which decision a human ultimately made. A rejected candidate has the right to a meaningful explanation, and that explanation must come from the system itself, not from a later reconstruction.
How do you deal with bias and discrimination?
We build a fixed bias-evaluation pipeline into the release flow. For each new model version, we measure whether the algorithm produces substantially different outcomes across different groups, such as gender, age, surname-based ethnic origin and educational background. Where that is the case, we reweight features, revise the training data, or introduce a mandatory human check. We document this, including what the test measures, what the thresholds are and what the outcomes are, as part of the AI Act documentation. This is not a separate audit afterwards, but a build step in the pipeline of the matching model.
Which skills taxonomy do you use as a basis?
By default, we use ESCO as the source taxonomy for the European context, with O*NET as a rich complement at the level of competencies and tasks. On top of that, we add a custom ontology layer in which your organisation's specific job functions, roles, certifications and project types are captured, linked to ESCO/O*NET where possible. For sector platforms, we connect to qualification frameworks such as CREBO, NLQF and professional association registers. For multinationals, this provides multilingual support and international interoperability out of the box.
Do you work with LLMs and embeddings, or with classic matching?
Both, and that combination is what makes the difference. We build a vector-embeddings layer for semantic skill similarity, and a classic text-matching layer as a fallback and as a second opinion. For the LLM layer, we work model-agnostically: OpenAI, Mistral, Anthropic or a locally hosted open-source LLM. For contexts sensitive to data residency, a local model is often the right choice. Our approach is described on the page custom LLM integrations.
How do we arrange information security and compliance in a healthcare context?
For sector-specific labour market platforms in healthcare, NEN 7510 is the governing framework. We design and build the platform within that framework: separation of roles, access authorised per role, logging where applicable, and ready for certification on delivery. For the privacy layer, we combine this with GDPR-compliant flows for access, rectification, restriction and erasure. For certificates and statements of competence, we integrate eIDAS-compliant electronic signatures, qualified where the law requires it and advanced where that suffices, linked to a trust service provider of your choice.
Do you also build a talent marketplace for internal employees?
Yes, this is one of the most common applications. We build an internal talent marketplace with an enriched employee skills profile, an open-role and project feed to which department managers publish directly, and an AI-driven matching engine with explainable reasoning. Often with an anonymous browsing mode, so employees can explore opportunities without their manager knowing who is looking. For the marketplace layer, we draw on our experience of building marketplace platforms.
What does a custom skills-matching platform cost?
A tightly scoped first implementation (one role type, one HRIS integration, one business unit) is a different project from an organisation-wide rollout with multiple collective labour agreements, several ATS integrations and sector-specific audit requirements. We work with a fixed planning phase in which we clarify the scope. Only then do we give a concrete price for the complete build, including integrations, AI Act documentation and the bias evaluation pipeline.
How do you get started in an organisation without its own AI team?
With one use case and existing data. We run the taxonomy workshop, deliver the first pilot and set up a dashboard so that your HR or talent team can see the matching results for themselves. Only once the pilot has proven itself do we broaden the scope. An in-house AI team is not a prerequisite for starting. We deliver the software, monitoring and documentation in such a way that a mid-market IT department can take it over without having to build a complete AI stack. For the broader context, we work from our approach to custom AI development.
Share LinkedIn Email

Talk to us about your skills-matching platform.

A half-hour introductory conversation with your HR director, talent manager or sector executive. We listen, ask questions about your skills taxonomy, AI ambitions and compliance context, and suggest a first direction. No obligation.

Edit content