EGY-001

ILO PROSPECTS Egypt – Skills Profiling Application (SkillLab)

Download PDF
Egypt, Arab Rep. Middle East, North Africa, Afghanistan & Pakistan Lower middle income Pilot / Controlled Trial Phase Confirmed

International Labour Organization (ILO PROSPECTS Egypt); Association of Businessmen in Alexandria (ABA) (pilot delivery); Caritas (JSC delivery partner)

At a Glance

What it does Classification — Matching and recommendation
Who runs it International Labour Organization (ILO PROSPECTS Egypt); Association of Businessmen in Alexandria (ABA) (pilot delivery); Caritas (JSC delivery partner)
Programme ILO PROSPECTS Egypt – Skills Profiling Application (SkillLab)
Confidence Confirmed
Deployment Status Pilot / Controlled Trial Phase
Key Risks Model-related risks
Key Outcomes Tracer study (n=400): 64% used the app to create a CV; 61% found it very easy/easy to use; mixed perceived usefulness for job search and training identification.
Source Quality 5 sources — Other, Report (multilateral / development partner), Government website / press release

The ILO PROSPECTS Egypt Skills Profiling Application is an AI-driven career guidance tool developed by SkillLab, a social enterprise based in Amsterdam, the Netherlands, and deployed in Egypt through a partnership between the International Labour Organization (ILO) PROSPECTS programme, SkillLab, and the Association of Businessmen in Alexandria (ABA). The application was piloted between 2020 and 2021 to assist refugees and host community members in Egypt in identifying, articulating, and communicating their employable skills to potential employers, with the broader goal of facilitating labour market integration for displaced and disadvantaged populations.

The core AI functionality of the application centres on an automated skills interview powered by natural language processing (NLP), graph theory, and Bayesian machine learning. The system is built on the European Skills, Competences, Qualifications and Occupations (ESCO) classification framework, which contains approximately 13,485 skills mapped to 2,942 occupations. During the profiling process, users engage with an AI-driven conversational interface that guides them through a structured self-assessment of their work history, education, and competencies. The underlying machine learning pipeline uses NLP and graph theory to exploit intrinsic relations within the ESCO skill dataset, a hybrid collaborative recommender system to intelligently query the most promising skills from the full ESCO taxonomy, and Bayesian machine learning algorithms that adapt to each user's input as the interview progresses. These Bayesian optimisation algorithms balance between exploiting the existing ESCO dataset and exploring possible new trends not captured in existing data. All machine learning components run on Google Cloud Platform and are written in Python.

At the conclusion of the profiling process, the application generates three key outputs for each user: a comprehensive list of their identified skills, a list of potential occupations matching those skills, and a professionally formatted CV that faithfully reflects the user's indicated skills, experience, and education. The system also assesses role fit by comparing individual skill profiles against occupation requirements, and identifies training gaps where additional skills development would enable access to further occupational pathways. Employment counsellors and career guidance staff use these outputs to inform their advisory sessions with job seekers, making the system an advisory and decision-support tool rather than one that makes autonomous placement or eligibility decisions.

The pilot was conducted among approximately 400 beneficiaries in the governorate of Alexandria, Egypt. ILO PROSPECTS Egypt subsequently integrated the application into Job Search Clubs (JSCs) operated in partnership with Caritas, establishing 16 JSCs between August 2021 and January 2022 in Alexandria and Damietta for asylum seekers and refugees. In the JSC deployment, 303 participants successfully used the skill profiling tool and extracted professional CVs.

A tracer study conducted by the ILO three months after the initial pilot (published in 2022) collected direct feedback from the 400 pilot beneficiaries. The study found that 64 percent of participants used the application to create a CV, 61 percent found it very easy or easy to use, and results on perceived usefulness for job search and training identification were mixed. In the subsequent JSC deployment, 76 percent of surveyed participants rated the application as good or excellent in assisting them to identify their skills, more than 75 percent found it good or excellent for CV writing, 64 percent discovered new potential employment fields matching their skills, and 78 percent found the application user-friendly. Four months after the JSC project concluded, 88 participants had found employment in occupations including marketing, sales, nursery teaching, electrician, tailor, and clinic assistant.

The human oversight model is explicitly human-in-the-loop (HITL). The application outputs serve as advisory inputs for employment counsellors, who retain professional judgement over career guidance recommendations. No automated entitlement, benefit, or placement decisions are documented. The ILO tracer study recommends localisation of terminology, induction training for new users, employer outreach to increase awareness of the skills profiles, and longer-term evaluation before wider roll-out.

SkillLab won the Google AI Impact Challenge in 2019, receiving financial support to further develop its AI-based skills assessment technology. The platform was recognised in the IRCAI Global Top 100 AI for Sustainable Development Goals index. The implementing model involves SkillLab as the third-party technology provider, with the ILO PROSPECTS programme funding the deployment and ABA handling local pilot delivery. The application targets refugees, migrants, mature workers, informal workers, and youth not in employment, education, or training (NEET).

Classifications follow the DCI AI Hub Taxonomy. Hover over field labels for definitions.

Social Protection Functions

Implementation/delivery chain
Profiling, job matching and support services primary
SP Pillar (Primary) The social protection branch: social assistance, social insurance, or labour market programmes. Labour market programmes
Programme Name ILO PROSPECTS Egypt – Skills Profiling Application (SkillLab)
Programme Type The type of social protection programme, classified under social assistance, social insurance, or labour market programmes. View in glossary Job search assistance and placement services
System Level Where in the social protection system the AI is applied: policy level, programme design, or implementation/delivery chain. View in glossary Implementation/delivery chain
Programme Description ILO PROSPECTS Egypt programme deploying SkillLab's AI-driven skills profiling application to assist refugees and host community members in Alexandria and Damietta in identifying their skills, generating professional CVs, and receiving career guidance aligned with local labour market opportunities. Piloted with the Association of Businessmen in Alexandria (ABA) and subsequently integrated into Job Search Clubs operated with Caritas.
Implementation Type How the AI output is produced: Classical ML, Deep learning, Foundation model, or Hybrid. Affects validation, compute requirements, and governance profile. View in glossary Classical ML
Lifecycle Stage Current stage in the AI lifecycle, from problem identification through to monitoring, maintenance and decommissioning. View in glossary Integration and Deployment
Model Provenance Origin of the AI model: developed in-house, adapted from open-source, commercial/proprietary, or accessed via third-party API. View in glossary Commercial/proprietary
Compute Environment Where the AI system runs: on-premise, government cloud, commercial cloud, or edge/device. View in glossary Commercial cloud
Compute Provider The specific cloud or infrastructure provider hosting the AI system. Google Cloud Platform
Sovereignty Quadrant Classification of data and compute sovereignty: I (Sovereign), II (Federated/Hybrid), III (Cloud with safeguards), or IV (Shared Innovation Zone). View in glossary IV — Shared Innovation Zone
Data Residency Where the data used by the AI system is stored: domestic, regional, or international. View in glossary Not documented
Cross-Border Transfer Whether data crosses national borders, and if so, whether documented safeguards are in place. View in glossary Not documented
Decision Criticality The rights impact of the decision the AI supports. High criticality requires HITL oversight; moderate requires HOTL; low may operate HOOTL. View in glossary Low
Human Oversight Type Level of human involvement: Human-in-the-Loop (active review), Human-on-the-Loop (monitoring), or Human-out-of-the-Loop (periodic audit). View in glossary HITL
Development Process Whether the AI system was developed fully in-house, through a mix of in-house and third-party, or fully by an external provider. View in glossary Fully third-party developed
Highest Risk Category The most significant structural risk source identified: data, model, operational, governance, or market/sovereignty risks. View in glossary Model-related risks
Risk Assessment Status Whether a formal risk assessment, informal assessment, or independent audit has been conducted for this system. Not assessed

Risk Dimensions

Data-related risks
Governance and institutional oversight risks
Market, sovereignty and industry structure risks
Operational and system integration risks

Impact Dimensions

Equality, non-discrimination, fairness and inclusion
Systemic and societal
  • Human oversight protocol
CategorySensitivityCross-System LinkageAvailabilityKey Constraints
Unstructured and text-based contentPersonalSingle source (no linkage)Currently available and usedSelf-reported work history, education, and skills captured via AI-driven automated interview; quality depends on user recall and ability to articulate experience

IRCAI (n.d.) 'SkillLab', IRCAI Global Top 100 Outstanding Projects. Available at: https://ircai.org/top100/entry/skilllab/ (Accessed: 24 March 2026).

View source Other

International Labour Organization (2022). Tracer study: Skills Profiling Application in Egypt for refugees and host communities. Geneva: ILO PROSPECTS. Available at: https://www.ilo.org/publications/tracer-study-skills-profiling-application-egypt-refugees-and-host (Accessed 31 Oct 2025).

View source Report (multilateral / development partner)

International Labour Organization (2022). Tracer study: Skills Profiling Application in Egypt for refugees and host communities – Knowledge Product page. Geneva: ILO Skills and Lifelong Learning Platform. Available at: https://www.skillsforemployment.org/knowledge-product-detail/5889 (Accessed 31 Oct 2025).

View source Report (multilateral / development partner)

International Labour Organization (n.d.) 'Assisting refugees and host communities in Egypt to turn their skills into careers'. Geneva: ILO PROSPECTS. Available at: https://www.ilo.org/global/programmes-and-projects/prospects/countries/egypt/WCMS_779051/lang--en/index.htm (Accessed: 24 March 2026).

View source Report (multilateral / development partner)

SkillLab (n.d.) 'Empowering Young Refugees to Find Decent Work in Egypt'. Amsterdam: SkillLab. Available at: https://skilllab.io/en-us/news/ilo-caritas-refugees-egypt (Accessed: 24 March 2026).

View source Government website / press release
Deployment Status How far the system has progressed into real-world operational use, from concept/exploration through to scaled and institutionalised. View in glossary Pilot / Controlled Trial Phase
Year Initiated The year the AI system was first initiated or development began. 2020
Scale / Coverage The scale and geographic or population coverage of the deployment. ~400 beneficiaries in initial pilot (Alexandria); 303 additional participants in JSC deployment (Alexandria and Damietta)
Funding Source The source(s) of funding for the AI system development and deployment. ILO PROSPECTS programme (funded by the Government of the Netherlands)
Technical Partners External technology vendors, academic partners, or development partners involved. SkillLab (Amsterdam, Netherlands) – provider of the AI-driven skills profiling application; Google AI Impact Challenge winner (2019).
Outcomes / Results Tracer study (n=400): 64% used the app to create a CV; 61% found it very easy/easy to use; mixed perceived usefulness for job search and training identification. JSC deployment (n=303): 76% rated app good/excellent for skills identification; 75%+ good/excellent for CV writing; 64% discovered new employment fields; 78% found app user-friendly; 88 participants found employment within 4 months of project end.
Challenges ILO tracer study recommends localisation of terminology, induction training for new users, employer outreach to increase awareness of skills profiles, and longer-term evaluation before wider roll-out. Mixed perceptions of usefulness for job search suggest need for stronger linkage to employer-side demand.

How to Cite

DCI AI Hub (2026). 'ILO PROSPECTS Egypt – Skills Profiling Application (SkillLab)', AI Hub AI Tracker, case EGY-001. Digital Convergence Initiative. Available at: https://socialprotectionai.org/use-case/EGY-001 [Accessed: 1 April 2026].

Change History

Created 30 Mar 2026, 08:38
by v2-import (import)