The OECD.AI Policy Navigator

Our policy navigator is a living repository from more than 80 jurisdictions and organisations. Use the filters to browse initiatives and find what you are looking for.

RASID


Added by:   OECD analyst
Added on:   11 Sep 2026
Updated by:   OECD analyst
Updated on:   11 Sep 2026

undefined
RASID is an AI-powered inspection system developed by the Saudi Food and Drug Authority to support inspectors at border checkpoints. The system analyses images of medicines carried by travelers to detect controlled substances and verify compliance with regulatory rules. It improves inspection speed, accuracy, and consistency while protecting public health and preventing misuse of restricted drugs.

Name in original language

راصد

Initiative overview

RASID is an artificial intelligence–based regulatory system developed by the Saudi Food and Drug Authority (SFDA) to support inspectors at border checkpoints in identifying controlled medicines carried by travelers. The system uses AI technologies to analyse images of medicine packages and automatically extract relevant information such as drug name, quantity, and dosage, and is designed to handle a wide variety of medicines across different brands, formulations, and packaging types.

The initiative addresses a key operational challenge in drug inspection processes, where inspectors previously relied on manual checks and personal expertise, leading to inconsistent decisions, longer processing times, and potential errors in identifying controlled substances. RASID reduces this dependency by providing a standardized, AI-driven approach that enhances accuracy and decision consistency.

Key features of the system include:

  • Automated detection of controlled medicines using image analysis
  • Comparison against official controlled substances lists
  • Verification of prescriptions and medical reports
  • Assessment of whether the quantity carried is reasonable based on medical need and duration of stay
  • Real-time alerts for restricted or non-compliant medicines

By automating several manual inspection tasks, the system significantly improves operational efficiency, reduces reliance on individual experience, and ensures consistent regulatory decisions. During its pilot phase, the system demonstrated a significant reduction in inspection time and improved accuracy in identifying controlled medicines.

RASID also has strong potential for scalability and replication. The solution can be extended to other entry points, integrated with additional regulatory databases, and adapted for use in other government sectors or countries facing similar inspection challenges. It represents a scalable AI solution that enhances border inspection processes and supports public health protection.

RASID has been awarded the SDAIA “Aware” badge in recognition of its alignment with ethical AI principles and responsible AI practices. The initiative follows national guidelines for trustworthy artificial intelligence and demonstrates the commitment of the Saudi Food and Drug Authority (SFDA) to deploying AI systems that respect transparency, safety, and ethical standards while supporting regulatory operations and protecting public health.

Other relevant details

Results, outcomes and impacts: RASID has demonstrated significant operational improvements in drug inspection processes. The average inspection time was reduced from approximately 20–50 minutes to around 3 minutes per case, representing an improvement of about 118%. The system also achieved high accuracy in identifying controlled medicines and improved the consistency of regulatory decisions. In addition, the initiative enhanced the overall experience for both inspectors and travelers by accelerating inspection procedures and enabling inspectors to focus on more complex cases. User feedback indicated high levels of satisfaction with the system’s performance, usability, and reliability. Challenges and lessons learned: One of the key challenges during development was ensuring that the AI system could accurately recognise medicines from images captured in real inspection environments, where lighting conditions and image quality may vary. In addition, enabling the system to support inspectors’ workflows and process medicines across multiple languages posed a significant challenge, requiring the model to understand diverse drug names, labels, and packaging formats. Another important aspect was equipping the system with an understanding of pharmaceutical contexts, including drug classifications, dosages, and regulatory requirements, to ensure accurate and reliable analysis aligned with real-world inspection practices.

About the policy initiative


Category:

  • AI policy initiatives, programmes and projects

Initiative type:

  • AI use cases/projects in the public sector

Status:

  • Active

Start Year:

  • 2025

OECD AI Principles:


Other relevant urls:


Images: