Digital Sensitivity Review (DSR) System

Accelerating sensitivity review for government document archiving

  • Publicly sourced

The challenge

The FCDO faced the critical challenge of reviewing massive volumes of government documents for sensitivity before public release to The National Archives, with the exponential growth in digital technologies creating an overwhelming increase in files requiring review that threatened to surpass the capacity of traditional manual review processes.

The solution

The Digital Sensitivity Review (DSR) System uses machine learning to automatically identify potentially sensitive content patterns and suggest redactions for reviewer approval. The AI-powered system was trained on past reviewer decisions and guidance, enabling it to pre-identify areas of known sensitivity while maintaining human oversight for complex cases requiring judgment.

The results

Operational since April 2019, with development since 2018, the DSR System has delivered significant efficiency and risk reduction improvements:

  • Only 10% of traditional sensitivity review effort required for processing documents
  • Reduced risk of sensitive content release to well below what was achievable without the technology
  • Eliminated need for rapid team expansion to meet growing demands for digital review

Details

Organisation name
Foreign, Commonwealth & Development Office (FCDO)
Government body
UK Government
User group
Civil servants
Use case type
Reusable
Type of technology
Machine Learning
Phase
Live
Impact
Improved efficiency / Time savings

Links

Get in touch

Email ai-knowledge-hub@dsit.gov.uk to:

  • find out how to use or collaborate on this tool
  • review content for this tool
  • talk to us about your own tool

Content created: 13 September 2025