Correspondence Triage Automation Tool

Automating ministerial correspondence triage and processing

  • Publicly sourced

The challenge

Manual processing of ministerial correspondence was time-consuming and inefficient. Staff had to manually sort, categorise, prioritise, and route thousands of incoming emails and documents. The system lacked automated identification of high-priority, high-risk correspondence and meeting requests. Standard response matching was done manually. These manual processes created bottlenecks and potential delays in government response times.

The solution

The Correspondence Triage Automation Tool uses AI to automatically process incoming ministerial correspondence. The system can sort emails by which team should handle them, summarise the main points, and flag urgent items that need follow-up. It can also match emails with standard government response templates, saving staff from having to search manually. The AI predicts eight key pieces of information for each email: whether it needs follow-up, if it is high-risk, if it is requesting a meeting, which minister should respond, suggested standard responses, a summary of the content, what subject area it covers, and which team should handle it.

The results

The Correspondence Triage Automation Tool is currently live in production and has delivered significant efficiency improvements for HM Treasury's correspondence processing, including saving several hours of manual work per day.

Details

Organisation name
HM Treasury (HMT)
Government body
UK Government
User group
Civil servants
Use case type
Specific
Type of technology
Machine Learning
Phase
Live
Impact
Time savings / Improved efficiency

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: 27 September 2025