UK Department for Transport uses Google Cloud AI to analyze 100,000+ public responses

UK Department for Transport accelerates public policy insights with Google Cloud AI

The UK Department for Transport (DfT) is using Google Cloud's generative AI and Gemini models to accelerate public consultation analysis, saving up to £4 million annually. For the UK's Department for Transport (DfT), which manages approximately 55 public consultations each year, analysing citizen feedback is a monumental task. These consultations often generate more than 100,000 free-text responses, creating a staggering data challenge that historically required teams to manually review and classify themes over several months. To help meet the principle to publish consultation responses within 12 weeks and unlock insights faster, the DfT needed a new approach. To solve this, the DfT's AI and Data Science Team collaborated with Google Cloud and the Alan Turing Institute to build the Consultation Analysis Tool (CAT). Built on Google's Vertex AI platform, the CAT system uses Gemini models to identify and categorise themes from massive volumes of public feedback in just a few hours -- a process that previously often took months. The evaluated solution has achieved up to 90% accuracy (various measures used) in its analysis, enabling the government to respond to citizens faster while saving up to £4 million annually (DfT, 2025). For example, the CAT supported the analysis of public comments responses to the Integrated National Transport Strategy and improving driving test booking rules. The department's innovation extends beyond public consultations. Using Google Cloud services like Cloud Run, Cloud CDN and Firestore, DfT also developed a Connectivity Tool to help urban planners make more sustainable infrastructure decisions. Additionally, the AI Correspondence Drafter produces first drafts of responses to public inquiries by using Vertex AI Search to retrieve relevant policy information from secure internal databases (hybrid search) and Gemini for drafting. The potential for AI to transform transport efficiency is immense, but it must be done responsibly. The DfT is utilizing AI to process data at scale while keeping human judgment at the heart of every policy. By using a "human-in-the-loop" model, they ensure AI outputs are checked for accuracy, fairness and bias, something DfT research with the public also identified as important. Google Cloud provides the processing power, but the vision and final decisions come from DfT policy experts. This transparent approach ensures that technology serves the public interest while contributing to a more efficient future for the nation's transport system. To learn more about how Google Cloud is helping public sector organizations accelerate their missions, visit our solutions page.

UK Department for Transport turns to Gemini to analyze public feedback

The UK Department for Transport (DfT) has developed a Consultation Analysis Tool (CAT) in partnership with Google Cloud and the Alan Turing Institute to enhance the analysis of public feedback from consultations. The tool addresses the challenge of managing approximately 55 public consultations annually, which generate over 100,000 free-text responses. Historically, analyzing this feedback required months of manual review. The DfT aims to publish consultation responses within 12 weeks, significantly speeding up the feedback process. The CAT, built on Google's Vertex AI platform, utilizes Gemini models to categorize themes from large volumes of feedback in just a few hours, achieving up to 90% analysis accuracy. This efficiency allows the government to respond more quickly to citizens and is projected to save the DfT up to £4 million annually by 2025. One application of the CAT includes analyzing public comments related to the Integrated National Transport Strategy. Additionally, the DfT has created a Connectivity Tool with Google Cloud services to assist urban planners in making sustainable infrastructure decisions. The DfT also introduced an AI Correspondence Drafter that generates initial drafts for public inquiries by leveraging Vertex AI Search and Gemini for drafting. The use of AI aims to transform transport efficiency while ensuring responsible implementation with human oversight. By employing a "human-in-the-loop" model, the DfT ensures that AI outputs undergo checks for accuracy, fairness, and bias. Research indicates that the public values these factors in AI outputs. Google Cloud supplies the computational power, while final policy decisions rest with DfT experts. This approach aims to ensure that technological resources serve the public interest and improve the nation's transport system.