Analyzing citizen feedback is a vital task for the UK Department for Transport (DfT), which manages around 55 public consultations each year. These consultations often generate more than 100,000 open-ended responses, creating incredible data challenges that previously required teams to spend months manually reviewing and categorizing themes. To adhere to the principle of publishing consultation responses within 12 weeks and derive insights more quickly, the DfT needed a new approach.
To solve this, the DfT’s AI and Data Science team worked 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 categorize themes from large amounts of public feedback in just a few hours. In the past, this was a process that often took months. The solutions evaluated achieved up to 90% accuracy in analysis (using a variety of measures), enabling the government to respond faster to the public while saving up to £4 million a year (DfT, 2025). For example, CAT helped analyze public comment responses to the Integrated National Transport Strategy and improve driving test booking rules.
The department’s innovation extends beyond public consultation. DfT has also developed connected tools to help city planners make more sustainable infrastructure decisions using Google Cloud services such as Cloud Run, Cloud CDN, and Firestore. In addition, AI Correspondence Drafter creates first drafts of answers to common questions by using Vertex AI Search to retrieve relevant policy information from a secure internal database (hybrid search) and Gemini for drafting. The potential for AI to transform transportation efficiency is enormous, but it must be done responsibly. The DfT uses AI to crunch data at scale, while putting human judgment at the heart of all policy.
Using a “human-involved” model ensures that AI output is checked for accuracy, fairness, and bias. This has also been found to be important in a public survey by the DfT. Google Cloud will provide the processing power, but the vision and final decisions will be made by DfT policy experts. This transparent approach ensures that technology serves the public good while contributing to a more efficient future for the nation’s transportation system.
To learn more about how Google Cloud helps public sector organizations accelerate their missions, visit our solutions page.
