evidoria

← Back to browse

Good practice Imported

PlanAI: AI-Summarised Public Consultation Analysis for Cambridge Planning

United Kingdom · Cambridge · See the United Kingdom profile · See the Cambridge profile

Evidence: Descriptive / self-reported Top 25% 73/100 · Ask Evidence Copilot about this practice

University of Liverpool and Greater Cambridge Shared Planning built PlanAI to summarise consultation responses. On 3 trial consultations it summarised 320 submissions in 16 minutes, versus 60+ hours of manual work.

320
Public submissions covered (three consultations)
16 minutes
Time for AI to generate all summaries and compendium report
60+ hours
Council planner time previously spent logging/summarising the same volume
18+ hours
Of which time spent on write-ups alone
PlanAI: AI-Summarised Public Consultation Analysis for Cambridge Planning

Details

Maturity
Pilot
Promoter
Greater Cambridge Shared Planning & University of Liverpool
Period
2024-2025
Keywords
urban planning, AI, public consultation, local government

Context

Greater Cambridge Shared Planning, the joint planning service for Cambridge City and South Cambridgeshire District Councils, partnered from October 2024 with the University of Liverpool's Department of Geography and Planning to build PlanAI, an AI tool for analysing public consultation responses, funded through the UK Government's PropTech Innovation Fund.

Activities

PlanAI was trialled on three live planning-guidance consultations — Cambridge Biomedical Campus, Planning Obligations, and Health Impact Assessments guidance — covering 320 public submissions. The tool generated a detailed summary of every individual submission plus a compendium report for all three consultations in 16 minutes.

Results

Council planners had previously spent over 60 hours logging and summarising the same volume of responses, including more than 18 hours on write-ups alone. An internal comparison found no noticeable difference between the AI-generated and human-written summaries.

Conclusions

Council officers stressed planners still read every individual submission before deciding, and Councillor Katie Thornburrow publicly cautioned that 'AI needs to be deployed carefully and responsibly.' The Local Government Association and UK Ministry of Housing, Communities & Local Government have since featured PlanAI as a model for wider adoption across England's planning system, though as of mid-2025 it remained a pilot limited to Greater Cambridge's own consultations.

Implementation
Indicative cost
Low (< €50k)
Time to results
Short (< 1 year)
Staffing & skills
Greater Cambridge Shared Planning officers, University of Liverpool Department of Geography and Planning (Prof Alex Lord, Prof Alex Singleton, Dr Mark Green), Council planners retaining final review of every submission

Conditions for success

  • PropTech Innovation Fund grant funding
  • Planners continuing to read every individual submission before deciding, rather than relying solely on AI summaries
  • Trial run on live, real consultations to test the tool

Common failure modes

  • Remained a pilot limited to Greater Cambridge's own consultations as of mid-2025, not yet adopted more widely despite LGA/Ministry endorsement
  • Comparison of AI vs. human summaries was an internal assessment, not an independent evaluation

Commonly funded by

National / regional programmes

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful