evidoria

← Back to browse

Good practice Imported

PlanAI — Greater Cambridge's AI Tool Cuts Planning-Consultation Analysis From 18.5 Hours to 16 Minutes

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

Greater Cambridge Shared Planning and the University of Liverpool built PlanAI, a large language model trained on 15 years of planning consultations, to summarise public responses to Local Plan documents — cutting one trial's analysis time from 18.5 hours to 16 minutes.

18.5 hours
Consultation analysis time, manual
16 minutes
Consultation analysis time, PlanAI
5
Councils in extended pilot (by Jul 2026)
PlanAI — Greater Cambridge's AI Tool Cuts Planning-Consultation Analysis From 18.5 Hours to 16 Minutes PlanAI — Greater Cambridge's AI Tool Cuts Planning-Consultation Analysis From 18.5 Hours to 16 Minutes

Details

Maturity
Scaling
Promoter
Greater Cambridge Shared Planning (Cambridge City Council & South Cambridgeshire District Council), with the University of Liverpool
Period
2024-2026
Keywords
local government, urban planning, generative AI, public consultation

Context

Local Plan consultations generate thousands of public comments that planning teams must read and summarise, a labour-intensive bottleneck for councils.

Activities

Greater Cambridge Shared Planning and University of Liverpool academics built PlanAI, a large language model trained on 15 years of consultation data (55,000+ representations, 40,000+ planning terms), funded by the government's PropTech Innovation Fund.

Results

In an initial trial across three live consultations, PlanAI produced detailed summaries plus a compendium report in about 16 minutes, versus roughly 18.5 hours manually — about a 90% reduction in analysis time. By July 2026 the pilot extended to five further councils.

Conclusions

MHCLG's account is pilot-stage efficiency evidence from the tool's developers and partner councils, not an independently audited study, and does not report accuracy or error rates against a human baseline.

Implementation
Indicative cost
Low (< €50k)
Time to results
Medium (1–3 years)
Staffing & skills
Greater Cambridge Shared Planning, University of Liverpool (Lord, Singleton, Green)

Conditions for success

  • large historical training corpus of past consultation responses
  • government PropTech Innovation Fund backing

Common failure modes

  • no accuracy/error-rate data against a human baseline
  • efficiency figures self-reported by developers and partner councils

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