# Analyse thousands of public-consultation responses fast

The UK's Consult tool themed 2,000+ responses for the Scottish Government; officials checked every theme.

Organisation: UK Government (i.AI, Humphrey suite); Scottish Government
Status: Deployed
Place: United Kingdom
Categories: Government & public services
Try it with: Claude, ChatGPT / OpenAI models, Gemini, Grok
Time to try: 30 minutes for a sample

## Why it matters

Governments ask citizens for views, but reading every response is slow and costly. Faster, checked analysis means more of what people say reaches the decision.

## How it works

Consult first proposes themes for each question, then maps every response to them. On the Scottish Government's consultation on non-surgical cosmetic procedures, the responses covered six questions; experts checked and refined the themes and, for this first live use, also reviewed every response manually (GOV.UK). In i.AI's evaluation, 60% of responses got exactly the same themes as human reviewers.

## Who it's for

Policy teams, regulators, councils and research agencies.

## The prompt

```
Below are anonymised responses, with IDs, to the consultation question: "[question]".

Stage 1: Read all responses and propose 6 to 12 themes. For each, give a one-line definition and two representative quotes of one sentence each. Then stop and wait for me to edit the themes.
Stage 2: When I reply, assign every response to one or more themes and output a CSV with response_id and themes.
Stage 3: Report the count and share of each theme, notable minority views, and responses that fit no theme.

Do not paraphrase quotes. Do not try to identify anyone.

[Paste responses with IDs]
```

## Caveats

Agreement with human reviewers was high, with some differences, and the tool was still in trial in May 2025; human review stays essential.

## Sources

BBC News and Civil Service World reported the trial independently, but the accuracy figures in all sources come from the government's own evaluation.

1. GOV.UK (DSIT): 2,000+ responses; six questions; experts checked themes; manual review. Government-built 'Humphrey' AI tool reviews responses to consultation for first time (https://www.gov.uk/government/news/government-built-humphrey-ai-tool-reviews-responses-to-consultation-for-first-time-in-bid-to-save-millions)
2. Incubator for AI (i.AI): Two-stage method; 60% exact match; F1 scoring. Evaluating Consult (https://ai.gov.uk/blogs/evaluating-consult-an-ai-tool-for-enhanced-public-consultation-analysis/)
3. GOV.UK: Transparency record; tasks call LLMs. DSIT: Consult (algorithmic transparency record) (https://www.gov.uk/algorithmic-transparency-records/dsit-consult)
4. BBC News: 2,000 submissions; 'nearly identical' results to human experts working in parallel; still in trial; humans in the loop. AI tool put to test sifting public views on botox and fillers (https://www.bbc.co.uk/news/articles/cpd4nxvw9lyo)
5. Civil Service World: Six questions; officials manually reviewed each of the 2,000 responses; F1 0.76; more evaluation before rollout. Civil service AI tool for consultation analysis passes first public test (https://www.civilserviceworld.com/professions/article/civil-service-ai-tool-for-consultation-analysis-passes-first-test)

Fact-checked: 16 Oct 2026

Page: https://escapevelocitysociety.com/picks/uk-consult-public-consultations

See Selected Projects: https://escapevelocitysociety.com/picks.md
