Skip to main content
lab-notes.aiPublic-service AI playbooks
Opportunity 07/17HousingHousing and communities

Housing Need and Service Insight

Explore what area-level quarterly figures can show about housing need and stock condition without using tenancy records.

Inspect starter dataSet up the build partner
Published sources
2
Starter data
20 synthetic records
Domain build partner
build-housing-insight
Last reviewed

From the draft strategy

Opportunity

The draft strategy names AI in housing for property management and tenant services as a potential public-service application, stating a broad opportunity without naming the service problem, the data it would use, or the decisions it must never make.

Where the draft says it

Table 2 — potential public-service applications

Read the draft strategy source (opens in a new tab)

Source register

Research already done

Real published source

We reviewed these published sources so you do not have to start from zero. Each source shows what it covers, how it can be accessed, and why it matters.

2 sources

  1. Department for Communities

    Open

    Northern Ireland Housing Statistics

    What it covers
    The annual compendium of Northern Ireland housing statistics, in sections on supply, energy, social renting demand, private renting demand, owner occupier demand, and household characteristics.
    Why it matters here
    Its social renting demand and energy sections are the published shape this playbook's synthetic records imitate: households and dwellings counted in groups by area, with nobody described.

    Open the source (opens in a new tab)

  2. Department for Communities

    Open

    Northern Ireland Housing Bulletin

    What it covers
    The quarterly bulletin covering social housing development activity, social housing demand, homelessness, and house sales and prices.
    Why it matters here
    It sets the quarter as the published period, which is the grain the synthetic records use, and shows that what reaches the public is counts of households and properties rather than anything about a tenancy.

    Open the source (opens in a new tab)

Starter data

Starter dataset

Synthetic working data

Use 20 synthetic quarterly rows across five area bands to explore service patterns without property, household, or tenancy records.

AI-assisted research helped identify and interpret the published sources. We then created a small, non-sensitive synthetic dataset shaped by the information those sources expose. It is for exploration—not evidence, training, or operational decisions.

Records
20
Fields
5

Field preview

table view
  • id

    SYN-HI-01 · SYN-HI-02 · SYN-HI-03

  • areaBand

    Urban area A · Urban area B · Mixed area C

  • quarter

    2025-Q1 · 2025-Q2 · 2025-Q3

  • waitingHouseholdsBand

    over 6000 · 3000-6000 · 1500-3000

  • stockConditionBand

    mostly band D · mostly band C or better · mostly band E or lower

Inspect all 20 recordsView repository file (opens in a new tab)Download JSON (opens in a new tab)

How it was prepared

AI authored fictional waiting-count and stock-condition bands for lettered areas across four quarters.

Limitations

  • The areas are letters and the bands are invented, so nothing here describes housing need or housing condition anywhere in Northern Ireland.
  • A banded count by area and quarter cannot show an urgent circumstance, and urgency is usually the thing that matters.
  • Condition and need are held here as two coarse bands, which is the safe choice and also removes almost everything a housing team would actually work from.

Clone and build

Domain build partner

Build with a domain-aware coding agent

Clone the repository, then ask your coding agent to load the skill that ships with it. The skill brings the opportunity, sources, starter data, known unknowns and constraints into the conversation before anything is proposed. It follows the open Agent Skills standard, so it works in Claude Code, Codex and any other agent that reads skills.

01 / Clone

git clone https://github.com/Hypership-Software/lab-notes.ai.git

02 / Invoke

Claude Code
/build-housing-insight
Codex
$build-housing-insight

Conditions, not a checklist

Before you build

These are not footnotes. They are conditions that any responsible prototype would need to address.

  • Housing records reveal sensitive circumstances

    Housing records can reveal finances, disability, household circumstances, address, and vulnerability, which is why this file counts households in bands and never describes one.

  • Recorded demand can hide barriers

    Recorded demand partly measures who managed to get recorded, so a low count can mean a barrier to reporting rather than less need.

  • Patterns must not judge households

    Service and maintenance patterns must not be turned round to judge a tenant or a household, and nothing here belongs anywhere near an allocation, eligibility, or enforcement decision.