Skip to main content
lab-notes.aiPublic-service AI playbooks
Opportunity 10/17Citizen servicesCitizen services and government

Joined-up Support after a Life Event

Explore the fragmented steps people face after a bereavement and where a joined-up service would need stronger evidence.

Published sources
2
Starter data
16 synthetic records
Domain build partner
build-life-event-services
Last reviewed

From the draft strategy

Opportunity

The draft strategy names linked citizen services after a bereavement as a potential public-service application, notifying the relevant services so that someone has less to do at a hard time, without saying who authorises each notification, what gets shared, or how a mistake is put right.

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. nidirect

    Open

    Who to tell about a death

    What it covers
    The published guidance on what has to be done after a death in Northern Ireland: telling the family doctor, registering the death with the district registrar, finding the will, arranging the funeral, reporting the death to the Bereavement Service, and then the long list of tax, rates, vehicle, council, bank, pension, and utility contacts a person makes themselves.
    Why it matters here
    It is where this playbook's journey steps come from, in the order the guidance gives them, and the fact that most of them are separate contacts is the problem the strategy's example is pointing at.

    Open the source (opens in a new tab)

  2. Northern Ireland Statistics and Research Agency

    Open

    Registrar General Quarterly Report

    What it covers
    Provisional counts of life event registrations in Northern Ireland — births, deaths, stillbirths, marriages, and civil partnerships — for each three-month period.
    Why it matters here
    It is the only published measure of how many people are going through this journey, and it counts registrations rather than journeys, which is why nothing published says where anyone gets stuck.

    Open the source (opens in a new tab)

Starter data

Starter dataset

Synthetic working data

Use 16 synthetic journey steps to explore where delays or drop-off might occur after a bereavement.

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
16
Fields
5

Field preview

table view
  • id

    SYN-LE-01 · SYN-LE-02 · SYN-LE-03

  • lifeEvent

    Bereavement

  • journeyStep

    Tell the family doctor · Register the death with the district registrar · Find the will

  • medianDays

    1 · 3 · 5

  • dropOffShareBand

    under 5% · 5-15% · 15-30%

How it was prepared

AI authored fictional timings and completion bands around the sequence described in published nidirect guidance.

Limitations

  • The days and drop-off bands are invented because no published source measures either figure.
  • A tidy sequence cannot represent grief, disputed authority, complicated estates, or accessibility needs.
  • A named step does not establish that anyone has authority to complete it.

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-life-event-services
Codex
$build-life-event-services

Conditions, not a checklist

Before you build

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

  • Joining records creates risk

    Bereavement can connect identity, family, money, health, property, and legal circumstances across services.

  • Authority comes first

    A notification sent too early or without authority can cause distress, loss, or fraud exposure.

  • Matching errors disclose private information

    A wrong match can reveal a death or private circumstances to the wrong party.

  • Service design may be the real intervention

    Consent, accessible journeys, and systems working together matter before any model is considered.