Overview

Your government services,
handled for you

An AI agent that understands government so you don't have to. One conversation, every department, nothing missed.

The Agentic Legibility Stack is two products that work together: a citizen app where an AI agent acts on your behalf across every government department, and a Legibility Studio where departments make their services ready for agents to understand and deliver.

This is not a technology proposal. It is an operating model for how citizens interact with government in an age of AI agents.

  1. 1The problem today
  2. 2Two products, one system
  3. 3What citizens get
  4. 4What departments get
  5. 5How they connect
  6. 6Why it is safe
  7. 7The future: your agent, your choice
1

The problem today

Government has over 1,500 services across dozens of departments. When something significant happens in your life, it is your job to find them, understand them, and deal with each one separately.

Today

  • You search GOV.UK, guess which service you need, and hope you find the right one
  • You fill in the same personal details on every form — name, address, National Insurance number, again and again
  • Nobody tells you about services you are entitled to but did not know existed
  • If your situation crosses departments, you navigate each one alone
  • There is no record of what you were told, why, or what happened next

With an agent

  • You describe your situation in plain language and the agent identifies every relevant service
  • Your verified data is used once — the agent fills in forms across departments for you
  • The agent proactively surfaces services you are eligible for but would never have found
  • One conversation spans every department involved in your life event
  • Every action is recorded: what was done, by whom, why, and with your explicit consent
1,500+
Government services
16
Major life events mapped
12×
Same data re-entered per life event
£23bn
Estimated unclaimed entitlements
2

Two products, one system

For agents to work on behalf of citizens, two things must be true: the citizen needs a trustworthy agent, and government services need to be understandable by that agent. These are two different products for two different users, designed to work together.

Citizen App

For citizens and the people who help them

  • Tell your agent what is happening in your life, in your own words
  • Review a plan of every service you need, across every department
  • Give consent for each service individually — nothing happens without your approval
  • Delegate to the agent or act yourself — you choose, service by service
  • Get a receipt for everything — what was submitted, when, and to whom

Legibility Studio

For departments and service teams

  • Describe your services in structured artefacts that any agent can read
  • See which of your services are agent-ready and which have gaps
  • Audit every agent interaction with your services — full evidence trail
  • Replay any citizen journey step by step for complaints or oversight
  • Track case volumes and completion rates across your service portfolio
The key idea: the citizen app and the Legibility Studio are two halves of the same system. The citizen side consumes what the department side publishes. Neither works without the other. Together, they create a new channel for government services — one where AI agents act on behalf of citizens, safely and accountably.
3

What citizens get

A single app where an AI agent handles government on your behalf. You stay in control of every decision. The agent does the work.

One conversation, every department

Describe what is happening in your life — bereavement, having a baby, losing a job — and the agent identifies every service you need across every government department. No more searching GOV.UK.

A plan, not a list

The agent builds an ordered plan showing which services come first, which depend on others, and which you can skip. You see the full picture before anything happens.

Your data, entered once

Verified credentials from your GOV.UK Wallet — driving licence, National Insurance number, passport — pre-fill forms across departments. You enter your details once, not twelve times.

Consent on your terms

Before the agent shares any information or submits anything on your behalf, you see exactly what will be sent, to whom, and why. Nothing happens without your explicit approval.

Delegate or do it yourself

For each service, choose: let the agent handle it entirely, or step through it yourself. Parents can act for children. Executors can act for the deceased. Carers can act for those they support.

Receipts for everything

After every submission, you get a receipt: what was sent, when, to which department, and the reference number. A complete, auditable record of everything your agent did.

Citizen app — Bereavement triage in chat
My husband passed away last week. I don't know where to start with everything.
I'm very sorry for your loss. I can help you with the services you'll need. Based on what you've told me, I've identified 9 services across 5 departments that are relevant to your situation. Would you like me to show you a plan?
Yes please.
Citizen app — Service plan for bereavement
1
Register the death
General Register Office
Agent will complete ~15 min
Delegate
2
Tell Us Once
DWP
Agent will notify 9 departments ~5 min
Delegate
3
Apply for Bereavement Support Payment
DWP
Agent will check eligibility and apply ~10 min
Delegate
Apply for probate
HMCTS
Requires: Register the death
Delegate all to agent

The plan shows which services are ready to begin, which are locked behind prerequisites, and how long each will take. The citizen delegates as much or as little as they want.

4

What departments get

A tool for authoring service artefacts, publishing them for agents, and monitoring how those agents deliver your services to citizens.

Service legibility

Define each service with four structured artefacts: a manifest (what the service is), a policy ruleset (who is eligible), a state model (the journey steps), and a consent model (what data is needed). Any agent can then understand and deliver your service.

Gap analysis

See at a glance which of your department's services have complete artefacts, which are partially described, and which are not yet agent-ready. Prioritise the highest-impact services first.

Evidence and accountability

Every agent interaction with your services is recorded: what data was accessed, what consent was given, what was submitted, and what the outcome was. Replay any journey for complaints or oversight.

Legibility Studio — Department gap analysis
Your department's services
47
Total services
8
Agent-ready
12
Partially described
27
Not started
Universal Credit
All 4 artefacts
State Pension
Missing consent model
Jobseeker's Allowance
Not started
Making a service agent-ready takes days, not months. The four artefacts express policy decisions departments already make — eligibility criteria, required evidence, consent requirements, and the service journey. The Legibility Studio guides service teams through authoring each one.
5

How they connect

When a citizen talks to the agent, here is what happens behind the scenes. The critical insight: the AI generates conversation, but deterministic code makes every decision.

Citizen
Chat
Eligibility rules
Consent checks
Service submission
Department
1

Citizen describes their situation

The AI agent listens and identifies the relevant life event — bereavement, starting a business, having a baby. It matches this to services across every department using a graph of over 1,500 government services.

2

Agent reads department artefacts

For each relevant service, the agent reads the structured artefacts published by that department: what the service does, who is eligible, what data is needed, and what consent is required. The agent does not guess — it reads what the department has published.

3

Deterministic code checks eligibility

Eligibility is not decided by the AI. Policy rules published by the department are evaluated by deterministic code. If you meet the criteria, you are eligible. If not, you are not. The AI cannot override this.

4

Citizen gives consent

Before any data is shared or any action is taken, the citizen sees exactly what will happen and gives explicit consent. Consent is enforced by code, not by the AI. The agent physically cannot proceed without it.

5

Data is submitted to the department

The agent submits the citizen's data to the department's service through a secure, audited gateway. Every field is traced: where it came from, whether it was verified or citizen-provided, and when consent was given.

6

Receipt issued

The citizen receives a receipt confirming what was submitted, to which department, when, and a reference number. The department receives an auditable record of the interaction. Both sides have proof.

6

Why it is safe

The most common concern about AI in government: what if it gets things wrong? The answer is an architecture where the AI is never the one making decisions.

The AI handles language, code handles rules

The AI turns "my husband died" into an understanding of a bereavement life event. But whether the citizen is eligible for Bereavement Support Payment, whether their data can be shared with DWP, whether probate requires registration first — all of this is evaluated by deterministic code, using rules published by departments.

Consent cannot be bypassed

Consent is a hard technical gate, not a checkbox the AI can skip. The code that enforces consent sits outside the AI entirely. No prompt, no edge case, no system error can cause data to be shared without the citizen's explicit approval.

Every action is traceable

Every step the agent takes is recorded in an immutable evidence store: what it did, what data it accessed, what consent was given, what was submitted, and what the outcome was. If something goes wrong, you can replay the entire journey step by step.

And when the agent cannot help? It hands off. If a service is too complex, if the citizen needs emotional support, if there is a safeguarding concern, or if the situation requires human judgement, the agent stops and connects the citizen to a real person — with a full summary of everything that has happened so far, so they don't have to start over.
7

The future: your agent, your choice

The citizen app is one agent. But the architecture is designed for a world where it is not the only one.

Today, the citizen app is the trusted government agent that acts on your behalf. But the service artefacts that departments publish — the manifests, policies, state models, and consent requirements — are not locked to a single app. They are structured, open descriptions of government services that any authorised agent could read.

That means the future could look like this:

The government agent

The default, built and maintained by government. Designed for trust, accessibility, and universal access. Always available, always free.

Third-party agents

An AI assistant you already use — ChatGPT, a future personal agent, or an accessibility-focused tool — could be authorised to interact with government services on your behalf, through the same artefacts.

Specialist agents

A bereavement charity, a legal aid provider, or a carer's organisation could build agents tailored to the people they serve — agents that know the right questions to ask and the right tone to use.

The architecture makes this possible because legibility is the supply side. Departments publish structured descriptions of their services once. Any authorised agent — government-built or third-party — can read those descriptions and act on them. The citizen chooses which agent to trust. The department controls what the agent can do. The evidence plane holds everyone accountable.

This is the same model that made the web work: government publishes information in a standard format, and any browser can render it. Here, government publishes service logic in a standard format, and any agent can deliver it. The citizen's choice of agent becomes as natural as their choice of browser.

Citizen
Any authorised agent
Standard artefacts
Department services

Government services that understand you,
not the other way around.

The Agentic Legibility Stack is an operating model for the next generation of government services. Two products — one for citizens, one for departments — that together create a world where AI agents can act on behalf of citizens, safely, accountably, and with the citizen always in control.

Agentic Legibility Stack · March 2026