Public sector · Agencies, directorates and municipalities

The counter closes at four. The questions don’t.

YPAI builds the knowledge systems and assistants that answer citizens and caseworkers when the counter is closed, and the multilingual data that proves them before release. Every answer keeps a thread back to an approved source. A named person takes what the assistant may not decide.

AI Implementation
Knowledge systems, assistants, document AI
AI Data & Evaluation
Citizen languages, evaluation, native review
Connected Delivery
One team owns the system and its data
Run in the EEA
Private deployment, Norwegian company

The thread Every answer keeps a line back to its source.

Sealed A cited, approved source.

A person A named caseworker takes what the assistant may not decide.

Before it answers for you

An assistant answering for the public stands or falls on three questions.

Can it say only what we have approved?

It retrieves from records you have approved, answers with citations, and when the evidence is not there it says so and stops. The answer inherits your access boundaries instead of bypassing them.

Does it serve every citizen?

Only if the data does. Dialects, minority languages and citizens who will never type a tidy sentence are the mandate, not an edge case. Native speakers record and review, and the assistant is graded per language before release.

Who answers when it cannot?

A named caseworker. The assistant performs only the bounded actions you intended; everything outside them is routed to a person who owns the exception, with the full exchange attached.

What YPAI delivers to public services

Buy the system. Buy the data. Or both, from one team.

AI Implementation

Delivered into your environment.

A working knowledge system, citizen or caseworker assistant, or document workflow for a defined public service, with its integrations, permissions and controls.

AI Implementation

AI Data & Evaluation

Proven in every language you serve.

The citizen questions, documents, evaluation sets and native-speaker review that train, test and prove the assistant before a citizen meets it.

AI Data & Evaluation

Connected Delivery

One team owns the failure.

The assistant and the data it answers from, built and fixed by the same people. Nothing is handed to another vendor.

How the loop works
150+
Languages in the contributor network
210,000+
Contributors in the network
50+
Countries delivered in

Operated from Norway, with EEA-based processing where required.

The citizen assistant

Citizens keep asking after four. The assistant answers from your approved records, or hands over to a person.

A benefit change, a deadline, a document list, and a question it must refuse. The assistant answers only from records the service owner has approved, cites them on the answer itself, and routes what it may not decide to a named caseworker. Built for the service you run, inside the access you already enforce.

AI assistants and chatbots
Citizen assistant16:12 · after hoursText · voice
Ask the assistant
Citizen

Assistant

The letter follows a rates-table change. Nothing is required from you unless your housing costs also changed; the letter’s step 2 covers that case.

Housing benefit guide · §4.2 · v7 · approved Rates table · 2026 · v3 · approved

Drawn from approved records

Assembled from records the service owner has approved, each one cited on the answer itself.

The thread stays attached

Every sentence keeps its line back to the passage it came from. A reviewer can open it tomorrow.

A person takes what it may not decide

Out of scope is routed, not improvised. A named caseworker receives the full exchange.

Built for the service you run

Caseworkers decide on the current rule. Post is read on arrival. Every language is proven before release.

Three deliverables a directorate or municipality buys from YPAI: a governed knowledge system for the people who decide, document AI for the applications and letters that arrive, and the evaluation that proves the assistant in every language your citizens speak. Each is delivered into your environment and can be bought on its own or together.

The caseworker knowledge system

Precedent, procedure and the current version of the rule, inside the access the caseworker already has.

System
A governed library of circulars, guides and decisions with retrieval that returns the passage, its version and its approval state, permission-aware.
Data
Your documents ingested with version and approval state on every record; superseded versions retired, never cited.
Enterprise knowledge assistants

Document AI for what arrives

Applications, attachments and letters read on arrival, classified, and routed with review where judgement is required.

System
Extraction and classification integrated with the case system, approval gates at every bounded action, a review queue for exceptions.
Data
Annotated applications and attachments from your own casework: extraction ground truth and exception taxonomies.
Document AI workflows

Proven per language before release

The service that works in the capital’s dialect, proven in the others before a citizen meets it.

System
An evaluation set built from the questions citizens actually ask, graded by native speakers per language and question class, re-run on every source update.
Data
Speech and text recorded and reviewed by native speakers; where a language fails, data is collected and the class is re-graded.
Evaluation
Knowledge system Inside the caseworker’s access · permission-aware
  1. Housing benefit guide · §4.2 · v7 · approved A change that follows a rates-table revision takes effect from the first day of the following month.
  2. Rates table · 2026 · v3 · approved Monthly rates by household size, effective 1 May.
  3. Housing benefit guide · §4.2 · v6 · retired Superseded. Not citable.

AnswerFrom the first day of the month after the rates-table revision. No action is required unless housing costs also changed.

Document AI · intake

Application · Housing benefit · received by post

Benefit

Period

Tenancy agreement

Tax assessment

Proof of income

Benefit
Housing benefit
Period
From 1 May
Tenancy agreement
Attached
Tax assessment
Attached
Proof of income
Missing
Routed to review queue · a named caseworker Approval gate before any letter is sent
Evaluation · per language
Entitlement Deadlines Documents Out of scope
Norwegian
English
Ukrainian
Arabic
Arabic · deadlines · data collected · re-graded Released · graded in every language

Two service lines, one team

Connected Delivery

When the failure sits in the data, the team that built the assistant fixes the data.

A circular missing from the library, a dialect the evaluation set never covered, a question class nobody graded. No hand-off between a system integrator, a model vendor, an annotation company and an evaluation supplier. Each service line remains independently purchasable.

  1. Observe the failure
  2. Isolate the gap
  3. Produce the data
  4. Improve the assistant
  5. Re-run the evaluation
  6. Release
  7. next failure

Every citizen

Serving every citizen is a data problem. We are also the data company.

Nordic depth

Norwegian Swedish Danish Finnish Icelandic

dialects and regional accents

European

German French Dutch Polish Spanish Italian

including low-resource languages

Beyond Europe

Arabic Somali Tigrinya Ukrainian Urdu

the languages your citizens arrive with

Code-switching

Nordic + English Nordic + Arabic

recorded as actually spoken

Recorded and reviewed, not machine-translated coverage. The exact language list is set with the engagement.

Jurisdiction
Norway, under GDPR
Data residency
EEA by default, defined per project
Deployment
Private and EEA, in your environment
Processing terms
Standard DPA, subprocessors and transfers defined per project
Erasure
30-day end-of-contract erasure
EU AI Act
Article 10 documentation, produced as part of delivery

Scope

Bring us the service that has to answer after four.

Start with a service or journey, the documents that should govern its answers, and the languages your citizens speak. YPAI will define the shortest credible path from the current state to an assistant you can hold accountable.

  1. Scope
  2. Sources approved
  3. Build
  4. Human review
  5. Acceptance
  6. Operate

Pilots are scoped to your specification. Scope and commercial terms are agreed per project before the pilot begins, every pilot carries a SOW, acceptance criteria and a DPA, and production is a separate decision after pilot review and acceptance.

Enquiry details are treated as confidential.

Scope an engagementOne brief. A project lead reads it, not a queue.

In scope (optional)

Questions

Frequently asked questions

The questions a service owner asks before an assistant answers in the agency’s name.

Can the assistant answer from documents we have not approved?
No. Retrieval is limited to records with an approval state you control. When the evidence is not in the library, the assistant says so and stops, or routes the question to a named caseworker. Every answer carries its citations, so a reviewer can open the record behind it.
Who decides when a question is outside the assistant’s scope?
A person. The assistant performs only the bounded actions agreed in scoping. Anything outside them is routed to a named caseworker with the full exchange attached, and the citizen is told who has the case. The assistant never improvises a decision.
How do we know it works in the languages our citizens actually speak?
It is graded per language before release, against an evaluation set built from the questions citizens actually ask. Speech and text are recorded and reviewed by native speakers, and the evaluation re-runs on every source update.
Where is the data processed?
In the EEA by default, with private deployment in your environment where the engagement requires it. Residency, subprocessors and transfer controls are defined per project in the DPA. YPAI is a Norwegian company operating under GDPR.