Registry data, queried in plain language.

Regis takes a question in natural language, retrieves from primary government registry records across 200+ countries, and returns the answer with the filing behind every value.

POST api.globaldatabase.com/v1/regis/queryawaiting query
Request body
{ "prompt": "
  • ResolvedGlobal Data Intelligence Limited → GB 09410808
  • RegisterCompanies House, United Kingdom
  • Readingstatus, company type, incorporation date, registered office
Response200 OKapplication/json
Active on the UK register. Company number 09410808,1 incorporated 28 January 2015.2 Registered office is Artisans’ House, 7 Queensbridge, Northampton, Northamptonshire, United Kingdom, NN4 7BF.3 Registered as a private limited company.4
Sources returned with the answer
1statusActiveCompanies HouseCS01 / 2026-01-28
2incorporation_date2015-01-28Companies HouseIN01 / 2015-01-28
3registered_officeArtisans’ House, 7 Queensbridge, Northampton, Northamptonshire, United Kingdom, NN4 7BFCompanies HouseAD01 / 2024-11-04
4company_typePrivate limited companyCompanies HouseIN01 / 2015-01-28

The model can only return what it retrieved.

A general-purpose model answers a company question from whatever it absorbed in training. There is no filing behind that answer, no date attached to it, and no way for a reviewer to check it. Regis is built the other way round: the question triggers retrieval against registry records, and the answer is assembled from what came back.

01

Retrieval first

No answer without a record. The question is resolved to entities and fields, those fields are read from primary registry records, and the answer is written from the retrieved values. Nothing in the response originates in model weights.

02

Refusal is a result

Empty is a valid response. Where the register does not publish a field, Regis returns the gap rather than an estimate. An empty answer with a stated reason is safer in a case file than a confident one you cannot source.

03

Same question, same answer

Reproducible for review. Answers are reconstructed from the underlying record, so a reviewer running the query again gets the same values, with the retrieval timestamp attached to show what the register held at the time.

04

Structured output

JSON, not paragraphs. Alongside the written answer the response carries the resolved entities, the fields used and the source records, so it can be written straight into a case management system without parsing prose.

Reaching the same records through a general assistant.

Company data can be pulled into a general-purpose model through a connector. It works. What it changes is how many suppliers sit between the question and the register, what the retrieval is billed as, and how much of the answer a reviewer can trace.

Regis APIData provider plus a general assistant
Source of the answerRegistry records retrieved at request time, with no company facts held in weightsRecords passed into a model context, assembled by a model that also answers from training
Citation levelField level. Each value carries its register, reference and retrieval timeDocument level, where the system cites at all
Missing fieldReturns null and names the register that is silentDepends on the assistant's behaviour
Commercial contractsOneTwo
Data processing agreementsOneTwo
Assistant seat licencesNoneRequired
Pricing basisPer resultPer token consumed
Bulk retrievalDirect, no inferenceThrough the model context
Data pathSingle supplierCrosses a third party
Vendor reviewOne vendor on the registerTwo vendors to assess, two answers on where the data travelled

Both columns return the same registry records.

Ask a general-purpose AI assistant for five years of financials on one company. Its accounts carry about 250 separate figures a year, so 1,250 figures have to travel into the model’s context window before it can say anything. That is roughly 19,000 tokens, billed at inference rates, to move data that was already structured.

0

FiguresFive years of accounts for one company
~

0

TokensWhat those figures cost to put in front of the model
~

0

TokensThe same request across a thousand companies
01A data provider plus a general assistant
  • Every figure is pulled into the model’s context before it reaches you — the retrieval itself is priced as reasoning
  • Ask a follow-up and the same context is sent again and billed again
  • On top of the token charge sits the assistant subscription, plus a seat for everyone who uses it
  • A second commercial contract and a second data processing agreement
02The Regis API
  • The same figures come straight out of the register as structured data, with no model in the middle
  • No tokens involved
  • Charged per result rather than per token, so a thousand-company pull costs what moving data costs
  • No subscription, no seats — one contract, one agreement

One dataset, two access patterns.

Global Database’s registry data is reachable two ways on the same API key. The structured endpoints take a company identifier and a named field, and return a fixed response shape. Regis takes a question and works out for itself which registers and fields answer it. Both read the same records.

Deterministic

Structured endpoints

You name the company and the field. KYB, officers, shareholders, group structure, financials, credit and bank verification each have their own path and a fixed response shape.

Input
Identifier or filters
Output
Fixed JSON schema
Provenance
include_provenance
Best for
Pipelines, batch runs
Natural languageAgentic

Regis query

You ask the question. Regis resolves the entities, decides which registers and fields answer it, retrieves them, and returns the answer with its sources. Multi-step questions resolve in one call.

Input
prompt as a string
Output
Answer plus sources
Provenance
Attached by default
Best for
Analysts, agents, apps

One POST, a token header, a string.

Authentication is a token in the header. There is no SDK to install and no query language to learn. If your service can make an HTTP request, it can call Regis.

# Ask a question. Get the answer and its sources.
curl -X POST 'https://api.globaldatabase.com/v1/regis/query' \
  -H 'Authorization: Token YOUR_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{
    "prompt": "Is Global Data Intelligence Limited still active, and what is its registered office?"
  }'
RESTPOST /v1/regis/query
A single endpoint takes prompt and returns the answer with its sources. The rest of the v2 API stays available for structured calls against the same records.
MCP servermcp.globaldatabase.com
Expose the same dataset as tools inside an assistant or an internal agent. The agent asks in the same plain language and gets the same sourced answer back.
Inside your productredistribution licence
Regis can sit behind your own interface and answer your customers' questions under your brand. Redistribution terms are set in the licence rather than assumed.

What arrives with the answer.

The written answer is the readable part. The part that survives an audit is what sits underneath it.

response fragmentone field
{
  "field": "status",
  "value": "Active",
  "source": {
    "register": "Companies House",1
    "jurisdiction": "GB",
    "filing_reference": "CS01",2
    "filed_on": "2026-01-28",
    "retrieved_at": "2026-08-04T05:43:17Z"3
  },
  "resolved_entity": {
    "name": "Global Data Intelligence Limited",
    "registration_number": "09410808"4
  },
  "unavailable_fields": []5
}
  1. 1
    source.register

    Names the government body that publishes the record, so the answer resolves to the statutory source rather than to a vendor's own dataset.

  2. 2
    source.filing_reference

    The document identifier as the register issued it. A reviewer can pull the original filing from the register without going through us.

  3. 3
    source.retrieved_at

    Fixes what the register held at the moment the decision was made, which is the question asked months later when the record has moved on.

  4. 4
    resolved_entity.registration_number

    Shows which of several similarly named companies the answer is actually about. Most disputes about company data are resolution errors, not value errors.

  5. 5
    unavailable_fields

    Lists what the register does not publish for that jurisdiction, so a missing value is distinguishable from a value of zero or none.

On the structured endpoints
Send include_provenance: true on enrichment, autocomplete and financials calls to get source metadata alongside the values. Documented in the v2 reference.

Four hundred registers do not agree with each other.

Plain-language querying is the surface. What makes it answerable is the part that took years: reconciling registers that publish different fields, in different languages, on different schedules, under different definitions of the same word.

Companies House
09410808Eight characters, with SC and NI prefixes for Scotland and Northern Ireland
Handelsregister
HRB 6684Register court, then HRA or HRB, then a number that repeats across courts
SIREN
552 100 554Nine digits, extended to fourteen for each individual establishment
KvK
33014286Eight digits, separate from the VAT and legal entity identifiers
Delaware file number
7714902Seven digits, unique to one state of fifty

Five incompatible ways of naming the same class of object. None of them was designed to interoperate with the others.

01

Entity resolution

The same company appears under a trading name in one register, a legal name in another and a transliteration in a third. Resolving a question to a registration number is the step that decides whether the rest of the answer is about the right company.

02

Field definitions

Turnover is not the same line in every accounting standard, and a director is not the same office in every company law. Answers are normalised to a common dictionary while the original value stays attached.

03

Document extraction

A large share of registry filings are documents rather than data. Financial statements, shareholder registers and charge filings are read out of the filed document and structured into fields.

04

Update cadence

Registers publish on their own schedules, from continuous to annual. Records are synced daily, and the retrieval timestamp tells you which side of a register's update you are on.

05

Ownership traversal

A beneficial owner three jurisdictions up is a chain of registry lookups, not a field. Regis walks the chain and returns each hop with the register it was read from.

The questions your second line will ask.

Every one of these arrives before a data source is approved. The answers are here so you can send them on without waiting for us.

Vendor assessmentRegis API · six standard questions
01

Where does the answer come from?

Primary government registry records, retrieved when the request runs. Not model recall, and not a score derived from someone else’s dataset.

02

Can we reproduce it months later?

Yes. Every value returns with its register, filing reference and retrieval timestamp, so the answer can be rebuilt against the original filing long after it was generated.

03

What happens when it does not know?

It returns null and names the register that does not publish the field. No estimate, modelled figure or comparable-company value is substituted for a missing filing.

04

Is our query data used for training?

No. Questions and payloads sent to the API are excluded from model training, with the controls set out in the data processing terms.

05

What certifications do you hold?

ISO 27001, and registration with the UK Information Commissioner’s Office. Security documentation and the data processing agreement are available under NDA before contract.

06

Can we redistribute the output?

Under a redistribution licence. Internal use, customer-facing display and redistribution are licensed separately, so contract scope is explicit rather than assumed.

Ask it something you already know the answer to.

That is the fastest way to judge it. Pick a company in your book, ask Regis a question you can verify, and check the filing it returns.

Common questions.

What exactly is Regis?

A query interface over Global Database's registry dataset. You send a question as a string, Regis resolves which companies and fields it concerns, retrieves those fields from primary government registry records, and returns an answer with the source of each value.

How is this different from asking a general-purpose model?

A general model answers from training data, which has no filing behind it and no date attached. Regis has no company facts in its weights. It answers from records retrieved on the request, and returns those records with the answer so the reviewer can check it.

What happens when the register does not publish the field?

Regis returns the gap and names the reason. It will not substitute an estimate, a modelled figure or a value from a similar company.

Which countries are covered?

400+ government registries across 200+ countries and territories. Field availability varies by jurisdiction because registers publish different things. Coverage by field and country is set out in the data dictionary.

Can I use it inside my own product?

Yes, under a redistribution licence. Standard API access covers internal use. Serving the data to your own customers is licensed separately so the terms are explicit rather than assumed.

Does it work with an AI agent?

Yes. The same dataset is exposed through an MCP server, so an assistant or internal agent can call it as a tool and receive the same sourced answers.

How current is the data?

Records are synced daily. Because registers publish on their own schedules, the response carries a retrieval timestamp so you know what the register held at the time of the read.

How do I authenticate?

A token in the Authorization header: Authorization: Token YOUR_API_KEY. Keys are issued from your account profile.

Can I still call the structured endpoints?

Yes. Regis sits alongside the v2 API rather than replacing it. KYB, officers, shareholders, group structure, financials, credit reports, bank verification and enrichment all remain available with fixed response shapes.

What security and compliance documentation is available?

ISO 27001 certification and UK ICO registration. Security documentation and the data processing agreement are available under NDA before contract.