Products/udX/udX Chat
Part of the udX family · Production-ready

udX ChatAsk your entire document base: every answer backed by its source.

udX Chat makes a company’s complete document base searchable like a conversation: without the language model making anything up. Every answer is traceable down to the document: from the verbatim passage to the reasoned conclusion.

What it is

Built directly on udX.

After udX has analysed a document’s entities, its content is automatically grounded in a vector database: stored so it stays precise, fast and searchable without losing the connection to the original document.

On top of that, udX Chat lets you talk to your documents through a language model. Two mechanisms make sure every answer is correctly framed: a three-stage search that always looks in the right place, and a graded evidence system that shows how well each answer is backed.

  • No separate onboardingEvery document analysed by udX is automatically chat-ready.
  • Evidence required by defaultBacked answers come exclusively from your documents, enforced in the backend rather than in the prompt. The optional research stage is kept strictly separate and visibly marked.
  • Research in secondsQuestions that used to take hours of manual searching are answered with evidence attached.

Three-stage search

Always the right search depth: automatically.

Each query is answered at the appropriate level. The user never has to pick the search depth; the system escalates on its own, so no relevant information is missed.

01

Within the current document

The narrowest, most precise level: used when you chat from inside a document view.

02

Within a document cluster

Related documents, such as all annexes of a contract or all policies of one customer. Clusters are built automatically from references and shared entities.

03

Across all documents

The full knowledge base, when the answer spans multiple documents: searched by an agentic retrieval step that selects the relevant passages itself.

Graded evidence

Every answer shows how well it is backed.

Answers are not delivered as a single block of text but structured by their level of evidence: the hardest, best-backed level is always tried first. Each grade is technically validated in the backend before anything reaches the user.

Verbatim
Backed by exact wording

The answer rests directly on entities and the exact wording of the documents. The backend verifies that every quoted passage really exists, character by character: only then is the source highlighted in the original.

Semantic
Backed by meaning

Information is derived from the document content but remains directly covered by the text: verified against the source passage after normalisation.

Derived
Concluded from facts

The answer draws a conclusion that is not spelled out word for word: a calculation or logical inference. Every underlying fact must still be quoted verbatim and validated.

Abstention
No answer instead of a wrong one

If no level produces a validated answer, udX Chat says so explicitly: "This information is not contained in the available documents." Nothing unverified is ever delivered.

Research stage

When your own documents fall short.

Some questions simply cannot be answered from your own documents. By default udX Chat stops at abstention. If you would rather have an answer, you can enable the research stage: it answers such questions from general knowledge or from a web search.

The separation is what matters. Answers from the research stage are unmistakably marked as such and are never mixed with backed statements. The evidence requirement for answers drawn from your document base is untouched by it.

  • Optional and switchableThe stage is off by default. The application points it out before use, and it can be disabled entirely.
  • Web search via an EU providerThe web search works with an EU provider. Providers outside the EU are blocked by default and usable only after explicit approval.
  • Never mixedBacked and researched statements stay apart. You can always see what an answer rests on.

Formats

What udX Chat can read.

Layout awareness instead of a wall of text: tables, columns and page structures are preserved as such. Scanned contracts and photographed pages become searchable through text recognition including descriptions of figures. Complex workbooks are condensed into dependable key statements rather than dumped cell by cell, with the time reference and origin of every figure staying traceable.

PDFWordExcelPowerPointJPGPNGTIFFTXTCSVMarkdown

Connecting sources

Collected where the documents already live.

Network drives and SharePoint

Both can be attached as connected sources. OneDrive and Google Drive are prepared.

Pre-analysis is mandatory

Before a source is connected you see the document count per file type, the page volume and a cost estimate. Only then do you confirm.

Deliberately manual sync

One click identifies new and changed files and analyses only those. Nothing runs unnoticed in the background racking up cost.

Cost protection built in

A token budget per chat, page and usage quotas per group, plus a pause switch for the entire processing pipeline.

Core functions

What udX Chat does.

Automatic grounding

Documents are placed in the vector database right after udX analysis: text, entities and even figures from charts and images become searchable.

Source reference per answer

Inline markers link every statement to the exact page, clause and highlighted passage in the original document: clickable in the viewer.

Anti-hallucination gate

Quotes that cannot be technically verified are discarded; answers without a single valid quote are never shown. Enforced in the backend, not just prompted.

Ask in any language

Questions are normalised and translated automatically; the answer comes back in your language while quotes stay in the original.

Follow-up aware

References like "and in euros?" are resolved against the conversation, so research works like a dialogue.

Live search status

While searching, the current stage is shown live: from the single document up to the full base.

Security & data sovereignty

Built for production, not for demos.

Operated in Germany

Runs in an EU region, Germany West Central for new installations. Your documents do not leave the EU.

No model training on your content

Your documents are processed to answer your questions, not to train models.

Virus scan on every upload

Every file is checked before it is read, analysed or indexed. Files identified as malicious are rejected, removed and logged.

Defence against manipulated documents

External content is handed to the language model explicitly marked as data. Hidden instructions inside a document cannot steer the application.

Fail-closed, no fallback path

Identity is verified cryptographically on the server. If the check is missing or fails, the request is rejected. There is no path that grants access when in doubt.

No keys in circulation

All service access uses managed identities with least-privilege roles. Secrets live exclusively in a managed key vault.

Deployment models

Three ways to run udX Chat.

An isolated environment per customer is the norm in production: no shared database, no application-level tenant separation that could be misconfigured.

Shared test environment

Evaluation

For trying it out without standing up infrastructure of your own.

  • Operated by koeniq, shared
  • Sign-in via koeniq
  • Test data only

Per-customer deployment

Production

The norm: a dedicated, isolated environment for your company alone.

  • Own isolated environment per customer
  • Sign-in via your corporate account
  • Data fully separated

Your infrastructure

Highest requirements

For organisations whose data must not leave their own network.

  • Runs in your data centre or your cloud
  • Sign-in via your directory
  • Data never leaves your premises

Typical scenarios

Where udX Chat earns its keep.

"Which contracts expire in the next 60 days?", with a source reference for every single document
Legal research across an entire contract portfolio
Instant answers on clauses, deadlines and conditions without manual searching
Cross-document checks in complex claims or audit cases

udX Chat answers open questions across your entire document base. Its sibling udX Audit does the opposite: it checks specific target documents against their governing sources, continuously.

Discover udX Audit

See udX Chat on your own documents.

Book a free 30-minute call. We show you the product live and tell you honestly whether it fits your document base.

Book a demo

Frequently asked questions

What is udX Chat?

udX Chat makes a company’s entire document base searchable like a conversation. Every answer is backed down to its source: page, clause and the highlighted passage in the original document. Documents already analysed by udX are chat-ready with no separate onboarding.

How does udX Chat prevent hallucinations?

Through technical validation in the backend, not through a prompt. Every quote is verified character by character against the original document, and quotes that cannot be verified are discarded. A backed answer without a single valid quote is never delivered.

What happens if the answer is not in the documents?

By default udX Chat says so explicitly: "This information is not contained in the available documents." That abstention is a deliberate answer level, because an invented statement costs more in legal or financial work than a missing one. If you would rather have an answer, you can enable the research stage.

How does the three-stage search work?

udX Chat picks the search depth itself and escalates when needed: first within the current document, then within a document cluster (such as all annexes of a contract), finally across the entire base. Users never have to select a search depth manually.

Which language can I ask questions in?

Any language. Questions are normalised and translated automatically and the answer comes back in your language. Quotes stay in the original wording so the chain of evidence remains verifiable against the source document.

Is there a free trial of udX Chat?

Yes. You can request trial access at udxchat.koeniq.ai/request. Once it is activated you can try udX Chat on your own documents. The free 45-minute slot offered on this site is a different thing: a consultation call, not product access.

Request trial access

Which file formats can udX Chat process?

PDF, Word, Excel, PowerPoint, images (JPG, PNG, TIFF) and text files such as TXT, CSV and Markdown. Tables, columns and page structures are preserved. Scanned contracts and photographed pages become searchable through text recognition, including descriptions of figures.

Can I connect SharePoint or a network drive?

Yes, both can be attached as connected sources; OneDrive and Google Drive are prepared. Synchronisation is deliberately manual: one click identifies new and changed files and analyses only those, so nothing runs unnoticed in the background and racks up cost.

Where is the data held, and is it used to train models?

Operation takes place in an EU region, Germany West Central for new installations. Your documents do not leave the EU and are not used to train models. On request, udX Chat runs entirely inside your own infrastructure.

How do I avoid surprise costs?

A pre-analysis is mandatory before connecting a source: it shows the document count per file type, the page volume and a cost estimate you have to confirm first. On top of that there are token budgets per chat, quotas per group and a pause switch for the entire processing pipeline.

How long are chats and logs retained?

Every data type has a technically enforced retention period: chat histories 180 days, administrative logs 365 days, usage and billing data 395 days, intermediate analysis results and operational logs 90 days each. Access and erasure requests are built in as guided processes.