Skip to content

Solutions · Chatbots · Custom project Knowledge chatbots for your documents and workflows.

Together with you, we develop an application that finds the right information and supports the steps you agree on.

Common hurdles

The answer is in your documents. But where?

Policies, manuals, contracts: the knowledge is there. But before anyone finds the right passage, there are searches, follow-up questions and emails to the specialist team.

  1. The challenge: Knowledge spread across many places

    Policies sit on the intranet, manuals on a shared drive, contracts in the archive. A keyword search for “leftover vacation” misses a document that says “unused vacation”.

    With deepsight: One question across all sources

    The knowledge chatbot searches all the documents you approve – for the meaning of the question, not just the keyword – and answers in full sentences.

    How the search works
  2. The challenge: The same questions, again and again

    HR, IT service or sales support answer questions every day whose answers have long been written down in a policy. That leaves less time for the tricky cases.

    With deepsight: Ask the chatbot first

    Employees ask the knowledge chatbot first instead of emailing the specialist team. It answers from the same documents the team would point them to.

    Typical questions
  3. The challenge: Answers without evidence

    A general AI chat doesn’t know your current policies. Its answers sound plausible but can’t be checked against your own documents.

    With deepsight: Answers with evidence

    The knowledge chatbot relies on your documents and names the document and passage. That way, anyone can look up what an answer is based on.

    See the example
  4. The challenge: Confidential documents

    Pay rules, contracts or internal instructions aren’t meant for everyone. And IT and data protection rightly ask where the documents are processed.

    With deepsight: Access and operation on your terms

    We agree with you who can reach which documents through the chatbot, and set up the infrastructure with your IT – including local language models in your environment if you wish.

    Collaboration and technology
Example

An answer you can verify

Three everyday questions, three documents. Choose a question.

Knowledge chatbot
How many vacation days can I carry over to next year?

Works agreement on vacation · § 4 · as of 01/2026
Source passage in the document
Works agreement on vacation · § 4 · as of 01/2026

(1) Unused vacation of up to five working days may be carried over to the following calendar year.

(2) Carried-over vacation must be taken by March 31 of the following year.

(3) Different rules for parental leave or extended illness are set out in § 7.

Select a sentence in the answer to see the source passage.

Not to be confused with the deepsight cloud assistant: it answers questions about your analysis, while a knowledge chatbot answers questions about your own documents.

Information and actions

Finding and acting stay separate

Answers with a source

The knowledge chatbot searches the documents you specify and points to the passage. If the documents contain no suitable information, it should say so instead of guessing; how reliably that works is something we test together using your questions.

Action with approval

Suggestion: create a service desk ticket

Category
Travel expenses
Subject
First-class reimbursement, Munich
Buttons in the sample interface:ApproveEdit
Process

How a project works

  1. Clarify the use case

    Which questions, which documents, which steps – and who will use the knowledge chatbot?

  2. Prototype

    A first version using a selection of your documents.

  3. Test with the specialist team

    Check and refine answers and sources using real questions.

  4. Operation

    We agree on access, document updates and further development together.

Questions

Questions your documents can answer

Examples from HR, IT, sales, service, purchasing, quality and market research.

  • Which documents do I need to apply for parental leave?
  • How do I set up VPN access on a new laptop?
  • Which services are included in the Basic plan, and which only in the Plus plan?
  • What does error code E42 mean according to the maintenance manual, and what should I do?
  • What liability cap applies to late delivery under the framework agreement?
  • Which inspection step does the work instruction require before release?
  • What did our past study reports find on price perception, and where does it say so?

Good to know: Anything that requires weighing up an individual case stays with your specialist team.

Documents and sources

What the knowledge chatbot works with

The documents your team already works with today – usually PDF and Word files or pages from your intranet and wiki.

Policies and agreementsWorks agreements, travel expense, IT and security policies, employee handbooks.
Product and contract documentsService descriptions, rate sheets and data sheets, terms and conditions, framework agreements.
Technical documentationOperating and maintenance manuals, work instructions and error catalogs, often with tables.
Repositories and systemsIntranet, wiki, document management or database. Which sources we connect, and how, is defined in the project.
Several languagesQuestion and source don’t have to be in the same language; the answer can come in the language of the question. The test shows how well this works for your languages.

Good to know: Scanned documents need text recognition. How well it works depends on the quality of the scan.

A knowledge chatbot is only as good as the documents it can access.

How it works

How an answer is created

Our knowledge chatbots use retrieval-augmented generation (RAG): search first, then write.

  1. Prepare the documents

    The specified documents are split into sections and indexed for search. Title and section are kept so the answer can cite the source passage.

  2. Find relevant passages

    For each question, the application finds the best-matching sections and ranks them by relevance. They form the basis of the answer.

  3. Write the answer

    A language model receives the question together with these sections and writes the answer from them, citing the document and passage.

    RAG in the glossary
  4. Apply rules

    Depending on the project, agreed rules apply before the answer is shown – such as limiting it to certain topics or referring people to a contact person.

Results

What you have at the end

Requirements description with effort estimateAfter the clarification phase: which questions, documents, user groups and actions the knowledge chatbot covers – and how much effort to expect.
Prototype test resultsWhich questions the prototype answers well and where documents are missing or contradict each other – as a basis for your decision on the build.
Application ready for useThe knowledge chatbot connected to your sources, as a standalone interface or embedded in an existing system, depending on the project.
Code and handoverWe work with widely used technologies and documented code. Usage rights and handover are set out in the project contract.

Start with one area and real questions – not a chatbot for everything.

Start where the same questions come up again and again, then expand.

Methodology

What matters with knowledge chatbots

Split documents sensibly

How documents are split determines whether tables, footnotes and exceptions stay with the paragraph they belong to during search. We adapt this to your document types.

Only valid versions

If there are several versions of a policy, the search may find the outdated one. So only approved versions go into the collection, and the source shows the version date if the document has one.

Data protection for questions, too

Questions can contain personal data. Whether and for how long conversations are stored is something we decide with the people responsible for data protection at your organization. If we process data on your behalf, we sign a data processing agreement under Art. 28 GDPR.

FAQ

Questions about knowledge chatbots