---
title: "How to prepare an AI assistant’s information · Lyntev"
description: "Organise sources, permissions, versions and tests for a business AI assistant. Includes examples, an answer workflow and a knowledge worksheet."
url: "https://lyntev.com/en/guides/prepare-ai-assistant-information"
language: "en-GB"
date_published: "2026-11-21T17:20:13.047Z"
date_modified: "2026-11-21T17:20:13.047Z"
---

1. [Home](<https://lyntev.com/en>)
2. [Practical guides](<https://lyntev.com/en/guides>)
3. How to prepare an AI assistant’s information

# How to prepare an AI assistant’s information

An AI assistant needs approved information, clear conditions and access limits. Uploading documents is only one step. This guide shows how to turn scattered information into a knowledge base that can answer, present the source and route questions that need a person.

By [Lyntev](<https://lyntev.com/en/company>). Updated on 17 November 2026.
About 5 minutes to read.

[Start reading](<https://lyntev.com/en/guides/prepare-ai-assistant-information#leitura>)[Download worksheet](<https://lyntev.com/recursos/en/preparar-informacao-assistente-ia.txt>)

**The answer starts with the source**Approved information, defined access and a verifiable answer.

Translation published on 21 November 2026. [Original Portuguese guide](<https://lyntev.com/guias/preparar-informacao-assistente-ia>); source revision 17 November 2026.

By the end, you can:

- Organise sources and their owners
- Define permissions and handover
- Test answers before making the assistant available

In this guide

1. [Start with the questions the assistant should resolve](<https://lyntev.com/en/guides/prepare-ai-assistant-information#ambito-do-assistente>)
2. [Assign an owner and validity conditions to every source](<https://lyntev.com/en/guides/prepare-ai-assistant-information#inventario-e-validade>)
3. [Write complete units of knowledge](<https://lyntev.com/en/guides/prepare-ai-assistant-information#unidades-de-conhecimento>)
4. [Apply permissions before retrieving information](<https://lyntev.com/en/guides/prepare-ai-assistant-information#permissoes-antes-da-pesquisa>)
5. [Prepare evidence-based answers with a useful next step](<https://lyntev.com/en/guides/prepare-ai-assistant-information#evidencia-e-encaminhamento>)
6. [Test what it should answer and what it should recognise as missing](<https://lyntev.com/en/guides/prepare-ai-assistant-information#conjunto-de-testes>)
7. [Maintain the knowledge with the same care as the service](<https://lyntev.com/en/guides/prepare-ai-assistant-information#ficha-e-manutencao>)
8. [Sources and criteria](<https://lyntev.com/en/guides/prepare-ai-assistant-information#fontes>)

## Start with the questions the assistant should resolve

Choose a specific task: explain services, help someone use a product or look up information about an authenticated order. List frequently asked questions, permitted decisions and matters requiring handover. Answering about a service, accessing an account and changing an order require different capabilities and authorisations.

In a RAG architecture, the system finds relevant information and provides that context to the model to prepare the answer. This is not the same as training the model on all the documents. Microsoft’s documentation describes this process. The method helps consult your own sources, but still requires tests of retrieval, answers and access.

- [Microsoft: how retrieval-augmented generation works](<https://learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation>)

## Assign an owner and validity conditions to every source

Create an inventory before importing. Record the subject, owner, approval status, authorised audience, version and validity conditions. A document without an owner can remain technically accessible after it no longer represents operations.

Define precedence by subject. For commercial terms, the source approved for that purpose takes precedence over an old presentation. The file’s modification date alone does not resolve a conflict. If two approved sources disagree, suspend the affected answer and ask the responsible person to decide.

Assign an owner and validity conditions to every source

| Source | Editorial decision | Access |
| --- | --- | --- |
| Approved catalogue | Index with version and owner | Public, if the catalogue is public |
| Ended campaign | Remove from current commercial information | Separate archive, if necessary |
| Internal procedure | Confirm approval and scope | Authorised working group |
| Order data | Look up in the responsible system | Authenticated and authorised customer |

## Write complete units of knowledge

Each unit should keep the answer together with the conditions and exceptions that make it correct. Preserve headings, lists and relationships between table cells. If a PDF was scanned, check that values and symbols have been read correctly after extraction. An extraction error can turn a correct source into a wrong answer.

When dividing documents into chunks, keep enough context to interpret each passage. Microsoft’s chunking documentation presents strategies based on structure and meaning. The right size depends on the documents and tests; there is no word count that solves every case.

Fictitious Oficina Horizonte record, unrelated to any real customeryaml

```
id: atendimento-prazo-orcamento
estado: aprovado
versao: 3
publico: publico
responsavel: operacoes
pergunta: When will I receive the quote?
resposta: The timescale is confirmed after the request has been assessed.
condicao: The equipment and the work must be known.
excecao: Incomplete requests need clarification.
fonte: procedimento-atendimento-v3
rever_em: 2026-12-17
```

- [Microsoft: strategies for splitting documents while retaining context](<https://learn.microsoft.com/en-us/azure/search/vector-search-how-to-chunk-documents>)

## Apply permissions before retrieving information

The system must establish identity and access through the application. Writing “do not show private data” in the assistant’s instructions is not enough. Documents eligible for retrieval must respect the permissions of the person asking the question, including chunks derived from each document.

Microsoft’s document-level access-control documentation shows this distinction between content and authorisation. In a simple project, separating the public knowledge base from the restricted area may make operations easier. In any design, test that a user cannot retrieve documents from another account, even when they know the title or identifier. Permission changes must also reach the index.

- [Microsoft: document-level access control](<https://learn.microsoft.com/en-us/azure/search/search-document-level-access-overview>)

## Prepare evidence-based answers with a useful next step

Ask for answers supported by approved passages, with a reference the user can consult when authorised. A correct link does not, by itself, prove the conclusion is correct: the source must support the claim. When conditions are missing, the assistant asks for clarification; when evidence is missing, it identifies the gap and routes the request onwards.

OWASP describes prompt injection: instructions received in a question or hidden in a document may try to divert the model’s behaviour. Treat retrieved documents as content, not as authorisation to carry out actions. The application must enforce permissions, limit operations and require human validation when the decision warrants it. A security instruction on its own does not eliminate this risk.

From a question to a verifiable answer

1. **Authorise**

  Determine the information the person can access.
2. **Retrieve**

  Find approved sources valid for the subject.
3. **Answer**

  Explain the conclusion and identify the evidence.
4. **Hand over**

  Ask for context or pass to a person when necessary.

Handover should preserve the necessary context without exposing information that should not be disclosed.

- [OWASP: prompt injection and mitigation measures](<https://genai.owasp.org/llmrisk/llm01-prompt-injection/>)

## Test what it should answer and what it should recognise as missing

Create a set of questions with the expected source, mandatory conditions and acceptable behaviour. Add different wordings and repeat critical cases: a single correct answer does not demonstrate consistency. Separate retrieval failures, outdated content, interpretation and authorisation to fix the root of the problem.

### Keep evidence of the trial

For each case, record the question, source version, answer obtained and review decision. Use examples without unnecessary personal data. Define the acceptance criteria before evaluating.

Test what it should answer and what it should recognise as missing

| Test case | Expected result |
| --- | --- |
| Question covered by the knowledge base | Answer consistent with the passage and conditions. |
| Ambiguous question | Clarification before assuming a condition. |
| Missing information | Gap acknowledged and useful handover. |
| Two contradictory sources | Conflict handled according to approved precedence. |
| Document from another account | Content excluded from retrieval and the answer. |
| Unauthorised instruction in a document | No change to authorisation and no unauthorised action. |

## Maintain the knowledge with the same care as the service

An update should go through review, source publication, index update and rerunning the affected tests. Confirm that the old version is no longer retrieved when it no longer applies. Record the change and prepare to restore the previous approved version if the update introduces errors.

Also review questions handed over to a person: they may reveal a missing explanation, a confusing process or a new need. Add knowledge after validating it with the responsible person. The aim is to improve coverage while keeping answers justifiable.

### Worksheet for your project

```
Assistant knowledge worksheet
Assistant’s task and audience:
Questions it should resolve:
Subjects and actions requiring handover:
Approved source for each subject and its owner:
Version, validity and next review:
Conditions and exceptions accompanying each answer:
Groups or accounts authorised to consult the source:
Rule for contradictory sources:
Expected answer when information is missing:
Test cases and acceptance criteria:
How to update the index and remove old versions:
Handover channel and information to pass on:
Person responsible for operations and approval date:
```

- [Explore Lyntev’s AI work for businesses](<https://lyntev.com/en/ai-for-business>)

## Sources and criteria

Content prepared with AI assistance and research using technical sources, with checks of the relevant examples and calculations. The references support the guide’s decisions; examples identified as fictitious let you try out the method.

- [Microsoft — Retrieval-augmented generation overview](<https://learn.microsoft.com/en-us/azure/foundry/concepts/retrieval-augmented-generation>)
- [Microsoft — Chunk large documents for vector search solutions](<https://learn.microsoft.com/en-us/azure/search/vector-search-how-to-chunk-documents>)
- [Microsoft — Document-level access control in Azure AI Search](<https://learn.microsoft.com/en-us/azure/search/search-document-level-access-overview>)
- [OWASP — LLM01:2025 Prompt Injection](<https://genai.owasp.org/llmrisk/llm01-prompt-injection/>)

## Continue to your next decision.

- [AI or automation: where to start](<https://lyntev.com/en/guides/ai-or-automation-where-to-start>)
- [Connect a website form to a CRM](<https://lyntev.com/en/guides/connect-website-form-crm>)
- [Artificial intelligence for businesses](<https://lyntev.com/en/ai-for-business>)

[Explore the guide library](<https://lyntev.com/en/guides>)

## Put this decision into practice.

Steps, examples and worksheets to prepare the work in your business.

[Find a reading path](<https://lyntev.com/en/guides#percursos-title>)

### [How to keep customer-support answers up to date](<https://lyntev.com/en/guides/keep-customer-support-answers-updated>)

Give answers an approved version and unanswered questions somewhere to go.

## Explore the research behind this decision.

Articles with sources, clearly identified examples and worksheets for assessing websites, AI customer service and business management systems.

[Explore all articles](<https://lyntev.com/en/research>)

Artificial intelligence · About 11 min

### [AI in customer service: what studies show and how to evaluate it in your business](<https://lyntev.com/en/research/ai-in-customer-service>)

See what studies show about AI in customer service. Learn how to test answers, quality, handover to the team and the time spent on the work in your business.

## Would you like to apply this to your business?

Send us your worksheet or explain what you need to improve. We help you choose the next step for your project.

- [Lyntev assistant Immediate answers about services, prices and timescales, with a cost estimate. Read the assistant guide](<https://lyntev.com/en/help/ai-assistant>)
- [WhatsApp +351 928 412 891. The message is only sent when you confirm it in WhatsApp. Write on WhatsApp](<https://wa.me/351928412891?text=Hello!%20I%20came%20from%20the%20Lyntev%20website%20and%20would%20like%20to%20discuss%20a%20project.>)
- [Form Describe what you need and receive the reply by email. Complete the form](<https://lyntev.com/en/contact>)
- [Email contacto@lyntev.com Send an email](<mailto:contacto@lyntev.com?subject=Request%20for%20information>)

![Wellinton Oliveira](<https://lyntev.com/media/autores/wellinton-oliveira.webp>)

Written by

[Wellinton Oliveira](<https://lyntev.com/en/company>)

CEO of Lyntev

Technology with context, original analysis and sources you can consult.
