---
title: "AI search & knowledge"
description: "Search and assistants that answer from your documents, tickets and manuals, with sources shown and permissions respected. Start with one workflow."
canonical_url: "https://netmedia.agency/services/ai-search-knowledge"
lang: "en"
content_type: "page"
collection: "pages"
slug: "ai-search-knowledge"
alternates:
  -
    lang: "en"
    url: "https://netmedia.agency/services/ai-search-knowledge"
---

# AI search & knowledge

## Your team stops asking

Your policies, manuals, past support requests and project notes already hold most answers. Finding them still depends on who remembers where they are. We build search and assistants on that knowledge, with permissions respected and the source shown behind every answer, so you stop being the person everyone asks.

AI search & knowledge · documents, tickets, manuals

the same three people

Answers come from your own documents, with the source attached.

Book an automation review

## Company knowledge gets stuck

You probably have the information already. What is missing is a reliable way to find the right part of it, at the moment someone needs it.

### Three people answer everything

The same colleagues get the same questions every week. When one of them is on holiday, work waits.

### Search finds files, not answers

Your shared drive returns twenty documents. Someone still has to open them and find the paragraph that matters.

### Answers without a source

A chatbot that cannot show where an answer came from gets checked by hand, and then it gets ignored.

### Knowledge in too many places

Manuals in folders, decisions in email, fixes in old support requests, numbers in the ERP. Nobody searches all four.

### Not everyone may see everything

HR files, pricing and client contracts need limits. A tool that ignores permissions becomes a risk.

Where it hurts

in people and folders

## Three ways to make your knowledge

Each one starts from content you already have. You do not need to write a new knowledge base first.

### Search across documents, tickets and manuals

One search over the places knowledge already sits: shared drives, SharePoint, past support requests, manuals. It finds the passage, not only the file. This is retrieval-augmented generation (RAG).

### Assistants that answer with sources

An assistant for one defined job, such as service desk, onboarding or internal policy questions. It answers only from approved sources, links each answer to the document, and says when it does not know.

### Plain-language questions to your data

Ask 'which orders from Germany were late last month' and get the figures with the query shown. It runs read-only on your existing database or reports, so it reads data and never changes it.

What we build

answer back

## From one set of questions to a tool

### 1. Pick one workflow and its questions

It starts with one team and the questions it asks most, for example the service desk or onboarding. Together we list which sources hold the answers and who may see them. This is the automation review: one workflow, a fixed scope, a short, fixed timeframe.

### 2. Prototype on your real documents

The prototype runs on your real sources and is tested with questions your team actually asks. Wrong or missing answers also show where your documents need fixing.

### 3. Connect sources and permissions

Only the sources the workflow needs are connected, with permissions taken from your existing user accounts and groups. Testing with real user roles makes sure each person only gets answers from documents they may already open.

### 4. Go live where your team already works

The search or assistant goes live inside a tool your team already uses, for example the intranet, Microsoft Teams or your own platform. Every answer links to its source.

How it runs

your team uses

## Tested first on our own knowledge

You get answers grounded in documented knowledge, checked by code and approved by a person. Our own content system, which runs this website, works that way. It is our system, not client work. Four of its rules carry over to your tools.

### Agents read the rulebook before they write

Before an agent drafts a page, it loads a structured packet with our voice rules, audience profiles and component rules. The draft is grounded in our documented knowledge, not in what the model guesses.

### Every section is sized for AI search

AI search tools split pages at headings. Each section on this site is checked against a size budget and must name its subject in its first sentence. Your documents get prepared for search the same way.

### Deterministic validation on every write

A command-line check rejects drafts that break the rules before a person reviews them. The model drafts, and code decides what is valid.

### Nothing publishes without a named approval

Agent output stays a draft. Publishing needs an explicit approval phrase from a person, and writes to the live site are gated and can be switched off completely.

Our own system, not client work

## What can go wrong with AI search, and how we handle it

Search and assistants touch your internal documents. These risks are planned for from the first workflow onward.

| Risk | Likelihood | Mitigation |
| --- | --- | --- |
| People see documents they should not | Depends | Results are filtered per user, based on the permissions in your existing accounts and groups. Testing uses real user roles before anything goes live. |
| Confident but wrong answers | Medium | Answers come only from approved sources and link to the passage used. When the sources do not cover a question, the assistant says so instead of guessing, and the question is logged. |
| Your data used to train models | Low | We build on Azure AI Foundry. Microsoft's terms for Azure AI Foundry state that prompts and documents are not used to train the models. Only the sources the workflow needs are connected. |
| EU AI Act obligations | Depends | Internal search and assistants are usually not high-risk under the EU AI Act, but users must know they are talking to AI. The assistant is labelled clearly, and uses that could be high-risk, such as decisions about employees, are flagged. |
| Running costs that grow quietly | Medium | Model and search costs grow with use. Running cost is measured on the prototype with your real questions and volume, before you decide to go live. |
| Answers based on old documents | Medium | Outdated manuals stay in folders for years. We agree which sources count as current and remove retired documents from the index, so they drop out of answers. |

## Questions about AI search and assistants

What teams ask before they connect their documents to an assistant.

### Do we need to clean up all our documents first?

No. The work starts with the sources one workflow needs. The prototype shows which of your documents are outdated or contradict each other, so you clean up only what the workflow uses.

### Can the assistant show information to people who should not see it?

It should not, and that is designed in from the first workflow. Results are filtered by the permissions your team already has in your existing systems, and testing uses real user roles before go-live.

### Is our data used to train AI models?

Microsoft's terms cover this for Azure AI Foundry, the platform we build on, and the risk table above quotes them. Only the sources one workflow needs are connected.

### What happens when the assistant does not know the answer?

It says so. Answers come only from approved sources, each with a link to the source. Questions it cannot answer are logged, which also shows you where documentation is missing.

### What does it cost to run?

Running cost depends on how many documents are indexed and how many questions your team asks. We measure it on the prototype with real usage, before you decide to go live.

### Do we need a new platform for this?

Usually not. The search or assistant sits inside tools you already use, such as your intranet, Microsoft Teams or your own platform, and reads documents where they already live.

## Other Applied AI

AI search & knowledge is one of four Applied AI lines. All four start with the same automation review on one workflow.

service lines

### AI strategy & discovery

- Feasibility check on one real workflow
- Prototype on your own data, not a demo set
- Roadmap with cost, risk and EU AI Act exposure

[AI strategy & discovery](https://netmedia.agency/services/ai-strategy-discovery)

### AI product development

- Assistants and search inside your product
- Generative features in an existing platform
- Agents that act through your APIs, with guardrails

[AI product development](https://netmedia.agency/services/ai-product-development)

### AI automation

- Document capture and processing
- Handoffs between inbox, CRM and ERP
- Content and catalogue work with human approval

[AI automation](https://netmedia.agency/services/ai-automation)

## Start with one workflow and its questions

In the automation review you bring one team's questions. Together we check which sources hold the answers and test on your real documents. You get a working first version or a clear no-go.

Book an automation review

FIRST STEP

Automation review

One workflow · Your real documents · A clear outcome

- It starts where the same questions come up every week, with one team.
- The prototype answers real questions from your real sources, with the source shown.
- Either a first version your team can use, or a plain explanation of why this workflow is not ready yet.
