Building your knowledge hub

In this article

• Overview
• Before you begin
• Building your knowledge hub step by step
• Organizing and maintaining your knowledge hub
• Using your knowledge hub across AutogenAI
• Best practices
• Summary

Overview

Your knowledge hub is the content library AutogenAI draws on to write with your evidence, in your voice. Build it before your first project, and every project starts with source material.

The knowledge hub holds the reusable content your team relies on for every proposal:

• Libraries and folders – documents such as case studies, past responses, policies, and CVs
• Datasets – structured data arranged in rows and columns, such as CVs or company facts
• Saved prompts – prompts your team has refined and wants to reuse

When you write, source providers let you choose which of these AutogenAI uses. When you create a project, you can connect existing libraries from the knowledge hub so the AI has context from the start.

This guide walks through building your knowledge hub from scratch.

Why build it first

• AutogenAI can only draw on what you give it. A well-stocked library means more of your own evidence in every draft.
• Projects start faster. Connecting an existing library is one step in project setup, instead of uploading files each time.
• Your content works across every proposal. Build once, reuse on every project and document.

Before you begin

A little preparation up front saves rework later. Before you add anything to the knowledge hub, work through this checklist:

• Gather your best content. Pull together the documents you would want AutogenAI to draw on, such as case studies, past project data, company policies, CVs, and strong previous responses.
• Clear out the clutter. Leave out outdated, duplicate, or draft versions so AutogenAI does not draw on them.
• Decide how you'll organize it. Folders work best when they follow how your team looks for content, for example by topic, sector, or client.
• Check your access. You will only see the libraries and folders you have access to. If something is missing, ask your administrator.

Documents or datasets?

Not all content belongs in the same place. Use this table to decide.

Tip: If a document contains many separate facts that you ask about again and again, a dataset will usually return more consistent answers than the document alone.

Building your knowledge hub step by step

Building the knowledge hub takes six steps. Steps 1 to 4 set up your document library. Steps 5 and 6 add structured data and reusable prompts, and are worth doing even though each project can run without them.

Step 1: Open the knowledge hub

Open the knowledge hub from the left-hand navigation bar. You will see the libraries you have access to. Each library is a collection of documents, folders, datasets, and saved prompts.

Step 2: Choose or create your library

Open the library you want to build in. If your team is starting from scratch, create a new library to hold your reusable proposal content.

Choose a name your whole team will recognize at a glance, such as the name of your team or business unit.

Step 3: Add your documents

Upload the source documents you gathered in the checklist. These become the evidence AutogenAI draws on when you generate content.

• Add your strongest, most current content first. You can always add more later.
• Use clear file names. "Case study - NHS digital transformation" is easier to find and select than "Final v3".

Step 4: Organize with folders

Group your documents into folders that follow how your team searches for content, for example by topic, sector, or client.

Folders matter beyond tidiness. When you generate content, you can choose specific folders or files as your source instead of the whole library, so a clear structure lets you point the AI at exactly the right material.

Step 5: Add datasets for structured data

Datasets turn repeated facts, such as CVs, revenue figures, or standard answers, into searchable rows and columns. To create one:

1. In your library, open the Datasets tab.
2. Select +Dataset. Create a blank dataset, or upload an existing Excel or CSV file.
3. Enter a name and a short description. Both are required, and they help AutogenAI understand what the dataset contains.
4. Choose a Dataset Type (see the table below).
5. Name each column clearly and specifically, for example "Company revenue (GBP)" rather than "Details".
6. To extract data from files already in your library, select the three dots in the top right and choose Populate Dataset from Files.

If you uploaded a spreadsheet, keep it clean: one header row, no merged cells, and no multi-tab workbooks, since AutogenAI reads only the first tab of an Excel file.

Tip: Column names act as instructions to the AI. Run a few test questions after setup to confirm answers are coming from the right column. For a full walkthrough, see Datasets for best results.

Step 6: Save the prompts your team reuses

Once a prompt works well, save it so your whole team can reuse it.

1. Open Saved Prompts, found under your library sources in the knowledge hub.
2. Select New Prompt, give it a name, and paste in your prompt text.
3. To use it later, select the Saved Prompts icon in the Ask AI or research prompt box. Choosing a prompt fills it into the box, ready to edit or send.

Quick reference

Organizing and maintaining your knowledge hub

A knowledge hub is only as useful as it is current. A few habits keep it that way.

• Replace, don't pile up. When you update a case study or policy, swap out the old version so AutogenAI does not draw on outdated content.
• Review datasets after changes. AutogenAI does not automatically refresh existing rows when you add columns or update source files, so revisit a dataset whenever either happens.
• Keep datasets focused. Each dataset should cover one topic, client, or subject area. Mixed-purpose datasets are harder to name well and harder for the AI to search accurately.
• Name consistently. Agree on a pattern for file and folder names so anyone on the team can find and select content quickly.
• Check access. Each person sees the libraries and folders they have access to. If a colleague cannot find content they need, review their access with your administrator.
• Name an owner. Assign someone to review the knowledge hub regularly, so upkeep does not depend on whoever happens to notice a gap.

Tip: If you would like help with knowledge management or optimizing your proposal library, your Customer Success Manager can support you.

Using your knowledge hub across AutogenAI

Once your knowledge hub is built, it feeds your work in four places.

Narrowing your sources

By default, AutogenAI can draw on everything you have access to. To focus it got to Settings > Source Selection:

• Turn off Generate using all Library Documents to choose specific folders or files.
• Turn off Generate using all datasets to choose specific datasets, including specific columns.

Every library and folder you have access to appears in the menu, which is why a clear folder structure pays off here.

Tip: Use a narrower source selection when the answer should come from specific evidence, such as one case study or one set of CVs. Use the full library for broader questions.

Connecting your library to a project

When you are ready to start a proposal, the next article, Creating a new project, takes you through project setup. At the project library step, select the libraries you just built so AutogenAI has context for your storyboard from the start.

Best practices

• Start small and strong. A focused library of your best, most current content beats a large archive of everything you have ever written.
• Match the content to the container. Use documents for narrative evidence and datasets for repeated facts you ask about often.
• Name things for the people who will search. Clear file, folder, and column names help both your team and AutogenAI find the right content.
• Test before you rely on it. After setting up a dataset, run a few sample questions to confirm answers pull from the right column.
• Build your knowledge hub before your first project. It makes the project library step quick, and gives AutogenAI context from day one.

Summary

Building your knowledge hub gives every future project a head start. The path is short:

1. Prepare. Gather your best content and decide how to organize it.
2. Build. Add documents to your library and group them into folders.
3. Structure. Add datasets for repeated facts, and save the prompts your team reuses.
4. Connect. Use your knowledge hub through source providers, and connect it to each new project.