Bring structured and unstructured data together with Amazon Quick

Organizations collect data in many forms. Structured data lives in databases and spreadsheets, whereas unstructured data sits in documents, reports, and files stored across file systems. Analyzing both together typically requires switching between multiple tools, running separate queries, and manually correlating results.

Amazon Quick addresses this with a unified experience. You can connect structured data through enriched datasets and unstructured data through S3-backed knowledge bases. You can then query both through a single conversational AI agent.

In this post, you learn how to:

• Connect Amazon Simple Storage Service (Amazon S3) as a data source and create a knowledge base.
• Build a Space that combines structured and unstructured data.
• Create and configure a custom chat agent that queries across both data types.
• Ask questions that span structured and unstructured sources in a single conversation.

Solution architecture

The following diagram illustrates how each component connects to deliver a unified data experience through Amazon Quick.

Figure 1: Solution architecture for combining structured and unstructured data in Amazon Quick

The architecture has three layers:

• Data layer: Your data exists in two forms. Unstructured content (documents, PDFs, reports) is stored in Amazon S3 and indexed through a knowledge base. Structured data (metrics, sales figures, and operational key performance indicators) is loaded as enriched datasets with semantic descriptions that the agent uses to translate questions into SQL.
• Workspace layer: A Space brings both data types together into a single workspace. The Space references your knowledge base for unstructured queries and your datasets for structured queries. It can also include dashboards, file uploads, and action connectors. This is the layer where data from different sources converges into a unified context.
• Agent layer: The custom chat agent links to the Space and uses it as its knowledge source. When a user asks a question, the agent determines whether to query the knowledge base, the dataset, or both, and returns a combined response with citations. Amazon Quick also applies built-in AI guardrails, such as content safety screening, to chat interactions.

With this layered approach, you can expand the solution over time. When you add a new data source to the Space, the agent linked to that Space can use it, and responses respect the permissions of the user who asks.

Prerequisites

To follow along with this walkthrough, you need:

• An Amazon Quick account with an Enterprise subscription for the user who follows this walkthrough (creating datasets requires Enterprise). For details, see Amazon Quick pricing.
• An Amazon S3 bucket for your business documents. To create one, see the Amazon S3 User Guide.
• Amazon Quick access to your S3 bucket, granted by an Amazon Quick administrator. In the admin console, the administrator chooses Permissions, then AWS resources, selects Amazon S3, and chooses Select S3 buckets. Selected buckets have read-only permissions by default.
• Permissions to create integrations, knowledge bases, datasets, spaces, and chat agents in Amazon Quick.

Prepare your sample data

This walkthrough uses two types of data:

Unstructured documents: Upload these to your Amazon S3 bucket for the knowledge base:

Structured data: Download this file to your computer. You upload it directly to Amazon Quick in Step 3:

Step 1: Create an Amazon S3 integration

Start by connecting Amazon Quick to your S3 bucket. From the Amazon Quick console, select Knowledge in the left navigation panel.

The knowledge page shows available connector types, including Amazon Q Business, Web Crawler, Amazon S3, and third-party options like Google Drive, OneDrive, and Microsoft SharePoint.

Under Amazon S3, choose Add. In the Create S3 knowledge base dialog, on the Connect S3 bucket page, provide the following details:

• Name: A descriptive name for your integration (for example, “My Data Access Integration”).
• S3 bucket location: Choose Quick Suite instance account to use a bucket in the same AWS account as Amazon Quick, or Other AWS account for a bucket in a different account.
• S3 bucket URL: The S3 URI of the bucket containing your data. The bucket must be in the same Region as Amazon Quick.

Choose Next.

Figure 2: Create integration dialog showing the S3 connection fields

Step 2: Create a knowledge base

After the S3 integration is created, Amazon Quick prompts you to create a knowledge base. The knowledge base indexes your S3 content for AI-powered search.

Configure the knowledge base:

• Name: “Business Knowledge Base”.
• Description (optional): Notes about how the knowledge base will be used.
• Content: Select “Add all content” to index everything in the connected S3 bucket, or “Add specific content” to specify the S3 prefixes for the folders and files to include (prefix filters are case-sensitive).

Next: Additional settings opens optional settings for document-level access control lists (ACLs) and a metadata files folder. Decide whether to use ACLs before you create the knowledge base, because you can’t change that choice later. This walkthrough uses sample data, so the default settings are sufficient. For details, see Set up and manage Amazon S3 integration.

Choose Create. A success banner confirms the S3 integration, and the knowledge base begins indexing in the background.

Figure 3: Create knowledge base dialog with the Business Knowledge Base name and content options

Step 3: Create and enrich a dataset

A dataset is your structured data file loaded into Amazon Quick. By enriching the dataset with semantic descriptions, custom instructions, and correct data types, the AI agent can interpret your data more accurately. It can then translate natural language questions into SQL queries.

Create the dataset

1. From the Amazon Quick home page, navigate to Data in the left navigation.
2. Choose Create dataset, then select Upload file.
3. Select the Product_Sales.csv file you downloaded earlier and choose Open.
4. On the confirmation screen, review the column names and data types. Choose Next to create the dataset.

Amazon Quick ingests the file into SPICE (the in-memory calculation engine) and the dataset appears in your dataset list.

The dataset takes its name from the uploaded file, so it appears as Product_Sales.csv in your account.

Enrich the dataset

Enriching your dataset with semantic information helps the AI understand your data in business context. The agent uses this context to translate natural language questions into more accurate SQL queries. From the dataset page, choose Edit dataset to enter the data preparation view.

Transform: Fix data types

In the Transform tab, update data types for columns that were auto-detected incorrectly. For this dataset:

• Change Order Date and Date Key from String to Date.
• Change Customer ID from String to Integer.
• Change Sales, Discount, and Profit from String to Decimal.
• Change Quantity and Unit Price from String to Integer.

Figure 4: Transform view showing data type changes applied to the Product_Sales.csv dataset

Output: Add semantic context

Select the Output tab to access the dataset-level enrichment fields. Here you provide context that helps the AI understand what your data represents and how to use it.

Description: Add a dataset-level description:

“Product sales transaction data for AnyCompany, covering orders from FY2024-FY2025 across North America, EMEA, Asia Pacific, and Latin America. Includes order details, customer information, product lines, and revenue metrics.”

Custom instructions: Add guidance for how the AI should query this data:

USAGE GUIDELINES:

• Revenue values are in USD.
• When comparing performance, group by Region (North America, EMEA, Asia Pacific, Latin America).
• Order Date should be used for time-based trend analysis. The fiscal year matches the calendar year.
• Date Key is a numeric YYYYMMDD representation of Order Date.
• Sales = Quantity x Unit Price x (1 – Discount)

COMMON USE CASES:

• Regional sales performance comparison.
• Product line revenue analysis.
• Quarterly trend identification.
• Customer segmentation by industry and segment.

TAGS: Sales, revenue, orders, regional performance, product analytics

Column descriptions: Select each column in the left panel and add a description. For example:

• Order ID: “Unique identifier for each sales transaction (format: REGION-YYYY-NNNNNN)”
• Region: “Geographic sales region: North America, EMEA, Asia Pacific, or Latin America”
• Product: “AnyCompany product name: Analytics Pro, Connect, Automate, AI Assistant, Data Catalog, or Integration Hub”
• Sales: “Order revenue in USD after discount”
• Segment: “Customer size segment: Enterprise, Mid-Market, or SMB”

Figure 5: Output view showing dataset details with Description and Custom instructions configured

Choose Save & publish to save your changes. The dataset summary now shows the columns with their correct data types and the descriptions you added.

Figure 6: Enriched Product_Sales.csv dataset summary showing all 16 columns, data types, and descriptions

This enriched dataset provides the structured data layer for your solution. When the agent receives a natural language question about sales data, it uses these descriptions and instructions to generate more accurate SQL queries. Combined with the knowledge base from Step 2, you now have both structured and unstructured data ready to bring together in a Space.

Step 4: Create a Space

Spaces in Amazon Quick act as unified data workspaces. A Space can hold file uploads, dashboards, knowledge bases, actions, and datasets, giving your chat agent a single location to query across data types.

From the left navigation, select Spaces and create a new Space. Name it “Business Intelligence Hub”.

Add your knowledge base and dataset to the Space:

1. Choose Add knowledge and select Knowledge bases from the list. Select “Business Knowledge Base” from the list.
2. Choose Add knowledge again and select Datasets from the list. Select “Product_Sales.csv” from the list.

The Space now shows both your knowledge base (unstructured documents) and your enriched dataset (structured sales data) linked as data sources. This is the central hub where both data types come together, giving your chat agent a single place to query across everything. Figure 7 shows the Space with both resources in the Ready state.

Figure 7: Business Intelligence Hub Space showing the Product_Sales.csv dataset and Business Knowledge Base

Step 5: Create a custom chat agent

Navigate to Chat agents in the left navigation and choose Create chat agent. Amazon Quick presents a prompt builder where you can describe your agent in natural language or choose from templates like Training Guide, Project Coordinator, and Onboarding Helper.

For this walkthrough, choose Skip to configure the agent manually.

Figure 8: Chat agent creation screen with the prompt builder and sample templates

Configure the agent persona

The configuration panel has several sections. Start with the Agent Persona:

• Agent identity: “Business Intelligence Assistant”
• Description: “An AI assistant that breaks down information silos by analyzing business data from your knowledge base”

For Agent Persona instructions, enter:

You are a Business Intelligence Assistant designed to help organizations break down information silos. Your primary functions are:

1. Analyze business data stored in S3
2. Retrieve relevant findings from the reports and memos in the knowledge base
3. Provide comprehensive insights that connect internal data with external trends
4. Generate clear, actionable recommendations based on data analysis

When answering questions, always cite your sources and explain how you arrived at your conclusions. Focus on delivering practical business value and highlighting patterns across different information sources.

A note appears confirming that your chat agent comes equipped with enterprise guardrails.

Figure 9: Agent persona configuration with identity and persona instructions filled in

Set communication style

Under Communication style, pick a response style preset. Options include Executive, Technical, and Creative. For a business intelligence use case, select Executive.

Link knowledge sources

Under Knowledge Sources, choose Link spaces and select the “Business Intelligence Hub” Space you created earlier. This gives the agent access to your S3 knowledge base and other data sources in that Space. When you link a Space, the agent answers from large language model (LLM) knowledge and the linked resources only.

You can also attach reference documents (PDF, TXT, HTML, MD, CSV, DOC, DOCX) directly to the agent for additional context. Amazon Quick extracts up to 100,000 characters of text from the reference documents that you upload.

Figure 10: Knowledge Sources section showing the linked Business Intelligence Hub Space

Customize the agent

Under Customization, configure:

• Welcome message: “Hello! I’m your Business Intelligence Assistant. I can help you analyze your sales data and business documents and provide insights by comparing internal information with market trends. How can I help you today?”
• Suggested prompts: “Summarize key insights from our reports” and “Analyze our quarterly sales performance”

Figure 11: Customization section with the welcome message and suggested prompts

Launch the agent

Choose Launch chat agent. The right panel shows a live preview of your agent with the welcome message and suggested prompts displayed.

Figure 12: Launched Business Intelligence Assistant with the welcome message and suggested prompts in the chat panel

Step 6: Query across structured and unstructured data

With the agent running, start with a question about your business results:

How did sales change by region in 2025?

For this question, the agent combines results from the Product_Sales.csv dataset with the documents in the S3 knowledge base. It returns a response with regional sales breakdowns, trends, and citations that point back to each source.

Figure 13 shows the response. Each citation marker links a figure back to its source document.

Figure 13: Chat agent response showing regional sales analysis from the dataset and the knowledge base documents

When you ask a question about structured data, the agent uses text-to-SQL to translate your natural language into a SQL query. It runs the query against the dataset and returns the results in a readable format. This means you can ask complex analytical questions without writing SQL yourself.

Next, ask about a specific document:

What are the key strategic priorities outlined in our product strategy memo?

The agent summarizes the strategic pillars, the FY2026 roadmap, and the investment requirements from the Product Strategy Memo, as shown in Figure 14.

Figure 14: Chat agent response summarizing strategic priorities from the Product Strategy Memo

Finally, ask a question that needs both data types:

How do our 2025 sales results align with the market trends identified in our analysis report?

The agent compares the trends in the Market Analysis Report with results from your sales data and cites each source, as shown in Figure 15.

Figure 15: Chat agent response comparing 2025 sales results with market trends from the Market Analysis Report

This is the core value of combining data types in a single Space. The agent can pull from structured CSV data and unstructured documents in the same response. You don’t need to know where the data lives.

Step 7: Generate artifacts and reports using natural language

The Business Intelligence Assistant can also generate formatted documents, including Microsoft PowerPoint presentations, Microsoft Excel spreadsheets, and Microsoft Word documents. Try these prompts in the chat agent:

• “Create a PowerPoint presentation summarizing AnyCompany’s Q4 2025 sales performance by region, including key trends and recommendations.”
• “Generate an Excel spreadsheet showing the top 10 orders by revenue with Order ID, Region, Product, and Revenue columns.”
• “Create a Word document with a quarterly business review summary based on our annual review data.”

Figure 16: Chat agent confirming the request and preparing a PowerPoint outline for AnyCompany’s Q4 2025 sales performance

Figure 17: Generated eight-slide PowerPoint with a downloadable AnyCompany_FY2025_Sales_Performance.pptx file

Step 8: Share the agent

When you launch a chat agent, it remains private until you share it. After you test the agent, share it with your team:

• From the left navigation, choose Chat agents.
• In the Actions column for Business Intelligence Assistant, choose the menu icon, and then choose Share.
• Enter the users or groups to share with, assign Owner or Viewer permissions, and then choose Share.

The agent returns permissions-aware responses, and a knowledge base is available only to its creator until you update its permissions. Make sure that the people you share the agent with also have access to the Space, the knowledge base, and the dataset. For details, see Custom chat agents.

What you accomplished

In this walkthrough, you:

• Connected Amazon S3 as a data source through an integration.
• Created a knowledge base that indexes unstructured business documents.
• Created and enriched a Product Sales dataset for structured data queries.
• Built a Space that serves as a unified data hub for your chat agent.
• Configured a custom chat agent with a defined persona and linked knowledge sources.
• Queried the agent across structured and unstructured data in a single conversation.
• Generated a PowerPoint presentation from a chat prompt.
• Shared the agent with your team.

Best practices

Use the following practices as you move from this walkthrough to your own data:

• Organize your S3 data: Use clear folder structures and file naming conventions. A clear structure also makes it more straightforward to scope a knowledge base to specific S3 prefixes.
• Write specific persona instructions: The more specific your instructions, the more consistent the agent responses. Include guidance on how to cite sources and handle ambiguous queries.
• Use Spaces to control scope: Rather than giving an agent access to everything, create focused Spaces with only the data sources relevant to that agent’s purpose.
• Start with suggested prompts: Suggested prompts help users understand what the agent can do. Choose prompts that demonstrate the agent’s range across both structured and unstructured data.
• Test before sharing: Use the preview panel to test your agent with representative questions before sharing it with your team.

Security considerations

Under the AWS shared responsibility model, you are responsible for configuring access to your data, knowledge bases, and agents. Consider the following as you adapt this solution:

• Grant least-privilege S3 access: Give Amazon Quick access only to the buckets that your knowledge bases need. Buckets that an administrator selects have read-only permissions by default. If you create knowledge bases through the API, you can provide a custom AWS Identity and Access Management (IAM) role for an individual S3 data source instead of granting account-wide S3 access.
• Control document access: If documents require per-user or per-group access, enable document-level ACLs when you create the knowledge base. You can’t change this choice later.
• Encrypted buckets: If your bucket uses AWS Key Management Service (AWS KMS) keys, follow the AWS KMS steps in the administrator setup guide.
• Add only trusted content: The agent uses the documents in your knowledge base to form responses, so include only content from sources you trust.
• Share selectively: Chat agents and knowledge bases are private by default. Share them only with the users and groups that need them.
• Use guardrails as one layer: Amazon Quick includes built-in content safety screening, and administrators can add up to 50 blocked words or phrases. These controls help reduce risk but don’t replace your responsibility to configure access and permissions. For details, see AI guardrails in Amazon Quick.

Clean up

To avoid ongoing charges, remove the resources you created:

• Delete the chat agent from the Chat agents page.
• Delete the Space from the Spaces page.
• Delete the Product_Sales.csv dataset from the Datasets page.
• Delete the knowledge base and S3 integration from the Knowledge page.
• If you created an S3 bucket specifically for this walkthrough, empty and delete it. Deleting a bucket and its objects is permanent, so back up any data that you want to keep.

Amazon Quick user subscriptions and account fees are billed separately from these resources. For details, see Amazon Quick pricing.

Conclusion

Amazon Quick helps you bring structured and unstructured data together. In this post, you connected S3 as a knowledge base, enriched a dataset, built a Space, and created a custom chat agent. Business users can now query both data types through a single conversational interface, without needing to know where the data lives or how to write queries.

About the authors