← Back
AWS ML Blog

Bring structured and unstructured data together with Amazon Quick

•17 min read•
#agents
Level:Intermediate
For:AI Engineers
✦TL;DR

Amazon Quick provides a unified experience for querying both structured datasets and unstructured S3‑backed knowledge bases through a single conversational AI agent. By creating a Space that references enriched datasets (with semantic descriptions for SQL translation) and a knowledge base (indexed from PDFs in S3), the agent can automatically route queries to the appropriate source and return combined answers with citations. This architecture lets engineers extend data sources over time while preserving user permissions and applying built‑in content‑safety guardrails.

⚡ Key Takeaways

  • Requires an Amazon Quick Enterprise subscription to create enriched datasets.
  • Uses a “Space” component to merge knowledge bases (unstructured) and enriched datasets (structured) into one workspace.
  • The custom chat agent decides at query time whether to invoke the knowledge base, the dataset, or both, balancing query relevance and latency.
  • Integration is configured via Amazon Quick’s admin console where S3 buckets are granted read‑only access for knowledge base indexing.
  • Responses respect the requesting user’s permissions, and Amazon Quick applies built‑in AI guardrails such as content safety screening.
💡 Why It Matters

Engineers can now build a single AI‑driven interface that surfaces insights from both relational data and document stores without stitching together separate tools, accelerating data‑driven decision making while maintaining security and compliance.

✅ Practical Steps

  1. In the Amazon Quick admin console, grant the Quick service read‑only access to your Amazon S3 bucket under Permissions → AWS resources → Select S3 buckets.
  2. Upload your unstructured PDFs (e.g., AnyCompany_Business_Review.pdf) to the S3 bucket and create a knowledge base that indexes these files.
  3. Create an enriched dataset by uploading your structured CSV/Excel file, then build a Space that references both the knowledge base and the dataset, and finally configure a custom chat agent linked to that Space.

Want the full story? Read the original article.

Read on AWS ML Blog ↗

More like this

New in AWS Quick: More capable flows, an updated web experience, and agents that work together

AWS ML Blog•#agents

How Google Duplex evolved to also call businesses for you in Gemini

Google Research•#agents

Genie ZeroOps, now in public beta: An autonomous agent that fixes data pipelines, with lessons from 80,000 customer issues

Databricks Blog•#agents

Towards a Science of Capable Autonomous Agents & Provable Safety — Part II

CMU ML Blog•#agents

EXPLORE AI NEWS

Daily hand-picked stories on LLMs, RAG, agents and production AI — curated for engineers who ship.

BROWSE NEWS

GET THE WEEKLY DIGEST

Join engineers getting the Monday signal-over-noise AI breakdown. No spam, unsubscribe anytime.

LEARN AI ENGINEERING

Curated courses, research papers, repos and tutorials built for engineers leveling up in AI.

START LEARNING