Amazon Quick adds live data to AI-built apps
Amazon Quick, the AI‑powered unified intelligence service, now supports Live Data in Apps, letting AI‑generated web applications query governed QuickSight datasets in real time instead of using static snapshots. Builders describe the desired app in plain language, the agent discovers the relevant datasets, writes the necessary SQL, and after consent from the user, publishes an app that re‑runs…
Key points
- Live Data in Apps lets Quick apps query QuickSight datasets at view time, not build time.
- The AI agent discovers datasets, writes SQL, and runs it per viewer, respecting RLS and CLS.
- Builders need Reader Pro role, dataset consent, and supported SPICE or Direct Query datasets.
The feature works with both SPICE (in‑memory) and Direct Query datasets, requires users to have at least Reader Pro access, and mandates one‑time consent for each dataset. It enables use cases such as sales leaders pulling up‑to‑date renewal numbers, analysts viewing current metrics, and teams combining enterprise content with live data without writing code or managing DevOps.
Operational guardrails include query size limits, pagination prompts, and the need to rebuild queries if dataset schemas change. The launch is aimed at enterprises that need secure, governed, and up‑to‑date data in AI‑built applications.
Serve live, governed data in AI-built apps with Amazon Quick
AWS Machine Learning Blog · 1 October 2026
Loading the full article…
This text was published by AWS Machine Learning Blog and written by Wei Kuo. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗
The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.
More in Enterprise & Industry
All →- Microsoft launches three real-time voice AI models for developers · 1 src
- Microsoft and Google back Ossie to standardize enterprise AI data interoperability · 1 src
- Microsoft warns AI agents expand cyberthreats across enterprise systems · 2 src
- Cloudera’s Brunnick outlines hybrid AI platform strategy for enterprises · 1 src
- OpenAI pauses AI training again after agents escaped sandbox · 1 src
Comments
via GitHub Discussions