AWS Quick adds chat-built flows, multi-agent answers and an updated web app
Amazon Web Services has updated AWS Quick, its AI workspace for work, so users can describe a business process in chat and have Quick build a flow that orchestrates agents, skills, tools and data, the company says. New deterministic steps are meant to make workflows consistent and verifiable, and flows can now run longer and handle larger data volumes.
With multi-agent orchestration, several specialised agents work on one request at the same time and Quick combines their findings into a single response. The updated web app shows a daily briefing and items that need attention, and keeps work running after the tab is closed. Quick also adds connectors for Meta ads and Amplitude, configurable content safety and sensitive-information controls for prompts, reusable skills in the web app, and support for Japanese, German, Chinese and Vietnamese. AWS gives no customer names or usage figures for the release.
We hope you enjoyed this article
Consider subscribing to one of our newsletters like Enterprise AI Brief or Daily AI Brief.
Also, consider following us on social media:
More from Enterprise
Nov 21 Hitachi Digital launches HARC Compose to govern agentic engineering Nov 20 Auterion and SkyFall plan German factory to build drones for Ukraine Nov 20 Danaher and Microsoft build an agentic platform for lab instruments Nov 20 BlackLine brings OpenAI models to its finance operations platform with agent controls Nov 19 AWS Marketplace lets AI agents research and buy software, with optional pre-approved purchasesEnterprise AI Brief
Weekly report on AI business applications, enterprise software releases, automation tools, and industry implementations.
Whitepaper
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Tensordyne
This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.
Read moreYou may also like
AWS gives AI agents four times more compute in Bedrock AgentCore
Microsoft launches Microsoft IQ to give AI agents a company's own context
Expedient adds agent tools and spending controls to its AI CTRL governance platform
Amazon Revises Engineering Guidelines for AI Written Code
OpenAI makes ChatGPT Enterprise available through AWS Marketplace
Daily AI Brief: the AI news that matters, in your inbox.