product update

AWS Quick adds chat-built flows, multi-agent orchestration and an updated web app

TL;DR

AWS Quick users can now describe a business process in chat and have Quick build a flow that orchestrates agents, skills, tools and data. The release also adds multi-agent orchestration, an updated web app with a daily briefing, Meta ads and Amplitude connectors, and new language support.

3 min read
0

AWS Quick, which AWS describes as an AI workspace built only for work, now lets users build flows entirely through chat and run several specialized agents on a single prompt. AWS announced the updates on its Machine Learning Blog.

What shipped

Flows built in chat. Users describe a process in conversation and Quick builds a flow that orchestrates agents, skills and tools, with access to structured data, knowledge and apps. A diagram beside the chat shows each step. AWS says new deterministic steps make workflows consistent and verifiable, and flows now support longer-running workflows and large data volumes. Flows can be started from the web, desktop or mobile app.

Updated Quick web app. The home screen now shows items that need attention plus a daily briefing. The app adds the agents and skills users built on desktop, and keeps work running after the browser tab is closed. Other changes:

  • A reorganized left navigation groups agents, flows, skills, knowledge and connectors under Customize.
  • A feed and daily briefing list email and messages that need a response in priority order, and Quick can draft replies for the user to review and send.
  • Users can schedule tasks or start longer requests, then review results and respond to waiting agents in Mission Control.
  • Library collects recent work, favorites, pinned items, and documents and files created in Quick.
  • Conversations, agents and files sync across web, desktop and mobile.

AWS says existing dashboards, topics and spaces work as before and nothing needs to be turned on.

Multi-agent orchestration. The agent a user asks can bring in several specialized agents at once, each working on the part it knows best, and then combines their work into one response. Each agent keeps its own instructions, knowledge and context.

Data connectors. Quick now connects to Meta ads and Amplitude, so users can query them in natural language and combine the answers with other sources.

Skills, governance and languages. Users can turn the way they do a task into a reusable skill, now in the web app. Configurable content safety and sensitive-information controls apply to user prompts. Quick adds support for Japanese, German, Chinese (Simplified and Traditional), and Vietnamese.

AWS's worked example

AWS illustrates the flow feature with a fictional finance scenario. A planning and analysis manager describes her monthly cost and margin report in chat. The resulting flow pulls results from a Quick dashboard, processes several regions at the same time, compares each against a budget spreadsheet using set formulas, flags regions that moved beyond her thresholds, and drafts commentary using a team skill. It then drafts a Microsoft Excel summary and a report email, and notifies the team in Slack. She publishes the flow, and a teammate runs it from the Quick desktop app, where it can use a spreadsheet saved on his computer. He reviews the draft before approval.

Customer claim

Pomelo, a Latin American fintech provider, is quoted by AWS. Rodrigo Marini, Head of Data at Pomelo Fintech Services S.A.S., says that without growing the team, nearly four times as many people now work with data each month, and that a single use case saves 80 hours of work per month. These figures are Pomelo's own statements.

What this means

The release moves Quick from answering individual requests toward repeatable, shared processes. Deterministic steps handle fixed calculations and checks, agents handle drafting and analysis, and a human reviews the output before it goes out. Multi-agent orchestration lets one request draw on several agents without merging their instructions or knowledge. Background execution and the Mission Control review step mean work can continue while the user is away and still pass through a person. The content safety and sensitive-information controls give administrators configurable settings for user prompts.

Related Articles

product update

Google rolls out computer use in the Gemini app for Mac for multi-step desktop tasks

Google announced on November 19, 2026 that computer use is rolling out in the Gemini app for Mac. Gemini can carry out multi-step work across local files, desktop applications and websites, working in an isolated background window with a live preview in the chat.

product update

Nous Research brings open-source Hermes Agent to Microsoft Teams, adds Collective Wisdom skill sharing

Nous Research says companies will soon be able to run its open-source Hermes Agent directly in Microsoft Teams, with agents sandboxed in Azure Container Apps. A new feature, Collective Wisdom, lets employees share reviewed skills with colleagues, and the shared knowledge stays inside the company.

product update

Databricks opens Genie ZeroOps public beta after agent observed 80,000+ customer issues in private preview

Databricks opened Genie ZeroOps to public beta on November 19, 2026, after private-preview testing. The company says the autonomous data-pipeline agent observed more than 80,000 real customer issues during that limited preview.

product update

Gemini adds Google Wallet as a Connector for spending analysis, rewards advice and ticket lookup in the US

Google Gemini now supports Google Wallet as a Connector through its Personal Intelligence features, letting users ask about spending, generate charts, understand card rewards and retrieve saved passes and tickets. The rollout covers Gemini users in the US on web and mobile. Bank and card linking runs through Plaid and is optional and read-only.

Comments

Loading...