Amazon’s Q Business AI agents gets smarter

A year ago, AWS announced Q, its AI assistant platform for business users and developers. Q Developer is getting a wide range of updates today and so is Q Business. The focus for Q Business is on new integrations that can help businesses bring in more data from third-party tools, the ability for third-party platforms to integrate Q into their own services, and new actions that will allow Q to perform tasks on behalf of its users across third-party applications like Google Workspace, Microsoft 365 and Smartsheet, among others.

More Q in QuickSight

Previously, Q was already able to pull in data from about 40 enterprise tools ranging from data stores like Amazon’s own S3 to services like Google Drive, SharePoint, Zendesk, Box and Jira. Q then creates a canonical index of all of this data (keeping access permissions and other settings intact). The idea now is to expand the types of data the service can index and then use that to provide ever more personalized results. This index, after all, is at the core of Q’s capabilities.

Image Credits:TechCrunch

Now, business will be able to take the data they have stored in databases, data warehouses, and data lakes and combine it with the rest of their business data, be that documents, wikis or emails — and they can now do so in QuickSight, AWS’ business intelligence service. Amazon Q in QuickSight, the company says, will allow employees to query this data and quickly generate charts and graphs with the help of Q (or augment existing charts with content from a wider variety of sources).

These new features are now in preview.

More Q on third-party platforms

The feature that is maybe the most interesting from a business perspective is that third-party services like Zoom, Asana, Miro, PagerDuty, Smartsheet and others will now be able to integrate Amazon Q Business into their own services. These services will get access to an API that will allow their generative AI-powered experiences to access the same index that is also used by Q.

Asana, for example, is integrating Q Business and Asana AI to help its customers find information from other third-party applications (that are indexed by Q) without having to leave Asana. And from there, they can then also kick off Q workflows and take actions in these third-party tools as well.

Image Credits:TechCrunch

Similary, Zoom will use the Q index to enhance its own AI assistant so that, for example, the Zoom AI Companion can transcribe and summarize a meeting while Q looks for relevant documents, email or wiki entries related to the call.

AWS stresses that all of these features will only surface information that the users have permission to access.

In this context, it is worth noting that others, including Atlassian’s Rovo, also heavily focus on third-party data integrations (Rovo offers about 80 or so connectors at this point). For many of them, including Atlassian, the idea is to keep users on their own platforms, though, not to have third-party services integrate their assistants and indexes. That’s an interesting play on AWS’ part.

More Q for more workflows

The dream of productivity nerds has long been to automate more of the repetitive but hard to automate processes that are part and parcel of running a business. With this update, Q Business will now feature a library of more than 50 actions that Q can perform for them, but more importantly, AWS is going beyond the workflow automation tools it already offered with Q. The service now uses generative AI so that users can simply describe a workflow using natural language or upload a document that describes a given process. They can also use a browser plugin to let Q capture how they perform an action step-by-step. Q Business then creates the agents that can perform and maintain this workflow.

These workflows can run at specific intervals or triggered by specific actions.

Image Credits:TechCrunch

The market for workflow automation is getting crowded with startups and incumbents like UIPath and Microsoft’s Power Automate. But it seems like the advent of generative AI may finally allow some of these products to live up to the promises of what was once called ‘robotic process automation.’ Those systems were often too brittle in real-world usage, but generative AI now allows for a bit more flexibility in how these tools interact with third-party platforms.

The new automation feature will launch in 2025.