Loading video...

Video Failed to Load

Go Home

AI Agents will completely transform how we interact with corporate knowledge by applying reasoning across multiple data sources. Here's an example of ChatGPT's new knowledge feature to pull information from Box and Gmail to combine it an answer a question.

73,760 views • 1 year ago •via X (Twitter)

17 Comments

Yashsmith shah's profile picture
Yashsmith shah1 year ago

This isn't an information problem, it's a political one The real challenge isn't the reasoning, It's what happens when the Al finds a conflict between the CEO's email and the engineering spec sheet Whose 'truth' wins? We're about to automate a power struggle

Shensi Ding's profile picture
Shensi Ding1 year ago

Yes I love this!!!!

Hashbyt's profile picture
Hashbyt1 year ago

This is the true productivity gain of AI. Eliminating "work about work" by seamlessly connecting disparate systems. The ability to reason across data silos like Box and Gmail is a game-changer for internal operations. We see a parallel shift in software development, where AI agents are beginning to reason across codebases, design systems, and user analytics to streamline frontend development and improve UX coherence. The future is integrated, context-aware systems.

Akbar Ahmed's profile picture
Akbar Ahmed1 year ago

Impressive demo. At the same time another big unlock will happen when the agent is able to pick the data sources on its own.

Cassandra Tang's profile picture
Cassandra Tang1 year ago

@glean does an amazing job at this - it has changed how I work

Jason Averbook's profile picture
Jason Averbook1 year ago

Knowledge management was a database problem. Knowledge activation is a human problem. AI agents make the handoff between the two seamless. @levie

Chris Barley's profile picture
Chris Barley1 year ago

So much of a business's knowledge is stored in messy docs, complex tables in PDFs, audio and video files, etc - basically stuff that Company Knowledge will find hard to access (LLMs don't like unstructured format). The real unlock is when all company data is auto saved in company knowledge bases. These can then power agents to provide more in depth answers for internal users, as well as external queries from customers and prospects.

Data Cole's profile picture
Data Cole1 year ago

Reminds me of how DeFi protocols need to reason across multiple data sources too - oracles, on-chain data, risk parameters. The infrastructure maturity pattern feels familiar!

AIxBlock's profile picture
AIxBlock1 year ago

Yeah, it saves employees hours by aggregating info from disparate systems.

Daniel Sharon's profile picture
Daniel Sharon1 year ago

Can you really find good answers to an employee's question without transforming the company's data files?

Luke Skywalker's Hand's profile picture
Luke Skywalker's Hand1 year ago

Now show it with the secret rerouting feature they rolled out again!! ( You know, the one they use when theu censor what you say)

VibeEdge's profile picture
VibeEdge1 year ago

Impressive step forward for enterprise AI! The ability to synthesize data across tools like Box and Gmail is a game-changer for efficiency. Curious to see how it handles complex data conflicts in practice. Great work!

Jason Averbook's profile picture
Jason Averbook1 year ago

AI agents won’t just find answers but they’ll dissolve the distance between knowledge and action. The real transformation is in how fast organizations can decide and do.

Amir Ashkenazi's profile picture
Amir Ashkenazi1 year ago

Spot on. The real value is surfacing insights hidden across silos, not just retrieving files. This is a true productivity unlock.

Dustin's profile picture
Dustin1 year ago

This development highlights the incredible potential of AI to streamline information access and enhance decision-making processes in the corporate world. Exciting times ahead for knowledge management.

Ak afridi's profile picture
Ak afridi1 year ago

Perfectly captured! The "work around work" - context switching, tool stitching, system hopping - is the real productivity killer. ChatGPT's company knowledge integration is exactly what we need to eliminate this friction. Game changer! 🚀

Ready Tensor, Inc.'s profile picture
Ready Tensor, Inc.1 year ago

Now's the best time to learn about AI agents . Ready Tensor has a comprehensive Agentic AI developer program . Best part ? It's free . Check it out .

Related Videos

Today, Box is announcing major new AI agent capabilities to let customers tap into the full value of their unstructured data. First, we’re announcing all new updates to the Box AI Studio to make it even easier to build AI agents that tap into your enterprise content for any job function, business process, or industry specific use case. We are also expanding our set of foundational agents that customers will be able to use to work with their enterprise content, including new features like search and research on unstructured data. Next, we’re announcing Box Extract to enable customers to use AI agents seamlessly for complex data extraction from any type of document or content. This makes it easier than ever to pull out data from contracts, invoices, research data, marketing assets, medical charts, and more. Finally, we’re introducing Box Automate, a new workflow automation solution within Box that lets you deploy AI agents across enterprise content-centric workflows. With Box Automate, you can design your business process in a simple drag and drop builder and then drop in AI agents at any step in the process. This ensures agents execute tasks at the right steps in a workflow every time. Best of all, our AI agents and workflow tools are designed to work across any system our customers work within, whether it’s leveraging pre-built integrations, Box APIs, or the new Box MCP Server. Ultimately, all of these capabilities come together to transform how companies can work with their enterprise content. Software has historically only been good at automating work that deals with structured data, which is why ERP, CRM, and HR systems have been mainstays of enterprise software for so long. The data in these systems fits neatly into a database, and the workflows are very ripe for automation. But it turns out most of the work in the world deals with unstructured data. It’s ideating through research documents, working with a client on contracts, reviewing details for a new product launch, looking at a patient’s healthcare record to make a diagnosis, working through due diligence documents for an M&A deal, and so on. For the first time ever, we can begin to bring all new insights and automation to this work with AI agents. At Box, we’re incredibly excited to be on this journey to help customers transform how they work with their most important data.

Aaron Levie

91,863 views • 1 year ago