Loading video...
Video Failed to Load
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

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

Yes I love this!!!!

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.

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

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

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

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.

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!

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

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

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

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!

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.

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

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.

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! 🚀

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 .
