# Enterprise Deep Research: The Next Killer App for Enterprise AI — Ofer Mendelevitch, Vectara AI Engineer · 2025-11-24 Ofer Mendelevitch from Vectara introduces Enterprise Deep Research as the next killer app for enterprise AI, applying autonomous, multi-step reasoning to internal knowledge bases. Vectara's trustworthy agent OS enables this with multimodal ingest, hybrid retrieval, and hallucination mitigation (HHEM model at 5.5M downloads). Deep Research queries private data to generate comprehensive reports with citations, replacing manual workflows. Key use cases include responding to RFPs by scanning enterprise datasets, generating on-demand employee onboarding guides from Jira/Notion/SharePoint, and creating investment memos in financial services. The system uses multi-agent parallel execution and corpus understanding for accurate planning, addressing 73% of LLM users' top challenge: factual accuracy. ## Questions this episode answers ### What is Enterprise Deep Research and how does it differ from regular Deep Research? Enterprise Deep Research is like web-based Deep Research—where an AI agent autonomously conducts multi-step investigation and synthesis—but applied to a company’s private data. It uses Vectara’s agentic RAG with corpus understanding, hybrid retrieval, and hallucination mitigation to generate comprehensive reports with citations. Regular Deep Research (e.g., Gemini, ChatGPT) searches the public web, while Enterprise Deep Research queries internal knowledge bases like Google Drive, SharePoint, or Jira, ensuring high accuracy and factual reliability. [3:14](https://aie.addtry.com/f7139095-1dc0-46d6-adf2-4e79b0e58b05?t=194000) ### What is the top challenge for companies implementing large language models, according to Ofer Mendelevitch? Ofer Mendelevitch states that about 73% of LLM customers implementing use cases say factual accuracy is their top challenge right now. This drives Vectara’s focus on hallucination mitigation, including their hallucination detection model (HHEM) which has passed 5.5 million downloads, enabling high-quality applications like Enterprise Deep Research. [1:44](https://aie.addtry.com/f7139095-1dc0-46d6-adf2-4e79b0e58b05?t=104000) ### What use cases does Ofer Mendelevitch suggest for Enterprise Deep Research? Ofer Mendelevitch highlights several use cases: responding to RFPs by automatically searching enterprise data to answer hundreds of questions; creating on-demand employee onboarding guides from up-to-date documentation in tools like Jira, Notion, or Google Drive; and generating investment memos in financial services. Additional applications exist in healthcare and insurance, leveraging the same autonomous, multi-step reasoning over company data. [3:50](https://aie.addtry.com/f7139095-1dc0-46d6-adf2-4e79b0e58b05?t=230000) ## Key moments - **[0:00] Intro** - **[0:24] Agent OS** - [1:22] Vectara's HHEM hallucination detection model surpasses 5 million downloads. - **[1:44] Hallucination Hurdle** - [1:44] 73% of LLM customers cite factual accuracy as their top challenge in implementing generative AI. - **[2:08] Deep Research** - **[3:14] Enterprise DR** - **[3:43] Use Cases** - [3:50] Enterprise Deep Research automates RFP responses, employee onboarding, and investment memo generation using private data. - **[5:03] Outro** ## Speakers - **Ofer Mendelevitch** (guest) ## Topics Multi-Agent Orchestration ## Mentioned Anthropic (company), Vectara (company), ChatGPT (product), Gemini (product), HHEM (product), Perplexity (product) ## Transcript ### Intro **Ofer Mendelevitch** [0:04] Hi, I'm Ofer from Vectara. At Vectara, we developed a trustworthy agent operating system, and there's a lot of really cool use cases with this, like document generation, conversational AI or chatbots (either internal or external), and Enterprise Deep Research, which I'm going to talk about today. But before I jump into Enterprise Deep Research, let me tell you a little bit more about our operating system for agents. First of all, it's a SaaS platform, but also runs on your own VPC or on-premise in your own data center. ### Agent OS **Ofer Mendelevitch** [0:38] And here's some of the main features that we really are proud of: we have very advanced multimodal ingest to support images, tables, in a way that makes them findable and retrieved, to be able to make sense of them in a RAG or agentic RAG workflow. Very strong focus on, again, retrieval accuracy with hybrid retrieval, lots of features around metadata, re-ranking, etc. And then we're kind of known for a lot of work around hallucination mitigation, both hallucination detection and correction. In fact, our hallucination detection model, also called HHEM, has just passed 5 million downloads about a couple months ago. I think it's at 5.5right now, or something like that. And generally, our operating system platform is what you would need for enterprise-grade deployments: security, role-based access controls, bring-your-own model, custom prompts, observability, monitoring—everything you would need. So why does this matter? ### Hallucination Hurdle **Ofer Mendelevitch** [1:44] Well, in any generative AI application, and Enterprise Deep Research is no different. Hallucinations are still a problem, and you want to base your applications on really robust information. In fact, this is statistics that shows that about 73% of LLM customers implementing use cases say that factual accuracy is their top challengeright now. ### Deep Research **Ofer Mendelevitch** [2:08] So that's why we spend so much time in hallucination mitigation, which enables Enterprise Deep Research at really high quality. Okay, so with that in mind, let me jump into what is Deep Research. Deep Research itself is something many of you probably know already. It's when an AI agent conducts in-depth, multi-step investigation, usually by autonomously browsing or searching the web in some way, getting results, synthesizing all these results together to generate a comprehensive report for you, with citations and all the information you need to answer a particular question. Many have implemented this sort of web-based deep research. Gemini or Google has that, ChatGPT, Anthropic, Perplexity, etc. Here's an example of what it looks like. If you haven't used it, I highly encourage you to use it. It's a very powerful tool, and I use this all the time. This is the screenshot of how you choose it in Gemini, for example, and here's how you choose it in ChatGPT. And this is usually something that takes about 20, 30 minutes to complete, because it does a lot of work underneath the covers. ### Enterprise DR **Ofer Mendelevitch** [3:14] Now, Enterprise Deep Research: think about it as exactly the same idea, only now it goes to your private data. So again, the same process: multi-agent with reflection, with synthesis of the final results, parallel execution of agents underneath. And it queries your enterprise data, of course, using, in this case, Vectara agentic RAG capabilities, with all the bells and whistles of high accuracy and hallucination mitigation. And then we have corpus understanding, which allows you to plan properly based on your data. ### Use Cases **Ofer Mendelevitch** [3:50] There are many really amazing use cases for this, and I'm going to just mention a few here that I like. One is responding to an RFP. I've had this in my career multiple times: when you have to respond to an RFP, and getting the answers to 150 questions is really difficult. So being able to use Enterprise Deep Research to go through all of your enterprise datasets, picking up theright documents and answering those questions is a really cool use case. Employee onboarding is this idea of: if you come to a new team, or you join a new company, and the company wants to onboard you quickly, it's usually very difficult. Nobody knows what's going on, there's no onboarding guide, the last one was generated 3 years ago and it's not up to date, etc. So again, being able to generate an on-demand onboarding guide using all the documentation we have on Jira, or on Notion, or Google Drive, or SharePoint—very, very powerful. And then, in different industries, there's also different use cases. For example, in financial services, you might have the generation of an investment memo as a really cool use case. And you can imagine the same thing in healthcare, in insurance, and other industries as well. So those are some of the use cases. There's a lot more. I'm Ofer, you can connect with me here in the links I'm showing below. And if you are interested to learn more about Vectara and Enterprise Deep Research, please contact us, and we'll be happy to do a demo for you. ### Outro **Ofer Mendelevitch** [5:17] Thanks very much. --- This library is powered by PodHood (https://podhood.com), the podcast website platform.