Almost every enterprise has joined the AI wave, and many are now rethinking how their AI architecture is built. The first move is rarely clear when a wealth of technologies and vendors promise to fix the business. Without visibility into who is using what and how many tokens each uses, policy and cost decisions are guesses.
In this interview on TFiR, Raviv Levi, Chief Product & Technology Officer at CData, walks through where to start with AI agents and an AI gateway, and what visibility unlocks next.
Guest: Raviv Levi, Chief Product & Technology Officer at CData
Show: The Agentic Enterprise
LinkedIn: Raviv Levi
Watch the discussion on YouTube
Here is what every platform engineer and AI team lead needs to know about starting with AI agents.
Technical Deep Dive
Q: How do you get visibility into AI agents before scaling them?
Raviv Levi, Chief Product & Technology Officer at CData, recommends starting with visibility: understand who is using what and how many tokens are being used by whom. Once that is in place, setting policies is easy, token savings become visible, and some traffic can be diverted to a locally hosted model. Levi adds that the same starting point lets teams build a context layer within the gateway, such as Connect AI Gateway, for a variety of next steps.
“The easy first step I would recommend is first get visibility, understand what’s going on, who’s using what, how many tokens are being used by whom.” Raviv Levi, Chief Product & Technology Officer, CData
Q: Who uses AI agents first inside an enterprise, and who owns the gateway?
Levi’s answer focuses on who is using agents rather than naming one owning team. Most companies start with coding agents, where the most value is seen today. Increasingly, agents are being used for enterprise applications across finance, marketing, sales and product management.
“So it’s not just about developers using agents to code, but everyone using agents in order to superpower their day-to-day job, whether you’re in finance, marketing, sales, product management.” Raviv Levi, Chief Product & Technology Officer, CData
Q: How do you move AI agents into business-critical workflows while keeping accuracy, security and cost under control?
Levi frames it as confidence: becoming AI native in a responsible way. That covers business risk, meaning governance and security, and cost, meaning tokenomics and token optimization. The sequence is to see all AI-related traffic, enforce governance and policies, and then, with the right AI gateway, get accurate answers and efficient access to data.
“So you have to be able to see all the AI-related traffic that goes through, and then you have to be able to enforce certain governance and policies.” Raviv Levi, Chief Product & Technology Officer, CData
Q: What capabilities does an AI gateway like Connect AI Gateway include?
Levi says CData’s work has been data connectivity and data replication for over 10 years, with caching as an important component. More recently it has extended to connectors for AI agents and tools, an MCP server and an MCP gateway. The Connect AI Gateway launch adds LLM gateways, MCP gateways, agentic gateways for A2A agent-to-agent connectivity and a kill switch, on top of the context and data connectivity technologies.
“Today we couldn’t be happier to launch our Connect AI gateway with LLM gateways, MCP gateways, agentic gateways for A2A agent-to-agent connectivity, kill switch, and everything that comes with that.”Raviv Levi, Chief Product & Technology Officer, CData
Resources & Documentation
- Connect AI Gateway, the AI gateway from CData covering LLM, MCP and agent-to-agent connectivity
***
👇 Click to Read Full Raw Transcript
Swapnil Bhartiya: For those organizations that are just getting started with agents. First of all, there are a lot of organizations, not a lot of, almost everybody’s on the AI bandwagon these days, but because of everybody gets excited, they get on board. And now actually a lot of organizations are rethinking, re-architecting their whole AI architecture. So this is also right time for them as well, as well as a lot of organizations who are starting their AI journey. What’s the practical first workflow where Connect AI Gateway will start showing value quickly versus over a period of time? Where should they get started? Where should— what are the touchpoints they should look at when they are looking at Connect AI Gateway?
Raviv Levi: Thank you. This is a great question. I understand that AI transformation could be overwhelming. There is a wealth of technologies and companies out there, you know, promising to fix the world and specifically your business. And it’s hard to understand where to get started. Working with quite a few customers and, you know, I’ve been privileged, we’ve been privileged to partner with them on their journey. The easy first step I would recommend is first get visibility, understand what’s going on, who’s using what, how many tokens are being used by whom. And get reliability. What’s most important for me right now? Do I want to set policies? That’s easy because you have visibility and you can see exactly what’s going on. You want to save some money on tokens? That’s easy. You can see what you can benefit by which measures that you may consider to deploy. You want to host a model locally and divert some of the traffic into this local model, you can do that as well. But it all starts from having visibility into what’s going on and starting to build that context layer within your gateway so that you’re able to leverage that For a variety of potential next steps after that.
Swapnil Bhartiya: When we look at organizations, who typically owns this gateway inside an enterprise? IT platform team, business units who are actually deploying agent? Where does the buck stop or it’s like everybody?
Raviv Levi: I think that most companies are starting with coding agents. That’s where we see the most value. As an industry, we’re seeing the same here at CData, but increasingly we’re starting to see the next waves after that where agents are being used for more enterprise applications. So it’s not just about developers using agents to code, but everyone using agents in order to superpower their day-to-day job, whether you’re in finance, marketing, sales, product management. It becomes the new standard of how you go about your work, how you access and transact with data, and how you’re able to automate many of the things that you do.
Swapnil Bhartiya: What does this architecture make possible for enterprises that they could not have done easily yesterday? And how does it also help them give the confidence to move AI agents into more business-critical workflows while also keeping accuracy, security, and cost under control?
Raviv Levi: I think you hit all the right points. And it’s really around confidence, around being able to transform your organization to become AI native in a responsible way, both from business risk standpoint, that’s governance and security, and also from a cost standpoint, and that’s everything that has to do with tokenomics or token optimization and all of that. The only way for any organization to be able to do that successfully is by making sure first that they have an understanding of what’s going on. So you have to be able to see all the AI-related traffic that goes through, and all of that. The only way for any organization to be able to do that successfully is by making sure first that they have an understanding of what’s going on. So you have to be able to see all the AI-related traffic that goes through, and then you have to be able to enforce certain governance and policies. And then finally, if you have the right AI gateway, then you’re also able to get the benefits of an accurate answer and an efficient access to data. Specifically for us here at CData, that has been our journey and mission for over 10 years, starting with the data connectivity, data replication, We hardly mentioned caching, but that’s a very important component as part of that. And we have evolved over the last few years to increasingly offer capabilities to our customers that would help them in their AI transformation, from connectors to AI agents and tools, go through MCP server, MCP gateway. And today we couldn’t be happier to launch our Connect AI gateway with LLM gateways, MCP gateways, agentic gateways for A2A agent-to-agent connectivity, kill switch, and everything that comes with that on top of all of the context and data connectivity technologies that we’ve been working on for a pretty significant time by now.





