One control point for enterprise AI. Governed down to the record, cheaper on every request.
Chapel Hill, NC
Joined August 2007
- Tweets7.8K
- Following471
- Followers2K
- Likes1.3K
Pinned Tweet
Introducing CData Connect AI Gateway.
One gateway between your AI and everything it touches. @ravivlevi and Amit Sharma show what we're announcing today.
Every question your teams and agents ask now runs through a layer that knows your systems, your permissions, and how your business works. The answers are accurate, the actions are reliable, and the token cost drops to a fraction of what it was.
Any model. Any platform. One context layer that goes with you.
Watch Raviv and Amit walk through it 👇
You’ve spent years teaching people how your company works. Your AI needs that knowledge too.
Introducing Connect AI Gateway.
It routes, governs, and learns from AI requests, building a system of record for how your company thinks.
Early access is live: cdata.com/ai
In the CData Arc Q4 2026 release, the built-in Model Context Protocol (MCP) server can take action. Ask it to run a connector, requeue a failed message, or clean up old files. Every action requires explicit confirmation and is recorded in the audit log.
Plus one-click AI diagnosis for failed transactions.
Details: bit.ly/4jQ0ybm
.@Adobe’s AI agents each get exactly the data their use case requires. Toolkits handle the scoping.
Cloud Gateway bridges on-premises systems without firewall changes. All of it runs through CData Connect AI: bit.ly/4kce74Z
CData Software retweeted
I built the world's first MCP server in Doom, and I've had so much fun showing it off at the CData booth at AgentCon + MCPCon in San Jose this week!
Customers don’t follow scripts. Great support moves with the conversation.
Art Courtney of @Edsal_Mfg explains why flowing with the context of a call makes Ava, their AI agent, work. He also shares how to build it.
Ava is built on CData Connect AI. Hear Art’s approach and get the details: bit.ly/4sd3NMi
CData Software retweeted
I recorded my CData Foundations session on a film set in Atlanta, which is a lot of lighting for a guy explaining MCP gateways. I had so much fun.
Today at Foundations 2026, we’re spending a day on one subject: the AI gateway.
The case for it, how it works, how it learns your business, what a CIO’s rollout really looks like, and how to get started. If you’re figuring out how agents get to your company’s data without losing control of it, this is worth an hour or two of your time.
It’s virtual, and it’s your last call to grab a spot: bit.ly/4k9w3gw
We run our own marketing, finance, and business development work on the AI gateway we're building.
Tomorrow at Foundations 2026, the people doing that work will show what it looks like day to day.
Join us: bit.ly/4iXvuWb
We were recognized as a Challenger in the 2026 Gartner® Magic Quadrant™ for Data Integration Tools.
We believe who pulls ahead with AI is decided at the data layer: how well you connect, the context agents get, and the control you keep.
Details: bit.ly/4zrkI07
CData Software retweeted
"We had bots running everywhere, and every new use case meant building and maintaining another one. It wasn't sustainable."
Sound familiar? That's Padmakar Pasala, who leads the integration platform team at @Adobe, describing where they were earlier this year.
So instead of building yet another bot, they solved data access once - one governed data layer on @CDataSoftware Connect AI.
Every system reaches their agents through the same MCP interface, and everyone signs in through Adobe's own identity provider (no extra set of credentials floating around).
3 connected systems turned into 10+ in a couple of months, with 12 internal teams in the pilot.
My favorite part: each use case only gets the tools it actually needs.
Turns out when agents have less to sift through, they get more accurate and burn fewer tokens. Who knew :)
Huge thanks to Padmakar and the Adobe team for building this with us, and to Amit Naik @suprgeek and our team for being right there with them!!
Details: cdata.com/case-study/adobe-i…
CData Software retweeted
Around 21 calls a day is more than any manager can coach by hand. Our business development team now has agents grade every Gong call, so feedback covers the whole week instead of whatever someone had time to hear.
More at CData Foundations 2026, Nov 5: bit.ly/4iXvuWb
A correct, governed task cost $0.26 through Connect AI Gateway and $5.67 through an open-source MCP gateway with the same business context. All 27 models, failed runs priced in.
Full benchmark: bit.ly/4sAivx4
We’re proud to announce we’ve been recognized as a Challenger in the Gartner® Magic Quadrant™ for Data Integration Tools. We have been recognized based on our Ability to Execute and Completeness of Vision.
Stay tuned for additional details, including complimentary access to the report.
Same 27 models, same business context, 2 MCP gateways. Correct answers took 93% fewer tokens through Connect AI Gateway, which serves context on demand and runs the computation across systems.
Video from CData Labs.
Full benchmark: bit.ly/4sAivx4
Everyone gets read access that mirrors their rights in the source system. Write access is granted with intention.
That’s how @Anaqua CIO Erik Bailey brings AI to business systems. He talks rollout with CData CMO @willcmdavis at Foundations 2026 on November 5: bit.ly/4e31eXb
.@Adobe manages every MCP connection in Connect AI.
10+ enterprise systems, cloud and on-premises, sit behind a single governed layer. Any AI agent gets secure, scoped access to live data. 20 teams already run on it.
Details: bit.ly/4kce74Z
Watch below, then see how Connect AI works: cdata.com/ai/
Our marketing team ran a Halloween video contest: the horrors of governing AI agent data access, made entirely with AI.
The entries got weird fast. @Mariesahr cast Amit, @ravivlevi, @AdamDeMi & me as Ghostbusters hunting rogue AI agents.
No agents were harmed. Happy Halloween!
Enjoy this preview of @Mariesahr and @RavivLevi taking us into the context engine, where agents get the meaning they need.
What separates correct agent answers from confidently wrong ones? A deep understanding of your data’s meaning. At Foundations on November 5, Dr. Nick Golovin, Mike Albritton, and Amit Naik show how the AI Gateway learns it.
Registration is open: bit.ly/4k9w3gw
You can give your Copilot Studio agents governed access to live data.
Henderson Brothers runs 3 Copilot Studio agents across @Salesforce, @GoogleCloud BigQuery, and @AppliedSystems Applied Epic. Each one is scoped, audited, and governed, and each took roughly half a day to stand up.
Join the session at @PowerPlatConf and hear from the people behind it. You’ll see a live demo and hear a fireside chat on where governed agents go next.
Today 👉 Thursday, Oct. 29, 10:45am PT in the Premier Ballroom 311
Speakers:
David Yuhas, Henderson Brothers @ExpectAnExpert
Sabin Nair, @Microsoft
Rahul Pahuja, @CDataSoftware
Session details: bit.ly/4yFVIBb
#PPCC26 #PowerPlatform
Edsal Manufacturing set a goal: 24/7 customer support, with the same quality experience at every hour.
That goal started Ava, @Edsal_Mfg’s AI customer support agent, built on Connect AI.
Art Courtney, Director of Information Systems, tells the story.
Full customer story: bit.ly/4sd3NMi