CData (@cdatasoftware) header
CData (@cdatasoftware) profile picture

One control point for enterprise AI. Governed down to the record, cheaper on every request.

Chapel Hill, NC
Joined August 2007
Photo by CData (@cdatasoftware)Photo by CData (@cdatasoftware)Photo by CData (@cdatasoftware)Photo by CData (@cdatasoftware)Photo by CData (@cdatasoftware)Photo by CData (@cdatasoftware)Photo by CData (@cdatasoftware)Photo by CData (@cdatasoftware)Photo by CData (@cdatasoftware)
AI gets expensive and risky in the same two ways. It burns a heavy model when a light one would do. And it grabs data it was never meant to touch. Most people never catch it. They pay the bill and hope the access rules held up. I've run businesses across a stack of tools for years. My data sits in Salesforce, in NetSuite, in a dozen other places. And every time I asked an AI something real, it either guessed at what my terms meant or pulled way more than it needed. CData Software showed me their Connect AI Gateway. It deals with both problems before the model ever runs. Watch one prompt go through it. "What revenue is at risk for mid-market in Q3." The gateway reads the intent first. It's just a lookup, so it sends it to a lighter model instead of the pricey one. Then it works out what my words actually mean. Mid-market. This quarter. Revenue. At risk. Each one maps back to a real system or a real definition. Then it pulls only the records I'm allowed to see. The permissions and the masking happen in the gateway, not the model. And it hands the model one clean subset. Not a data dump. That last part got me. The raw pull was 200,000 tokens. What reached the model was 9,500. Same answer, a fraction of the cost. Every step logged too. Prompt, permission, record, response. Here's the part I keep thinking about. When you confirm what "at risk" means, that sticks. It becomes a saved fact. The thing knows a little more than it did a minute ago. Everyone chases the flashy AI stuff. But the boring layer that controls cost and access is what makes the rest safe to actually use. Check out CData here: cdata.com/ai/ P.S. Building a 10-business portfolio. 6 businesses in, all remote. #CDatapartner
6
1
10
404
The fastest open models, now connected to live enterprise data. We're excited to partner with @cdatasoftware . PrimaLabs brings fast open-model inference, ranked at the top of Artificial Analysis. CData Connect AI Gateway brings governed access to hundreds of enterprise sources. Together, teams can run agents on open models with the data access and controls they already need. Looking forward to building this with the @cdatasoftware team cdata.com/blog/cdata-primala…
2
1
7
348
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!
7
2
28
924
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.
1
1
4
490
"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…
1
2
1
3
108
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
1
1
25
One more day at @AgenticAIFdn AGNTCon+MCPCon with @cdatasoftware where Doomguy is "processing" live data via Connect AI Gateway. Want the shirt? Come by @suprgeek's session in Room 210A @ 2:55PM!
2
3
82
Agents, applications, and people all need access to company systems.     Foundations 2026 covers keeping control of access, actions, and cost, plus research with benchmark harnesses and raw results anyone can run.    Nov. 5, free and virtual: bit.ly/4ihg1Qt
1
1
23
Agents, applications, and people all need access to company systems.     Foundations 2026 covers keeping control of access, actions, and cost, plus research with benchmark harnesses and raw results anyone can run.    Nov. 5, free and virtual: bit.ly/4ihg1Qt
1
1
20
【kintone × Claude | 10月22日(木)開催】 Claude に話しかけるだけで #kintone の顧客・商談データを集計・更新できる――そんな環境を一緒に作ってみませんか?🙋 無料ツールだけ・60分で試してみるハンズオンセミナーです! 必要なのはClaude の無料アカウント、kintone 開発者ライセンス、CData Connect AI のトライアル(14日間)だけ。 📅10/22(木)14:00〜 💻Zoom・参加無料 視聴のみでの参加も歓迎です👌 jp.cdata.com/resources/claud…
2
5
1
11
831
Every CData Labs benchmark ships with a public harness so you can rerun it on your own data. Hear what the lab tests next at Foundations 2026 on Nov. 5: bit.ly/4jmxJmE
1
1
21
AI token costs climbing? In a CData benchmark, Connect AI reduced tool calls from 22 → 1 and query cost from ~$0.60 → under $0.03. See how our Token Savings Calculator estimates your potential savings. 🎥 youtu.be/5GOlBs_bIrQ #AgenticAI #AIOptimization #CData
1
2
30
AI gateways have made real progress on routing, access + spend. Agents also need to know what a field means, whose permissions apply, and what an action changes. That lives in the data layer. CData Connect AI Gateway starts there: bit.ly/4ynhZob sprou.tt/1tdO7oqaVcz
1
2
42
I keep watching developers wire AI agents into production data. Building the agent is easy. Getting people to trust it is harder.
2
1
2
552
CData Labs found that none of 22 AI models stayed within what they were authorized to change on raw access to enterprise data. One run alone queued 628 rows it was never allowed to touch.   Full benchmark: bit.ly/4yfGcNc
1
1
48
Our (@cdatasoftware) model benchmark is reproducible on your own machine. Copy three Google Sheets, clone the harness, and do a dry run before spending anything on models. Then get Connect AI to see how much of accuracy, safety, and cost comes from the model, and how much from the gateway beneath it. Guide: bit.ly/4dc2Rl2
1
1
1
106
With enterprise AI, the data layer is now non-negotiable.     @CDataSoftware connects to enterprise systems and understands every object, relationship, validation rule, and custom field inside them.    Inside CData Connect AI Gateway: bit.ly/3Vm6eQk
1
1
61
Every agent request can go to the model that fits the task. CData Connect AI Gateway routes it there, and token cost drops. Sign up for early access: bit.ly/4AG5GEX    Find the @CDataSoftware team at booth 132 at The @AIConference.     #taic2026 #theaiconference
1
4
81
Push accuracy and safety into the data layer and the model becomes a cost decision. We benchmarked 22 AI models, economy to frontier, on live enterprise data through @CDataSoftware Connect AI: the identical correct answer cost 178x more from one to the next. cdata.com/lp/ai-cost-whitepa…
1
1
34
A quick behind-the-scenes (literally) shot of some upcoming content. Looking forward to sharing what we've got brewing at @cdatasoftware soon!
2
3
67