I’ve been writing about the semantic layer for some time now, and regularly at that! I’ve said before that AI + SL is a match made in data, and I really believe that semantic layer adoption is necessary for any organisation that wants to use AI with their data - whether this is to make AI experiences for their customers or to democratise data access internally.
This is the basis on which Michael and I founded Delphi Labs. We could see many startups being founded to offer this democratisation by using LLMs to write SQL queries, but we believed that this method was very limited. After experimenting with a few we realised that this method really suffers from hallucination as soon as a data model is more than a handful of tables. Delphi was the first company founded to focus on using third party semantic layers, like Cube, as the governed interface for LLMs to use data.
Through experimentation with all of the main semantic layer offerings, Michael and I found Cube. We found the Cube Semantic Layer to be the very best to use with LLMs and for our AI application in Delphi. We also met some great Cube folks and formed a strong partnership with them, leading to our announcement today.
Michael and I are joining Cube full time. I will be joining as VP of AI and Michael will be working alongside me to help bring AI offerings into Cube. We will be leveraging our knowledge of both AI and data engineering to enhance Cube’s product even further.
We see huge potential in joining Cube and real affinity with our mission. If you ask any senior data stakeholder, CXO/VP/HoX, whether they want to simply ask a question and get an answer back in seconds or minutes rather than hours, days or weeks… they say yes please! Ask the same stakeholders what a semantic layer is and why they should invest in one, and they require a lot of education and persuasion of the benefits. When it’s simply the infrastructure needed for their AI data experience to work, to be safe and to be reliable - then it’s like explaining why a train needs rails.
This move will help a much larger audience access what we’ve built and learnt, more easily. They can get the benefits of the best semantic layer out there and AI in one place. Get in touch to learn more about LLM and AI built on top of Cube’s semantic layer.
Michael and I are both experts in deploying and using semantic layers in practice, having both used them since leading data teams in our practitioner careers. We are excited to help contribute to Cube’s semantic layer progression that isn’t related to AI too! Given what I’ve written about before in my blog, it’s clear to all that I’m a semantic layer fan!
There will be more specifics to come about integrations, what we’re building at Cube, timelines, etc. as we move forward.
I must admit that it has been hard to give up on something of our own, and I’ll share something that conveys those feelings alongside this post. That doesn’t take anything away about how much this makes sense for us, our investors and our mission.
At Cube we get beefed up in every conceivable away:
GTM: teams of Marketing, PMM, Alliances, Sales and Solutions. I have been very envious of what they have in this regard, and am very glad to be working with them now! This is some real muscle for a SaaS business to have. Add to this the reduction in customer friction in being able to buy one service with both AI features and SL - it’s already a much bigger engine and then with this nitro to boot. Cube already has a great customer base who can soon benefit from the new features we will release.
Engineering team: that has built a technically superior open-source semantic layer, best-in-class OLAP cache, best-in-class APIs with a sensible and pragmatic Cloud offering. As great a partner as Cube has been, it will be easier to build features needed for AI in the semantic layer from within. Moving from having one engineer, even of Michael’s ability, to having a team and being able to expand as we want to, again is a big advantage.
Infosec: Cube has all the acronyms… SOC2, HIPAA - you name it, they have it. As a young business Delphi wrestled with what to invest here, but we had begun to compete for deals where this was an issue and we didn’t have it, nor could buy it immediately - catch 22. It will be nice for this to not even be an issue going forward. It’s also easier to be the data processor than point to a sub-data processor during infosec reviews, providing you have the acronyms. It’s also the case that many infosec teams won’t sign off on working with a smaller company like Delphi - this is yet another advantage we gain upon joining. I’ve been really impressed by Cube’s commitment to infosec, even down to architectural minutiae that set us up to pass any infosec review.
As I mentioned last week, I’m in New York City this week. It was great to see many of you at Data Universe. I’m here till Monday so let me know if you’d like to meet up!
Some of you were also subscribed to the Delphi substack to hear about what we were building there, our post there from earlier this week, will be the final one. If you want to continue to hear about what we’re building, sign up to the Cube blog where I will be writing regularly.
Congrats on joining the Cube team! I'm sure it's bittersweet as a founder, but having a "soft landing" like that is a great outcome. Excited to see what you all will do there!