Video summary
Enterprise AI initiatives frequently stall before delivering a return on investment because traditional databases were not designed to handle the specific demands of artificial intelligence, such as context awareness, reasoning, and real-time data access. Organizations often face a difficult choice between migrating to entirely new database systems or building custom stacks, both of which are time-consuming processes that can take months or even years. This gap between the initial excitement of AI demos and the reality of production deployment creates significant friction, as companies struggle to integrate AI into legacy financial or operational systems without rebuilding their entire infrastructure from scratch to accommodate regulatory compliance and data privacy requirements.
To address these challenges, RavenDB has introduced Quill, a context layer that sits atop existing SQL databases to unlock them for production AI agents without requiring a rip-and-replace migration. This solution fundamentally changes the approach by allowing organizations to point their systems directly into their current database schemas, where Quill automatically understands the structure and retrieves relevant details on its own. By managing the logistics of data invocation and transformation internally, Quill enables companies to move from concept to production in weeks rather than years, effectively bypassing the need for massive resource allocation to developers who would otherwise be tied up in complex integration projects for extended periods.
A critical component of this innovation is the inversion of control regarding security and governance, which ensures that AI agents cannot act as untrusted entities with unrestricted access to sensitive data. Instead of allowing an AI model to execute arbitrary queries like "select star from credit cards," Quill defines a set of well-known, pre-approved operations where the platform controls the scope of what data can be accessed and how it is used. This approach treats the AI not as a super-intelligence but as a secure secretary or natural language interface that operates within strict guardrails, ensuring that privacy regulations like ISO standards are met while still providing users with actionable insights through safe, governed interactions.
The practical impact of this technology is already visible in high-stakes industries such as healthcare, where it has been used to build active lifestyle applications for hundreds of thousands of users without compromising safety or regulatory compliance. For product leaders and CFOs weighing the costs of internal development against adopting Quill, the resource case is clear: building an AI solution in-house often requires losing top talent for a year and deploying another six months later, whereas Quill offers immediate playability with free access to start exploring new projects right away. By providing a secure, scalable foundation that integrates seamlessly with existing data ecosystems, Quill allows enterprises to finally bridge the gap between AI experimentation and reliable, production-ready deployment.
Read the full video transcript
When it comes to databases, most
enterprises build them around
transactions and queries. Then came AI
and AI started demanding something
completely different. Context,
reasoning, realtime data access,
guardrails, those things were not part
of how you would build traditional
database. So now organizations teams are
stuck. either they migrate to new
database for AI which will take months
or they build a custom stack suitable
for their database and AI needs which
once again will take months. So neither
options are ideal. Now Revit DB says
that there is a faster and better way.
They just announced Quill, a context
layer that sits on top of your existing
SQL database and unlocks it for
production AI agents. No RIP and replace
is needed. You will have full control.
You can build guards, governance and all
that. And today we have with us Orurin
Ini, CEO and founder of Raven DB to walk
us through why this really matters.
First of all, Orurin, great to have you
on the show. Thank you for having me.
It's great being here.
>> It's uh my pleasure. And as I was trying
to lay the foundation of this decision,
how how correct or wrong I was when I
was trying to explain when you look at
the databases, how they were built and
when you just plug in AI into it, what
kind of friction, what kind of
challenges organizations run into. So
let's talk about the problem area first.
I think that the primary problem is the
difference between
uh the demo layer, the the demo level
and uh actual production system. So
let's talk about the financial example.
I go to my bank account. I download my
credit card statement and I can go troll
a chart and tell it how much did I spend
on entertainment, how much did I spend
on utilities and it will give me
everything including charts and
information. Really nice. Now I go to my
bank website and it's pretty much
unchanged from the '9s. So the key
problem that we have to deal with is why
is this is the case. So in any
[clears throat] modern company today in
any company that is you know bigger than
mom and pop you have the board saying do
AI this is what we must do and then you
know the CEO the CT or CO whatever goes
to the IT department sit with the R&D
team says okay do and they take the
three best people that they have and
they do an amazing demo in a few weeks
and that's really nice and then you
start looking at what does it take to
actually take this demo and move it to
production. Oh, you're not a man and pop
shop. You have to deal with regulation,
sock to ISO, etc. stuff like that. Well,
what are the privacy that you have to
deal with? How how how are you going to
put guards in place? So, if someone ask
nicely, they will be able to see your
credit card uh details because you know
the AI would do that for you if you're
not careful. So the whole idea here is
that there is a huge gap in practice in
implementing AI typically in the order
of I have to look into my system map
everything almost rebuild it from
scratch because all of the system were
not built design or even conceived with
the idea of AI. So I have to rethink the
whole thing.
>> Thank you so much. Now the thing is as
you mentioned earlier that every company
were like hey I want AI and everybody is
trying to get around AI bandwagon but
the fact is that you have seen that many
enterprise AI initiatives they kind of
install before they can actually deliver
any ROI. The exciting part is part is
sorry let me just do it. I said fart in
the part uh uh u like as you rightly
said every enterprise wants to embrace
AI and they are trying to but in most
cases their AI initiatives stall before
they can deliver any ROI. So talk a bit
about what does quill do differently to
help them so that their AI initiatives
their AI projects are successful.
>> So the chief problem is that the data
that you have is not in one system. It
is not uh envisioned to be used by AI.
So in most cases if you want to do AI
properly you have to first figure out
what all the data is and speaking of
financial systems you have checking you
have savings you have loans you have
mortgages you have credit cards each one
of them is a separate system now you
have to somehow bring them together
figure out what is the scope of access
that you have to do with that and
transform that into a form that the AI
agent can make sense of that is the huge
project that is a key to an open heart
surgery in your envirance component
and what quill allows us to do is just
point our system into your database. It
would understand the schema and the
structure that you have and it will pull
the relevant details that you need on
its own. So the whole idea is that we're
able to take care of all of the
logistics of building the AI and
invoking that and managing that for you
without you having to deal with this. So
instead of you know going into this huge
project you know I'm going to spend a
year or two just spinning that the whole
idea is that you roll off the production
line within weeks.
>> Can you also talk about when we do talk
about giving AI access to data databases
we have to also ensure guard rails what
they can do with the data or not. So can
you also talk about how does quill
balance giving AI agents access to data
but also ensuring uh it is the
governance is there that what they can
or cannot do with the data. So let me
try talk a little bit for one second
about MCP and model protocol. This is a
way for the AI to control to make
invocation do calls etc. And I think
that if you're building a tool like uh
cloud code or something like that it's
amazing. If you're building an AI agent
that is meant to be used by the public,
it is a horrible idea because the whole
idea is that the entity in control is
the AI and the AI is not a trusted
agent. The way that Qu looks at that, we
invert the whole process. The entity in
control of what's going on is Quill and
Quill is very focused on insurance
security. So when the the when the AI
needs data and when you ask a question
about that it is not oh I'm going to
invoke MCP and run some query and get
the data for that because that's a
security night instead define well a
well-known queries and operations that
you can execute and each one of those
carry the scope that is involved with
that. So it's not do a select star from
credit card where ID equal what and the
entity in control of what the ID here is
the LM. It's give me my credit card
statements and that's the effect that
you have and because the AI is not in
control you're in a much safer location.
you know what's going to happen and that
is a huge difference that inversion of
control that okay uh the point of the AI
here is not to be the you know the super
intelligence it is to be there to e to
be the secretary to be the the the the e
the natural
language interface into my system
because for most business most
enterprises I don't need a super
intelligence I need I don't need I need
just someone tell me what form I need to
do and what I'm supposed to put in this
location. That's it. And that would be a
huge thing to have.
>> Can you talk about what kinds of
organizations or use cases is qu best
suited for right now or is it something
that should become normal irrespective
of what industry they are in.
>> So I think that uh we are we are
applicable in many different industries.
We have a really good success recently
in a healthcare organization and what
they did they built
a go active uh sort of app and that
helps you go with you know uh be more
active track your steps encourage you on
that give you the ability to ask
question uh I'm so I'm you know I'm male
40s uh so and so diet what should I do
for exercise and it is able to give you
some really concrete
results.
>> And if you think about that in a
healthcare organization, the complexity
that you deal with is again safety,
regulation, all of those sort of things
and the ability to not have to deal with
all of that because this is already
handled by the platform is a a a huge
shift in the ability to deliver the the
entire project. I think was under 3
months including the specification
everything and this is now in
production. serving something of 600,000
people
>> for those you know product leaders or
CFOs who are watching this uh what is
the cost resource case for quills versus
doing it inhouse by themselves
>> doing it in yourself is take your three
to five top developers and lose them for
a year and then you have to deal with
the actual deployment which is another 6
months to another year doing that with
quill means plug it into your system and
click next a few times and the entire
thing is obviously we're AI oriented and
we're doing the center the AI so the
entire thing is next next and you have
something that you can immediately play
with and start exploring
uh I'm we are confident enough that what
we have uh is that we are giving away
the first three months you know go and
do whatever you want you get free access
to everything and by the end of 3 months
the expectation that you would be on
your second or third iteration or
project or new item that you can do in
that time frame.
>> Orin thank you so much for joining us
and walking us through quill and how
it's changing the way enterprises bring
AI agents to their existing data and
because as AI is moving into production
this is a serious challenge this is a
serious problem and this is this needs
to be solved. So thank you so much for
joining us and explain and of course uh
those who are watching please go and
check out uh revendb.net
and uh quill for yourself how it can
help you and once again thank you so
much uh for uh chatting with me and I
look forward to chat with you again.
Thank you.
>> Thank you for having