The New Private Catalog: Now You Can “Bring Your Own Documents” to Regulatory AI

If you’ve been following along with HData’s journey, you know that in May of this year, we announced the launch of Regulatory AI. This industry-first generative AI technology works within HData’s platform to help our users uncover answers that are buried in the tens of thousands of pages of FERC filings and other regulatory documents. Regulatory AI has been nothing short of game changing for analysts, and we’ve loved hearing about how it has transformed the way they work. 

Today, we’re incredibly excited to announce the next step in our AI journey: the Private Catalog. Today, you can “bring your own data”!

Until today, when using Regulatory AI’s interface, the Librarian, you could only search for answers within our library of public regulatory documents, including FERC Forms 1, 3Q, and 714. Now, you can create your own collection of documents to add to this query-able library, and they’re kept securely within the virtual walls of your own HData Private Catalog. You can add PDF, PPT, TXT, HTML and Doc files, and query them with the same question-and-answer interface we’ve all become comfortable with. These documents are secured within your organization’s HData instance, visible only to your teammates, protected by a Soc 2 Type II security rating. 

The Librarian is “grounded” and constrained to look for answers only within these documents, which means it won’t wander out into the greater internet to return irrelevant answers (or worse yet, make things up, or “hallucinate”). It is conversant, making the interface easy for anyone to use - simply type in your question and get a common-language answer in seconds. You can dictate the answer format to make the data easier to consume, like in tables, and bulleted or numbered lists. Ask follow up questions and dig deeper into your Librarian’s answers; the more you use it, the more relevant the answers you receive. And now with the addition of the Private Catalog, you can “bring your own data” to the conversation, expanding the body of data available for AI-backed analysis. 

So, why are we so excited about this? Everyone loves a sports analogy, so here’s one to illustrate just how game-changing we believe Regulatory AI (now featuring the Private Catalog) to be. 

Regulatory analysts have a tremendously hard job. They are responsible for uncovering mission-critical intelligence that’s hidden within troves of industry data. They’re standing on their own goal line, looking down the entire football field, with so much copying, pasting, checking, and rechecking to do before they have what they need to get started. They not only have to source the data, but then have to synthesize it into something useful. 

Standardizing the FERC forms for digital reporting moved the ball up the field a bit. At least now it’s consistent and readable for anyone who wants to use it. Companies (like HData and our Compliance solution) built tools that made it easier to file with greater accuracy. The ball is on the 50-yard line now. 

Now it’s easy to locate the data that analysts need to explore. Business Intelligence tools like HData’s Insights help pinpoint relevant information, research competitive trends, and visualize the data in ways that make it easier to understand. You can establish KPIs and metrics to track progress, and benchmark against the rest of the industry in seconds. We’re on the 40-yard line now.

Here comes Regulatory AI, moving up the field even more. While previously you had to know exactly where to look to find the data you needed, now you just need to ask questions and let the Librarian do the work for you. Overwhelming, labor-intensive searching for the equivalent of a needle in the data haystack is now replaced with a query prompt that returns accurate answers in literal seconds. You’re empowered to actually analyze data, not just frustratingly search for it. 

At HData, we believe the Private  Catalog is the next iteration in our goal answering previously unanswerable questions. Now, you can perform complex analysis with your own data, combined with public data, in a secure, private, and accurate way. (We aspire) to help you finally capitalize on the intelligence hidden in tens of thousands of pages of documents.

We know an Analyst’s job is hard. You’re tasked with answering questions about growth, profitability, viability and competition. Just identifying the intel needed to answer these questions has been largely impossible in the past due to the sheer volume of data needed. But now, when you come to work each day, you’re starting on the 30 yard line. Your job is still hard, and you still have a lot of work to do to get to the mission-critical answers. But it’s a significant head start, each and every day, thanks to a virtual AI assistant that knows the ins and outs of every document and data point in your library, in an unbiased and accurate way. HData’s platform sources and synthesizes the data, and serves it up to you in a format that’s just waiting to be capitalized upon. 

Regulatory AI, and now the Private Catalog are just the next steps in a long journey to making regulatory data a transformational asset for organizations around the world. We’re working hard to compile, scrub, format, and present all the regulated energy data that exists so you can spend your time actually working with the data, not on data research and hygiene. Today, we think we’ve gotten you all the way to the proverbial 30 yard line. We can’t wait to see how this head start transforms the results and impact of your day to day work. 

We just launched a monthly newsletter. If you’d like to follow along with our journey, be sure to subscribe. And of course, we’d love to know what you think!

File, explore, analyze, and capitalize. Unlock the power of regulatory data with HData.