CCBJ: What sets Epona apart from its competitors in the document management space?
Marcel Lang: First and foremost, your documents, your emails, all your content, will not exist in an Epona environment. It will always exist in your Microsoft 365 (M365) SharePoint tenant space, under your control. This means you will always have 100 percent control of your content, as it will remain in your environment. That means no vendor lock. This is an enormous difference from all our competitors, and it’s the primary reason that 20 percent of the Fortune 100 are already Epona clients. It is also a primary differentiator when it comes to compliance and security, and it make us as different as night and day compared to other content management service providers.
Being in the Microsoft cloud with Epona means you will get compliance, security and records, all as part of the Microsoft compliance center. Contrast that with our competitors, where you will be using their security models, which are partially reliant in some form on Microsoft, but as an externality. The simple answer is that you’re going to be better off putting all your content in a Microsoft environment. And that is why corporate entities prefer Epona. It’s a one-stop, single-solution platform. Also, when we talk about Teams integration with the Epona solution versus all other competitors, again all your content will exist strictly in the Microsoft platform. Additionally, updates, upgrades and all integrations on the Epona platform are in the Microsoft paradigm, which means you will be using the Microsoft update paradigm versus the alternative paradigms of the other third parties. This is an enormous differentiator.
Lastly, the Epona solution is also significantly more cost-effective than the other solutions. In the Epona paradigm, there is an initial upfront cost to get set up in the Microsoft tenant, and licensing costs going forward from there. In the other solution sets, you will be paying for storage and other things that add to your costs that are not part of the Epona solution – because, once again, you are storing your content in the Microsoft tenant, which you already pay for. These are some of the major differences between Epona’s solution and all the others.
What do critics say about Epona?
The legacy document management system (DMS) solutions claim that Epona and SharePoint Online lack scalability. While SharePoint did lack this aspect some years ago, I would like to update this claim with some real numbers that will counterstrike this argument: 2 million site collections. That means, for a law firm, a typical design choice would be that each matter is a site collection. Also, you get 25 terabytes per matter, up to 30 million items in a matter (files and folders), up to 500,000 licensed users, storage from the client’s M365 tenant with additional storage available from $0.20 per gigabyte/monthly, if you want to archive into “cold” storage while still maintaining all security, compliance, policies and metadata properties in a SharePoint Archive ($0.05 per GB/monthly). I believe these numbers speak for themselves.
What is next for Epona?
The next phase for Epona is focused on artificial intelligence (AI). The rollout of Microsoft SharePoint Premium is giving Epona the edge over our competitors. Some AI features include autofilling of metadata properties by prompts. Sensitive information prebuilt models are another feature: Among the most important things in a DMS are the permissions. You can set up the permissions based on a matter or client, and of course also based on folders and items. But what about sensitive documents where users just save them into the DMS? For this you can use an AI model to detect certain information and analyze if it’s sensitive enough to classify the item as “sensitive.” As a firm, you can decide yourself what is “sensitive.” Some out-of-the-box examples are of course bank account numbers, credit card info, etc.
Another powerful feature of the DMS is autoprofiling. It’s very useful to have the right information in the metadata profile without having to ask users for it. Out of the box, you can create your own models and decide what to extract.
Our prebuilt models use optical character recognition combined with deep learning models to identify and extract predefined text and data fields common to specific document types. Just to mention a few examples:
- Contracts. The contracts prebuilt model analyzes and extracts key information from contract documents. This model analyzes contracts in various formats and extracts key contract information, such as client name and address, contract duration and renewal date.
- Invoices. The invoices prebuilt model analyzes and extracts key information from sales invoices. The application programming interface (API) analyzes invoices in various formats and extracts key invoice information such as customer name, billing address, due date and amount due.
- Receipts. The receipts prebuilt model analyzes and extracts key information from sales receipts. The API analyzes printed and handwritten receipts and extracts key receipt information such as merchant name, merchant phone number, transaction date, tax and transaction total.
- Sensitive information. The sensitive information prebuilt model analyzes, detects and extracts key information from documents. The API analyzes documents in various formats and detects and extracts key sensitive information, such as personal and financial identification numbers, physical addresses, email addresses and phone numbers.
The unstructured document processing model (formerly known as document understanding model) uses AI to process documents. These documents must have text that can be identified based on phrases or patterns. The identified text designates both the type of file it is (its classification) and what you’d like to extract (its extractors).
Add classifiers and extractors to your unstructured document processing models to do the following actions:
- Classifiers are used to identify and classify documents that are uploaded to the document library. For example, a classifier can be “trained” to identify all contract renewal documents that are uploaded to the library. The contract renewal content type is defined by you when you create your classifier.
- Extractors pull information from these documents. For example, for each contract renewal document identified in your document library, columns will display the service start date and client for each document.
Then we also feature Copilot agents. With Copilot and your DMS inside the M365 cloud, you can imagine that the data used will be everything inside your tenant, including emails, calendars, chats and of course documents. This is not always what you want, as sometimes you want to ask questions about curated data such as a KnowHow repository or a matter. Microsoft released Copilot agents where you (or a user) can select the files or matter and create a Copilot agent. This will result in Copilot only using that data to answer your questions or do tasks.
This is only the beginning of how Epona and Microsoft will elevate your DMS solution.