Check out the on-demand sessions from the Low-Code/No-Code Summit to learn how to successfully innovate and achieve efficiency by upskilling and scaling citizen developers. Watch now.
A startup emerging out of stealth today wants to help companies understand massive stores of text data using AI. The company is called Primer, and it uses machine learning techniques to help parse and collate a large number of documents across several languages in order to facilitate further investigation.
Here’s how it works: Users feed Primer’s software a stream of documents, and it automatically summarizes what it determines to be the most important information out of that haystack of data. Users are then able to filter by topic, event, and other categories to drill down into the information Primer collected so they can go beyond the automatically generated headlines.
The idea is that Primer will augment work done by the human analysts who would ordinarily be tasked with the job of wading through many sources and collating them into a report. The software is useful for intelligence agencies (among Primer’s customers) as well as large companies trying to understand how events logged in text impact their business.
One of the major features of Primer’s software is that the system is capable of processing many more documents than a human could, which means it should provide a more complete picture. As it stands, companies, intelligence agencies, and other organizations are pulling in far more data than the humans working for them can effectively process.
Intelligent Security Summit
Learn the critical role of AI & ML in cybersecurity and industry specific case studies on December 8. Register for your free pass today.
Primer isn’t the first company to offer a natural language understanding tool, but the company’s strength comes from its ability to collate a massive number of documents with seemingly minimal human intervention and to deliver a single, easily navigable report that includes human-readable summaries of content. It’s this combination of scale and human readability that could give the company an edge over larger tech powerhouses like Google or Palantir.
In addition, the company’s product can run inside private data centers, something that’s critical for dealing with classified information or working with customers who don’t want to lock themselves into a particular cloud provider.
In addition to the product news, Primer revealed that it has raised $14.7 million in two rounds of funding. Data Collective (DCVC) led the company’s series A, and Primer has also received funding from In-Q-Tel, Lux Capital, Amplify Partners, and others.
Primer has a contract with In-Q-Tel, an organization that helps connect the U.S. intelligence community with new technology through investment and contracting. The startup’s product is being used by several agencies within the American government, although Primer doesn’t know specifically which ones.
Intelligence agencies aren’t the only ones interested in Primer’s technology. Walmart is an early customer, and Primer sees its platform being useful for anyone who wants to understand things like subtle changes in financial filings or shifts in regulator statements around key policies.
The company is also working to expand its tools to support more complex reports, like automatically generated maps that call out key events. For example, the company was able to collate news reports about terrorism over the past year from sources in both Russian and English and to highlight key media events by country.
VentureBeat's mission is to be a digital town square for technical decision-makers to gain knowledge about transformative enterprise technology and transact. Discover our Briefings.