Seed World

Could Your Seed Catalog be Written by a Robot?

Do you have lots of useful data but lack the time to analyze it or compile results into reports?

New “robotic writers” could be your solution and help free up employee time to do more useful tasks.
Ninety percent of the world’s data has been generated in the past two years, said James Wotecki of Automated Insights.
New natural language generation software is being used by companies, such as the Associated Press, Yahoo,, AllState and other companies, to take data and turn it into stories with a narrative, honing into key insights from the numbers.
Think about your company — earnings reports, seed and product guides, customer and on-farm information, regional agriculture data. How do we use and make sense of all this data? The answer, according to Wotecki, is “robo-writing.”
Automated Insights is the first company to patent software in the automated writing space. It is part of the Vista Equity Partners portfolio and operates as a subsidiary of STATS LLC. The company was founded in 2007 in the sports sector. Today it operates in the spaces of finance, personal fitness, consumer content, business intelligence and website analytics.
The company takes data sets, hones in on key insights from the numbers and writes stories. Clients are able to choose the article tone, personality and variability they want the story to convey to readers.
“We can create narratives that are very rich, without a ton of data,” Wotecki explains. “But we always want more data; the more, the better. In the stories for the AP, for example, the data set doesn’t have to be that huge in order for the stories to be virtually written.
“Automation is coming and if your job is to crunch numbers and turn them into narratives, maybe you should look for something else because automation is coming.”
One potential application for this is analysis and stories based on the U.S. Department of Agriculture’s reports. Or a company product guide could no longer need a human editor spending hours pouring over data and coming up with a brief synopsis on each product, highlighting its features.
However, Wotecki cautions that the data must be correct. “We are only as good as the data,” he says. “It’s absolutely fundamental that you have good data because that’s what the software depends on.”
You can learn more about Automated Insights at