Pulse

@Pulse__AI

Production-grade unstructured document extraction

San Francisco, CA

runpulse.com

Replies Reposts Media

Pulse
@Pulse__AI
Jul 1
Every document extraction system can read the text on a form, yet almost none of them can read the pen, so the checkmarks, circles, underlines, and strikethroughs people use to record decisions get treated as noise and quietly ignored. Today Pulse is launching Selection Mark, a
2
Pulse
@Pulse__AI
Apr 23
Table extraction is one of the hardest unsolved problems in enterprise document intelligence, because tables encode relationships where position is meaning and a number landing in the wrong cell doesn't just look wrong, it breaks downstream analytics, compliance workflows, and
runpulse.com
Table Extraction Benchmarks: What They Measure, What They Miss, and What the Field Needs | Pulse AI
A close look at the four most-cited table extraction benchmarks, what they measure, where they fall short, and what enterprise document intelligence actually requires. | Pulse AI
Pulse
@Pulse__AI
Dec 19, 2025
Enjoyed this!
Ritvik Pandey
@ritvikpandey21
Dec 19, 2025
We spent the past couple weeks delivering holiday gifts to 100 startups around SF to close out the year. Got to do a few office visits along the way, some of our favorite offices were @usepylon , @MomenticAI , and @juicebox_work . Huge thanks to the teams for the office tours.
1
Pulse
@Pulse__AI
Dec 18, 2025
For a long time we put all our energy into infrastructure. Models, pipelines, evaluation. Design took a back seat. As more teams started depending on @Pulse__AI in production, it made sense to bring the brand up to the same standard. The new site goes deeper into how Pulse
1
Pulse
@Pulse__AI
Sep 25, 2025
Pulse is now officially part of @cloudera's Enterprise AI ecosystem. Excited to partner with Cloudera and continue delivering the most accurate document extraction models at enterprise scale.
9