We're open-sourcing PulseBench-Tab, a frontier benchmark for table extraction.
Table parsing remains one of the hardest and most poorly measured problems in document intelligence. TEDS operates on DOM trees and conflates HTML formatting conventions with structural errors.
@Pulse__AI is now #1 on ExtractBench.
ExtractBench is LlamaIndex's open benchmark for schema-guided extraction from enterprise documents: 370 real documents, 4,869 pages, and 67 schemas spanning SEC filings, customs entries, court exhibits, energy filings, and scanned forms
Our engineering team has been launching a lot of features. Here's what we launched over the past few weeks at @Pulse__AI
1/ MCP server
2/ Generate-split
3/ Selection model
4/ CLI
5/ One-click SSO
6/ Tutorial mode
All of it is live today, and there's more on the way.
@Pulse__AI is now on Claude.
Point Claude at any document and it comes back as clean, structured data without ever leaving the conversation.
Once connected, Claude can call on Pulse directly to pull a document into markdown, tables, and JSON from a URL instead of copying and
Charts are among the most valuable objects in an enterprise document, and until now they have also been among the least usable.
A decade of company performance can live inside a single line chart, and decades of subsurface measurement inside a scanned well log. Conventional OCR
