We started Pulse last year, building for niche operations teams who were dealing with critical business data trapped in millions of spreadsheets and PDFs.
PDF parsing and OCR tools have been around for decades, yet both legacy players and AI startups still struggle with real-world document processing. Existing solutions fall apart when they hit complex tables, messy formatting, or domain-specific content. We've seen teams lose 20-30% of their business-critical information due to poor extraction.
At Pulse, we're taking a new approach to document understanding by combining intelligent schema mapping with fine-tuned extraction models that maintain enterprise-grade accuracy across millions of documents. All without losing context.
Today, we’re thrilled to announce our $3.9M seed round led by Nat Friedman and Daniel Gross (NFDG). Our round also includes participation from Y Combinator, Sequoia Capital Scout, Soma Capital, Liquid 2 Ventures, Olive Tree Capital, Tiferes, and execs from NVIDIA, OpenAI and Ramp.
Pulse was founded by Sid Manchkanti (CEO) and Ritvik Pandey (CTO). Our product is powering software teams of all sizes, from early-stage startups to fast-growing unicorns and public multi-billion dollar enterprises.
Here are a few recent examples:
A Fortune 100 enterprise is leveraging our platform to transform unstructured documents (PDFs, images, and spreadsheets) into clean, structured datasets for their production RAG pipeline, significantly improving retrieval accuracy.
A YC startup has automated their investment workflows by processing complex financial CIMs (Confidential Information Memorandum), reducing due diligence time from weeks to days.
A public investment firm is using our infrastructure to extract and normalize data from thousands of real estate rent rolls, powering their new ML-driven market intelligence product.
A growth-stage startup has eliminated manual data entry in their accounting workflows using our schema-enforced extraction pipeline, saving over 2,000 hours monthly in operational overhead.
A big focus of our engineering team in 2025 is to squeeze the maximum amount of intelligence out of every document. We're expanding our extraction capabilities to handle multimodal file formats, including audio and video, in order to generate higher quality training data. Our goal is to make data ingestion as seamless as possible.
We're a small but fast-growing team of engineers in San Francisco, working to solve complex data challenges. Our vision is to fundamentally transform how organizations handle data ingestion, building infrastructure that will power the next generation of AI systems.