HomeCompaniesReducto

Reducto

Unlocking data behind complex documents

Reducto offers robust and reliable document ingestion for any workflow. Our API allows you to convert complex, unstructured documents into structured outputs that are perfect for RAG, process automation, and more.

Latest News

Jobs at Reducto

San Francisco, CA, US
$150K - $240K
0.10% - 1.00%
3+ years
San Francisco, CA, US
$100K - $160K
0.10% - 0.30%
Any (new grads ok)
San Francisco, CA, US
$150K - $250K
0.10% - 1.00%
3+ years
San Francisco, CA, US
$110K - $170K
3+ years
San Francisco, CA, US
$90K - $140K
1+ years
Reducto
Founded:2023
Team Size:4
Location:
Group Partner:Diana Hu

Active Founders

Adit Abraham, Founder

Co-founder/CEO at Reducto. Before Reducto I studied CS at MIT, made Ads/Search things as a PM for Google, did ML research at MIT's Media Lab, and spent an unreasonable amount of time playing Pokemon Showdown.
Adit Abraham
Adit Abraham
Reducto

Raunak Chowdhuri, Founder

Co-founder/CTO at Reducto. Before Reducto I studied CS at MIT, founded/scaled a comp. chem consulting company to 200k ARR, published computer vision papers with 100+ citations before finishing high school, and spent a little too much time shit posting on Twitter.
Raunak Chowdhuri
Raunak Chowdhuri
Reducto

Company Launches

Reducto is a team from MIT building vision models to turn complex documents into LLM-ready inputs. Every part of our core API was made to offer the most accurate extraction possible, and we now power document ingestion for leading AI teams ranging from startups to Fortune 10 enterprises.

We’re excited to release a new Structured Extraction API, which leverages LLMs along with our vision models to extract the data that you need with exceptional accuracy and flexibility.

📃 The Problem

Nearly 80% of enterprise data is in unstructured formats like PDFs and spreadsheets
PDFs are the status quo for enterprise knowledge in nearly every industry. They’re stored in a structure that’s simply impractical for use in digital workflows, which leads to dozens of wasted hours every week.

Custom extraction models require hundreds of hours to build and maintain

Companies often use traditional solutions to build a custom extraction pipeline for every document layout they’re working with. That requires dozens of hours for labeling and training the model, and constant maintenance when models break from changing layouts.

LLMs offer better flexibility at the cost of reliability

Off the shelf LLMs can offer exceptional reasoning but they struggle with hallucinations and extraction inaccuracies, making them unreliable for production use cases.

✅ Our Solution

We’ve built vision models to read documents the way a human would, and a language model that we trained for schema-based extraction. Our new model can handle significantly larger documents, and is trained to cite the source for each piece of information, allowing you to audit and verify outputs easily.

This means you can:

  • Extract important fields with simple, natural language instructions
  • Verify any information using our source citations
  • Build powerful automations by integrating Reducto’s API with your custom workflow

🚀 Automate your unstructured data processing

Our API is live in production with leading teams across insurance, healthcare, and finance, and we would love to work with you to improve your unstructured data ingestion.

This new API leverages all of the work that we’ve put into improving our document understanding models to make structured extraction work across all layouts with best in class accuracy.

You can sign up to get started right away, or reach out to us at founders@reducto.ai for a demo!

Other Company Launches

🔮 Reducto - Unlocking data behind complex documents

Our API allows you to convert complex, unstructured documents into structured outputs that are perfect for RAG, process automation, and more.
Read Launch ›