Nik Bozhinov
Scaling Verifiable AI
How to answer questions across large document collections without overloading context.
Blog
Research results, engineering notes and product news from the team building Parsewise.
Shan Singh
What's New in Navi
Build apps from project data, inspect extraction decisions, dictate prompts, and use screenshots as context.
Maximilian Hofer
The Risk of Sampling
How measuring the narrative record reduces ambiguity in complex transactions
Gergely Csegzi
A search for meaning
Or how different search methods span syntax and semantics
Nik Bozhinov
SOTA results on Databricks OfficeQA
Our data engine outperforms frontier models in grounded reasoning
Shan Singh
Navi: A New Interface to Parsewise
Plain language control of the Parsewise Data Engine to create and govern AI agents.
Mark Menezes
Empowering Business Experts: UX Design for Agent-Driven Workflows
A Powerful Engine Deserves an Equally Refined Set of Controls
Gergely Csegzi
Building Document Processing In-House
What It Takes to Build and Operate
Maximilian Hofer
The Core Loop
Why LLMs Haven't Revolutionized Decision-Making (Yet)
Greg Csegzi
Software 3.0
What is needed for the LLM operating system