Launch HN：Parsewise (YC P25) – 通过 API 实现跨文档推理

Hi all, it’s Greg and Max, founders of Parsewise here<p>Parsewise transforms a bucket of unstructured data into schema compliant data retaining lineage for values resolved across documents. Imagine giving Claude a bunch of files and asking for a CSV or JSON output. If you have tried this, you know both the system limitations (number of files, type of inputs, cost, latency) but also the human-facing challenge of having no way to validate the results quickly. We solve both. We help tech teams simplify their unstructured data ETL, and loop in business experts for the definitions and for instant validation.<p>Here is a video with a few use cases: <a href="https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=dbRllnnh47w" rel="nofollow">https:&#x2F;&#x2F;www.youtube.com&#x2F;watch?v=dbRllnnh47w</a><p>Parsewise in the words of someone coming to us: ”I need to extract information from insurance policy PDFs, phone calls that have been transcribed, emails, etc. I am NOT looking for something that would just extract data point by data point, page by page into a structured well-defined schema but more something more agentic that can understand that information might be across documents and that it should reason over what to extract.”<p>We started the company based on a decade of experience (and pain) in complex data transformation and data analysis &#x2F; synthesis. Greg was building both classical ETL and implemented AI workflows at Palantir. At Bain, Max did highly complex data analysis in the financial sector, similar to many of our customers.<p>Parsewise works by taking in a bucket of data (think hundreds or thousands of pdfs, excels etc.), and outputting schema compliant data where every single value is traceable down to word level citations across multiple documents in the bucket. We provide API customers with ways to show the lineage in their own applications, or they can use our platform for internal operations. At the core of the data processing we have self-improving agent definitions. They define the acceptable sources, the logic for resolving or combining values, and the rule for highlighting uncertainty to the end user.<p>The underlying tech is model and cloud agnostic and can be deployed in private networks. We have seen the best results with Gemini models for visual reasoning, achieving SOTA (beating Claude Fable) on the strongest grounded reasoning benchmark we have found (Databricks OfficeQA) [will include link to our blog post]. Notably, we focused more on the “human harness” rather than the model harness, leaning into the actual friction we saw in uptake, which is around verifiability. That means optimizing the time and clicks required to trust the outcomes. We use vLLMs for parsing, and then we use small models for efficient large scale exhaustive search. Unlike RAG, we do not sample; instead, we exhaustively find all relevant values for a given query. We use larger models for decision making around resolutions and flagging inconsistencies to users.<p>This exhaustiveness and explicit value sourcing is unique to our platform, and it goes beyond the first step of data parsing that many existing providers cover.<p>We would love to welcome builders and tinkerers to try Parsewise on your complex document challenges. We have a ton of ideas on how we can expand the product and make it better, but would appreciate feedback and ideas from the community!