
Finance
|
Modeling & Analytics
|
YC W26
|
Valuation:
Undisclosed

Last Updated:
March 24, 2026

Builds an AI agent for real estate underwriting and financial modeling that turns offering memorandums into fully auditable institutional underwriting models directly within Excel, in seconds. Targets PE, investment banking, and real estate acquisitions teams.
Excel-native AI agent processing 200+ page offering memorandums. Single-prompt model generation from PDFs and unstructured documents. Hundreds of millions in AUM already using the product. Expanding from real estate underwriting to broader private-market asset classes.
Lean 2-person team. Real estate underwriting focus as beachhead with expansion plans to broader private markets. Common vertical-first GTM strategy.
AI-powered extraction and assembly of full three-statement financial models from unstructured PDFs and deal documents in a single prompt.
Instead of an analyst spending a full day manually copying numbers from a 200-page PDF into Excel, the AI reads the entire document and builds the model for you in minutes.
It's like having a photographic-memory intern who can read a 300-page offering memo, perfectly type every number into the right Excel cell, and write all the formulas connecting them—in the time it takes you to grab coffee.
Automated anomaly detection and error flagging across complex financial models using ML-driven cross-validation and statistical outlier analysis.
The AI acts like a tireless senior analyst who checks every single formula, cross-reference, and assumption in your model for mistakes or suspicious numbers before anyone else sees it.
It's like spell-check for spreadsheets, except instead of catching typos it catches the kind of formula errors that could accidentally make a $500 million deal look like a bargain.
LLM-powered natural language interface for running complex scenario analyses, sensitivity tables, and stress tests on financial models through plain-English prompts.
Instead of manually tweaking dozens of assumptions across multiple tabs to see what happens if interest rates spike, you just type "show me what happens if rates go up 200bps and vacancy doubles" and the AI runs it instantly.
It's like having a co-pilot who not only instantly runs any "what if" you can dream up, but also whispers "hey, you should probably also check what happens if the Fed raises rates again" before you even think of it.
Ryan Samadi brings Stanford CS/AI and Citadel trading experience. Michael Wachsmann brings Cornell CS and infrastructure engineering. Years building systems around financial data and modeling workflows, with the product already in use across hundreds of millions in AUM.