73 Strings launches AI tool for private markets reporting

73 Strings has launched Extraction Agent for alternative asset managers, designed to automate financial data extraction and mapping for portfolio reporting.

The tool sits within the company's 73 Extract product and targets a recurring task for private markets firms: collecting information from portfolio company reports, spreadsheets and financial statements that often arrive in different formats.

Alternative asset managers face pressure from limited partners and regulators to deliver reporting faster and with greater transparency. Many firms still rely on manual processes to pull figures such as revenue, EBITDA, cash and debt from quarterly company materials, then reconcile those numbers for internal monitoring and investor reporting.

The system uses several software agents to handle document intake, recognition, extraction, mapping, validation and review. It also records user corrections and applies those adjustments to later reporting cycles, with every extracted figure linked back to its source document.

Human approval is required before any data is saved, a process intended to preserve an audit trail while reducing time spent on repeated manual work.

Reporting burden

The launch reflects a broader push across private markets to apply artificial intelligence to middle-office tasks such as data collection, portfolio monitoring and valuation support. Managers in private equity, private credit and venture capital often receive information from portfolio companies in PDFs, scanned files, spreadsheets and other formats, making consistent reporting difficult.

These operational frictions can become more pronounced over repeated reporting periods, particularly when firms oversee large portfolios with different accounting presentations and varying levels of data quality. In credit strategies, similar issues arise when lenders monitor borrower reports on a recurring basis.

Extraction Agent can process individual files, batches of reports and emailed documents. The system identifies the relevant portfolio company and extracts information from tables, charts and commentary across formats and languages without using fixed templates.

The product also includes validation checks to flag anomalies, inconsistencies and low-confidence values. Users can amend individual figures or request broader changes through natural-language instructions before approving the final dataset.

Company backdrop

Founded in France in 2020 and now headquartered in New York, 73 Strings develops software for valuation and portfolio intelligence in private markets. The company says it works with clients across private equity, private credit, growth equity, venture capital and infrastructure.

Clients using its platform manage more than $20 trillion in assets across private and public markets. Earlier this year, the company closed a USD 55 million Series B funding round led by Goldman Sachs, with continued backing from Blackstone Innovations Investments and participation from Golub Capital, Hamilton Lane, Broadhaven Capital and 7RIDGE.

The group has offices in New York, San Francisco, London, Paris, Riyadh, Abu Dhabi, Singapore, Bengaluru and Hyderabad. Its software focuses on data extraction, standardisation, portfolio monitoring and valuation workflows for institutional investors and managers.

Yann Magnan, Chief Executive Officer and Co-Founder of 73 Strings, outlined the rationale for the new product in a statement accompanying the launch.

"In private markets, the value of any valuation or performance metric depends entirely on trust in the underlying data. With LPs and regulators demanding greater transparency, firms need both rapid reporting and absolute auditability. Extraction Agent delivers both by connecting every extracted figure directly back to its source, allowing teams to report faster while standing behind every single number with complete confidence," said Magnan.