73 Strings Unveils Extraction Agent to Streamline Financial Reporting With Agentic AI

Transformative AI-powered solution revolutionizes financial data extraction and mapping, continuously learns from user corrections and eliminates repetitive manual work for private markets investment teams

PARIS & NEW YORK & LONDON--(BUSINESS WIRE)--73 Strings, the AI-powered valuation and portfolio intelligence platform for alternative asset managers, today announced the launch of Extraction Agent, a new agentic AI solution that automates financial data extraction and mapping through a multi-agent AI workflow that learns from previous user corrections to reduce repetitive manual work and accelerate recurring portfolio reporting.

For alternative asset managers overseeing portfolios of companies with varying reporting formats, financial data collection remains a significant operational burden. Investment teams must navigate inconsistent financial statements, spreadsheets and quarterly reports to identify, extract and reconcile critical performance metrics. These challenges compound across reporting cycles, as teams repeatedly address the same formatting inconsistencies and data mapping issues.

Built into 73 Extract, Extraction Agent uses a coordinated multi-agent AI workflow comprised of specialized agents, orchestrated through an intelligent agent orchestrator. Working together, the concierge agent, intake agent, extraction agent, mapping agent and validation capabilities manage the end-to-end process, from document intake and recognition through financial data extraction, mapping, validation and review.

Combining a deterministic extraction core with an agentic AI layer, Extraction Agent brings together the reliability and consistency of deterministic processing with the adaptability of agentic AI. This best-of-both-worlds approach enables complex financial documents to be transformed into structured, review-ready data without requiring rigid templates, while maintaining control, accuracy and source-level traceability.

“In private markets, the value of any valuation or performance metric depends entirely on trust in the underlying data,” said Yann Magnan, CEO and Co-Founder of 73 Strings. “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.”

Key capabilities of Extraction Agent include:

• Multi-agent Workflow: Specialized agents work together to manage document intake, recognition, processing, mapping, validation and review, transforming incoming reports into structured datasets through an end-to-end AI-powered extraction workflow.
• Adaptive learning through Soft Memory: Extraction Agent remembers user updates, reporting preferences and data mappings, applying them to future documents. Soft Memory continuously improves with use and can be shared across teams, reducing repetitive work and improving consistency.
• Flexible document processing: Users can upload individual or multiple reports or forward files by email. Extraction Agent automatically identifies the relevant portfolio company and processes any document type, including spreadsheets, PDFs, scanned documents and images, extracting data from tables, charts and commentary across formats and languages without rigid templates.
• Automated validation and human oversight: A dedicated validation agent uses built-in rules and confidence checks to flag anomalies, inconsistencies and low-confidence values. Users can correct individual values or request broader changes through natural-language instructions, with human-in-the-loop validation and sign-off required before data is saved. This AI-as-maker, human-as-checker approach shifts investment professionals from manual processing to reviewing and validating AI-extracted data.
• Complete source-level traceability: Every extracted number links directly to its precise location in the original source documentation, creating a clear audit trail that enables users to verify figures and maintain confidence in financial reporting.
• Enterprise-grade security: Extraction Agent protects sensitive client and portfolio company information through zero data retention, with no client data used for AI model training.

Designed for private equity, private credit, venture capital and other alternative investment strategies, Extraction Agent supports use cases ranging from extracting financial data like revenue, EBITDA, cash and debt figures from quarterly portfolio company reports and operational KPIs to automating borrower reports for ongoing credit monitoring and portfolio performance analysis.

To showcase Extraction Agent’s capabilities, 73 Strings will host a live product demonstration on Thursday, Dec. 3 at 10:00 AM ET giving investment professionals an opportunity to see the technology in action, explore real-world use cases and learn how agentic AI can help streamline their financial reporting processes. Interested participants can register here.

For more information about Extraction Agent or to request a personalized demo, visit https://www.73strings.com/introducing-extraction-agent/.

About 73 Strings

73 Strings is the AI-powered valuation technology company transforming how private capital firms manage data, monitor portfolio performance and deliver institutional-grade Net Asset Values. Purpose-built for alternative investments, its platform, 73 Intelligence, combines intelligent data extraction, standardization and labeling, portfolio monitoring and observability and deterministic AI-powered valuation workflows, replacing fragmented manual processes with a single, governed platform. 73 Strings is building the next-generation data infrastructure for private markets, bringing together the metrics, valuations and insights that inform how investment opportunities are assessed, performance is measured, and capital is allocated.

Trusted by many of the world’s leading alternative asset managers and supported by leading global Valuation Advisory and Audit organizations, 73 Strings supports private equity, private credit, growth equity, venture capital, and infrastructure clients managing more than $20 trillion in assets across private and public markets. Built by valuation practitioners, the platform combines deep private markets expertise with enterprise-grade governance to deliver transparent, reproducible and fully auditable valuations at scale.

In February 2025, 73 Strings closed a $55 million Series B led by Goldman Sachs, with continued support from Blackstone Innovations Investments and participation from Golub Capital, Hamilton Lane, Broadhaven Capital, and 7RIDGE.

Founded in France in 2020 and headquartered in New York, 73 Strings has offices in New York, San Francisco, London, Paris, Riyadh, Abu Dhabi, Singapore, Bengaluru and Hyderabad, supporting a global client base.

The company’s leadership team and advisors bring more than 300 years of combined experience across private markets, valuation, and financial advisory.

Learn more at www.73Strings.com.