
Faster Footnotes with AI-Powered Decision Trees
Faster Footnotes with AI-Powered Decision Trees
At Tellen, our vision is to empower auditors with GenAI to streamline their workflows. We analyze auditor workflows and build data pipelines to efficiently extract, transform, and deliver data so auditors can complete their procedures more accurately in far less time.
We are currently building a new module for FootnoteAI: an AI-powered decision tree tool to quickly draft footnote disclosures that are specific and accurate to each entity, even if such disclosures were never previously created for that organization.
How AI-Powered Decision Trees Work
By using this AI-powered decision tree workflow tool, auditors will follow a sequence of steps that require answering questions and uploading documents that are processed by AI models. This orchestrated workflow ultimately results in the AI-powered generation of a footnote disclosure where the auditor remains "in-the-loop" providing oversight and guidance throughout the process.
The Workflow Process
- Entity Profiling: Our decision trees first discern the necessary information about the entity from the user
- Characteristic Establishment: After profile characteristics (industry, reporting framework, etc.) are established, the user is prompted to input further information
- Documentation Upload: Supporting evidence and documentation are uploaded for AI model processing
- AI Generation: The AI model generates a workable draft of a footnote based on all provided inputs
- Auditor Review: Throughout the process, auditors maintain control and provide oversight
The FootnoteAI Suite Evolution
We view our decision tree tool as the logical progression of the collaborative work we have been doing with our design partners to build our FootnoteAI application:
Current Tools
- FootnoteDB: Assists in searching for comparable disclosures from publicly available 10-Ks or from your firm's proprietary collection of financial statement disclosures
- Clerical Accuracy Tool: Checks for internal consistency throughout the financial statements, including footnotes (rolling out next)
In Development
- Decision Tree Tool: The focus of this post (currently in design)
- Additional specialized tools for the complete FootnoteAI suite
Future Autonomous Capabilities
As this decision tree tool matures, we anticipate integrating autonomous AI agents into the workflow that specialize in specific repeatable tasks:
- Lease Agent: Automatically produces lease amortization tables whenever a new lease contract is uploaded
- Regulatory Monitor: Continuously checks the FASB website for regulatory updates before generating footnotes
- Document Processor: Handles various financial document types and extracts relevant data automatically
The Economic Impact
Ultimately, this AI-powered decision tree tool will transform basic background information and supporting documents into fully prepared workpapers and disclosures in minutes. We believe that the economics of firms that utilize our AI-powered tools will be fundamentally altered.
The efficiency gains from reducing footnote preparation time from hours to minutes will allow auditors to focus on higher-value analytical work while maintaining accuracy and compliance standards.
Moving Forward
We are excited to bring developments like these to our existing design partners and look forward to bringing more firms on board as they choose to AI-enable their businesses. The future of audit efficiency is here, and it's powered by intelligent decision trees that understand the nuances of financial reporting.