Implementing Proof of Concept of Private Generative AI for Audit Automation
AI & MLData ScienceFintech
3 Weeks (60 Hours)
South Carolina, US
AWS Bedrock|Azure AI Studio|Private GPT|Python
AI/ML
Dedicated team behind the project
The Client
Investinet, a trusted partner specializing in debt collection services for law firms across the United States, approached us with a challenge tied to their core project, WayThru. As their business grew, so did their need for regular and detailed security audits. These audits required sensitive information, handled primarily by senior management, resulting in a time-consuming process that strained their resources.
The Challenge
The primary goal of this Proof of Concept (PoC) was to determine the most suitable technological stack and framework for automating the completion of security audit questionnaires. To address this, we conducted extensive research to evaluate the current technological landscape and identify potential solutions. After selecting the most promising options, we implemented basic functionality to test the feasibility of the project and ensure it could meet Investinet’s requirements.
The solution needed to securely handle sensitive data, save time and resources, and be scalable to accommodate future growth while adhering to strict U.S. security regulations.
What Was Done
To ensure we delivered the best solution, we evaluated three potential setups before recommending Azure OpenAI Studio. Each option was analyzed based on its ability to meet the project’s key requirements of security, scalability, and efficiency:
/ 01: Ubuntu Server with PrivateGPT
This setup allowed maximum control and customization, particularly in selecting models and embeddings for data processing. However, it required significant maintenance and was complex to manage, making it more suitable for larger projects with dedicated engineering teams. It was not the right fit for InvestiNet’s immediate needs due to high maintenance costs.
/ 02: AWS Bedrock
AWS Bedrock provided a stable and highly reliable environment with minimal bugs and an easy setup process. It allowed us to experiment with vector storage for optimized data retrieval. However, the platform offered a limited selection of models compared to other solutions, which could be a drawback for projects requiring a wide range of options.
/ 03: Azure OpenAI Studio
Azure OpenAI Studio stood out for its maturity and extensive model availability, including high-performance GPT models from OpenAI and other industry leaders like Microsoft and Meta. The platform’s integration capabilities and user-friendly interface made it a strong candidate, especially for U.S.-based projects where data security and compliance are critical.
Implemented Features:
Integrated Azure OpenAI Studio’s Large Language Models (LLMs) to automate responses for security audit questionnaires, ensuring high accuracy and reducing manual effort.
Developed custom API solutions to seamlessly connect the audit automation tool with Investinet’s existing systems, ensuring smooth data flow and minimal disruption to current workflows.
Implemented strong data encryption protocols to protect sensitive audit information, in line with U.S. regulatory standards, including HIPAA and data privacy laws.
Fine-tuned GPT models within Azure to align with Investinet’s specific audit requirements, optimizing for both speed and accuracy.
We implemented a local version of the LLM to give InvestiNet full control over their data processing environments. This deployment was configured across multiple infrastructures, including on-premises servers and cloud platforms.
Results
The PoC showed that by automating the completion of security audit questionnaires, Investinet could reduce the time senior management spends on audits by up to 50%, potentially saving around $18,000 annually
The PoC indicated that switching to a serverless architecture could reduce operational costs by 30-40%, primarily by eliminating the need for extensive infrastructure maintenance and dedicated engineering teams
The PoC verified that Azure’s platform is fully capable of meeting U.S. data security and compliance standards, including HIPAA, ensuring secure handling of sensitive audit data
The PoC confirmed that Azure OpenAI Studio’s serverless design can support Investinet’s future growth without significant changes to infrastructure, ensuring scalability for evolving business needs
Tech Stack









Daniel
Head of Engineering at Ralabs
Simplify Your Audits with AI
Let our experts help you save time, reduce costs, and ensure compliance with a customized AI solution
Relevant Cases
back to portfolio Duration: August 2023 – ongoing Customer location: The US Dedicated team behind the project OlesiaSenior Back-end Engineer AndrewFull-stack Engineer OleksandrFull-stack Engineer Olha
back to portfolio Website: waythru.com Duration: 3 Weeks (60 Hours) Customer location: South Carolina, US Dedicated team behind the project DanielSolution Architect ElidorSenior ML Engineer
back to portfolio Duration: 2019 Customer location: Palo Alto, US Dedicated team behind the project AndrewSenior Engineer DmytroSenior Data Engineer AndrewFront-end Engineer Previous Next PARTNERSHIP
back to portfolio Website: waythru.com Duration: 2021 – ongoing Customer location: South Carolina, US Dedicated team behind the project Alina Project Coordinator AndriiTech Lead Yaroslav