AI AGENT PLATFORM FOR CARRYING OUT COMPLEX FINANCIAL ANALYSES

Key points at a glance

A financial services provider uses AI agents for financial analysis to give all staff easy access to complex data – thanks to an orchestrated multi-agent platform that operates in natural language, is secure and scalable.

How a financial services provider lets its staff speak through the data

The analysis of financial data – for example, in the context of credit decisions or balance sheet audits – is an extremely demanding task that requires highly specialised expertise and specific tools to model complex valuation logic. To ensure that this expert knowledge does not become a bottleneck in the future, given rising analytical demands and a growing shortage of skilled personnel, a leading financial services provider sought ways to support analytical processes using AI, thereby effectively reducing the workload on financial analysts.

The vision: Data that speaks

However, the client’s vision went far beyond a mere automation solution: rather, the company wanted to provide its staff with intuitive access to the data available on the organisation’s benchmarking and analytics platform. Users in the specialist departments were to be able, regardless of their level of expertise, to interact with the data using natural language, ask questions of the dataset and generate customised reports.

A multi-agent approach for improved performance and flexibility

iteratec supported the client right from the start in realising this ambitious vision – whilst pursuing a novel technological approach: to ensure the system met the requirements for speed, scalability and adaptability, the team designed and developed what is known as a multi-agent architecture. This took the concept of the single AI agent a step further: instead of a single LLM-based agent that has access to the data and is capable of generating visualisations and so on, the work is divided amongst the team.

Orchestrated collaboration between specialised AI agents

The resulting multi-agent system consists of several specialised AI agents that work together like an orchestra to tackle complex tasks. Each agent performs a specific technical or functional task – ranging from interpreting and categorising chat enquiries, through carrying out specific analyses, to generating graphical representations. Thanks to the interaction between the individual agents, the system can operate much more efficiently and flexibly than comparable single-agent approaches. The result is a tool that allows users to ask questions of the dataset in natural language and receive personalised results in real time – in the form of text, tables or graphics.

Scalability and future-proofing through modular architecture

By breaking down highly complex analytical processes into individual task packages, which are executed by agents optimised for this purpose, a highly flexible and scalable architecture is created, on which a wide variety of different use cases can be implemented. In this way, it will be possible in future to implement additional output formats – for example, for generating specialised reports – or to integrate further data sources for carrying out additional analyses in other business areas, all on the same technology stack.

Data protection and quality assurance in a highly sensitive business environment

The storage and processing of financial indicators as part of financial analysis is a sensitive area, as it involves highly confidential information about companies, investors or markets and forms the basis for far-reaching decisions. To meet the specific requirements regarding the security and reliability of the systems, iteratec has developed innovative approaches to ensure the quality of results and the security of the data:

Test automation

LLM-Guard

Hybrid data processing

From idea to market-ready MVP with Project Management 2.0

iteratec supported the project from the initial concept right through to a functional MVP and is currently overseeing the implementation and further development of the system. As the approach to GenAI projects can differ significantly from that of traditional software development projects, iteratec supported the client throughout the entire development period through intensive project management and by providing a technical Product Owner role, which ensured effective and efficient solution development in this technical environment, which was new to the client. In this way, a solid and scalable technical foundation was established within a short timeframe for the development of further future-oriented AI services within the company.

Your contact

Do you have a specific request or questions about possible AI and data analytics projects for your company? Send a request and we will get back to you.

Dr. Felix Böhmer, Director Al & Data Analytics

Get in touch