Building Compliance AI with the Azure AI APIs and Azure AI Studio

English Intermediate Other

In this talk we will present how we use Azure AI services to build our foundational Compliance AI that serves as the basis for Copilot and Chatbot functionality in our products for financial services. The core of our product are digital rules that help our clients to stay compliant in cross-border situations. We built a first pilot project to answer compliance questions based on document content like internal policies, applying retrieval-augmented generation (RAG) approaches to achieve high accuracy for different document types and content structures. We will present our findings on how the current AI offer on Azure can support building quick prototypes, but also allow for iterative development to reach a production ready solution. We will guide you through the first steps within the Azure AI studio, but also show you our best practices to use the Azure AI APIs directly from our service infrastructure. We will also explain in detail the advantages and disadvantages of each approach and will share our advice to start your own RAG-based copilots. Last but not least we will connect the dots to complementary Azure services like Azure Functions to implement data pipelines that feed the data to your AI products.

Azure User Group Portugal

View community info

Speakers

Peter Bouda

Head of Apiax AI Lab

Peter has more than 18 years of experience in software development and Natural Language Processing. He holds a Master of Arts in General Linguistics from the University of Munich. Peter started his career building products with speech recognition and machine translation technology and works now with LLMs and semantic technologies as Head of the Apiax AI Lab.

Duarte Balata

Data Scientist at Apiax

With a diverse academic foundation highlighted by two master's degrees in Biology and Data Science, Duarte Balata has dedicated his career to bridging the gap between scientific research and technological innovation. His journey began in bioinformatics, where for over two years, he engaged in scientific research and contributed to the community through published papers. This experience laid the groundwork for his transition into the dynamic field of data science, leading him to Apiax, a pioneer in the RegTech space. There, as part of the innovative team for more than two years, he has honed his focus on Natural Language Processing (NLP), delving into the realms of Generative AI and Chatbot technologies.

Code of Conduct

We seek to provide a respectful, friendly, professional experience for everyone, regardless of gender, sexual orientation, physical appearance, disability, age, race or religion. We do not tolerate any behavior that is harassing or degrading to any individual, in any form. The Code of Conduct will be enforced.

Who does this Code of Conduct apply to?

All live stream organizers using the Global Azure brand and Global Azure speakers are responsible for knowing and abiding by these standards. Each speaker who wishes to submit through our Call for Presentations needs to read and accept the Code of Conduct. We encourage every organizer and attendee to assist in creating a welcoming and safe environment. Live stream organizers are required to inform and enforce the Code of Conduct if they accept community content to their stream.

Where can I get help?

If you are being harassed, notice that someone else is being harassed, or have any other concerns, report it. Please report any concerns, suspicious or disruptive activity or behavior directly to any of the live stream organizers, or directly to the Global Azure admins at team@globalazure.net. All reports to the Global admin team will remain confidential.

Code of Conduct for local live streams

We expect local organizers to set up and enforce a Code of Conduct for all Global Azure live stream.

A good template can be found at https://confcodeofconduct.com/, including internationalized versions at https://github.com/confcodeofconduct/confcodeofconduct.com. An excellent version of a Code of Conduct, not a template, is built by the DDD Europe conference at https://dddeurope.com/2020/coc/.