Why a GenAI Dev SIG (Special Interest Group) ?

March 6, 2025

Exchange on development around GenAI

The considerable amount of information contained in GenAI “clouds”
makes them almost indispensable to user interface in product marketing,
finance or legal assistance.

Given the immense diversity of indexed documents (texts, images,
etc.), can they be used as quantitative instruments for processing
knowledge? GenAI engines (e.g. Gemini-Google) offer exploration and
integration processing tools, but documentation on the content of the
“clouds” and the capabilities of their engines is almost absent. In such a
case, all that remains is to discover these processing capabilities by
experimentation.

This situation justifies the exchange of experiences between users and
developers given the almost infinite number of possible experiments.
Collective enrichment is desirable.

For a given domain (science, industry or services), questions arise about
the capabilities of particular engines (ChapGPT, Claude, Gemini…):

● What development tools are offered (Python, Java, Nodejs, R…).
● Immersion of new data in a GenAI (Embedding)
● Mastering the design of dialogues (Prompt engineering)
● Constraining the response to a set of predefined data (Grounding)
● Services offered: OCR, translation, calculation, logical reasoning
● Construction of agents under semantic constraints of environment
and objective

Wrestling with a similar regulatory or operational challenge?

We help regulated firms reduce the friction between what compliance requires and what teams actually have to do — through better processes first, AI where it earns its place. A 30-minute Business & Automation Review maps where your time is going and where automation could pay back fastest.

Compliance Testing – Fairness Assessment using R

Retrieval Augmented Generation (RAG) augmented by ML can help in Proactive Risk Identification enabling predictive analysis to identify potential issues regarding unbalanced customer selection.

Company default prediction – DLMM internal rating model in R

Most firms are sitting on data that could predict which clients are at risk or which investments are underperforming. Machine learning is the type of artificial intelligence that enables computers to learn from this existing knowledge and data.

Behavioral & decision-making quantification

GenAI can adopt a persona and "make decisions" or "behave" in a way that can be quantified. This technique is used to simulate scenarios, which can then be analyzed quantitatively and used in particular to assess multi-criteria decision alternatives

Prompt for data

Extracting quantitative information using GenAI tools requires to properly structure the prompts used to question them to efficiently use their large language models (LLMs)

Machine learning augmentation: Closing the Data Gap

Machine learning is a type of artificial intelligence that enables computers to learn from existing knowledge and experiment results. These models are traditionally used for prediction and can be augmented by GenAI for training data generation and screening in particular

Retrieval augmented generation (RAG)

Retrieval Augmented Generation (RAG) is a critical technique using proprietary or domain specific documents to augment base LLMs to address specific enterprise or applications needs.