PLATA
on demand, written in a Python framework called Streamlit.
Ivan says:“ We think that within the next year, every analyst will write their own small BI tools using AI agents. It will be a total disruption – a completely different experience of working with data.”
The plan is not without its challenges. Ivan is candid about the limitations of simply pointing an AI model at a database and expecting accurate answers. The quality of any AI-generated output depends entirely on how well the underlying data has been described. Metadata – the structured information that explains what each dataset contains and how it relates to others – must be thorough and accurate before AI can interpret it reliably.
Ivan explains:“ People say you can integrate an LLM with any database and it becomes a simple computer you can question about anything. But that’ s not our reality. You need to describe your data first, and that’ s where we are working now.”
Building a single window for data Alongside the move away from BI, Plata is developing what Ivan describes as an internal integrated development environment, or IDE. An IDE is a software application that provides a centralised workspace for writing and running code. In a data context, it would give every type of user – from a business analyst to a senior executive – a single interface through which to access all of the company’ s data capabilities.
bancoplata. mx 11