For the last 30 years, business users have been given reports and dashboards to answer the data questions they have. However, as businesses evolve, these users rely on scarce and overworked data professionals to create new visualisations to answer new questions. Business users and data teams are trapped in this unfulfilling and never-ending cycle that generates countless dashboards but still leaves many questions unanswered.

With the excitement around GenAI, the BI industry started a new wave of incorporating Data conversational assistants into BI tools to try and solve this problem. Unfortunately, while these offerings are promising in concept and make for impressive product demos, they tend to fail in the real world. When faced with the messy data, ambiguous language, and nuanced complexities of actual data analysis, these "bolt-on" data experiences struggle to deliver useful and accurate answers.

The reality is that it's not enough to just point an LLM at a database schema and do text-to-SQL, because the schema itself is missing a lot of knowledge, like definitions of business processes and metrics, or how to handle messy data. The other approach is to capture this understanding in formal semantic models, but they require significant up-front investment, can't capture all the nuances, and are impractical to keep up-to-date as data and business processes evolve.

The "real" semantic model lives in people's heads, and it comes pouring out whenever they interact with DataGOL systems to run queries, create dashboards, and perform analyses. DataGOL BI is a new BI product that captures this understanding from interactions across DataGOL to augment the context already available in the unified Data Platform, and leverages the resulting knowledge to deliver useful answers in the real world.

‍

 Fig illustrates a multi-agent system that uses semantic understanding to interface between business intelligence (BI) tools like dashboards and conversational agents

‍

At the core of BI is a multiAgent system that utilises an ensemble of AI agents to reason about business questions and generate useful answers in return. Each agent is responsible for a narrow but important task, such as planning, SQL generation, python generation, explanation, visualization and result validation. Together they provide reasoning capabilities far beyond any individual, monolith model. The multAgent system is designed to continuously learn and improve its performance based on human feedback.

‍

BI  is built from the ground up to deeply understand the data semantics and enable users/anyone to analyze the data for themselves w/o technical knowhow. BI is built on a Multi agent system that draws insights about your data from its full lifecycle across the DataGOL platform. It powers two complementary product experiences

1. Dashboards: an AI-powered, low-code dash boarding solution that includes all the conventional BI capabilities you'd expect out-of-the-box, for answering a fixed set of business questions; and
2. Data Conversation Agent (Annie): a conversational interface that can learn the underlying data and semantics continuously based on human feedback, and can answer a much broader set of business questions based on its reasoning capabilities, while still providing trusted answers for query patterns specified by the data teams.

Additionally BI integration with DataGOL unified data platform ensures unified governance, lineage tracking, secure collaboration and lightning speed performance at any data scale.(Critical because most of the Self serve analytics falls behind when the data set is greater than 100 GB). It also supports structured and unstructured data to be managed at individual workspace.

Collaboration is built right into the DataGOL platform so that you can easily share your analysis with anyone in your or outside organization. Because DataGol BI does not have seat-based restrictions, you can add anyone from your organization without having to worry about procuring new licenses.

BI Dashboards

Despite their aforementioned shortcomings, dashboards are still the most effective means of operationalising pre-canned analytics for regular consumption. BI Dashboards make this process as simple as possible, with a low-code authoring experience that makes it easy to configure the data and charts that you want.

They come with standard BI capabilities you'd expect, including sleek visualisations, cross-filtering, and periodic PDF snapshots via downloads. But notably, they also don't come with things you don't want – no cumbersome SQL queries, no data extracts, and no new BI services for you to manage. Furthermore, exploring insights unavailable in the dashboard is a click away into a complementary “Annie” space.

‍

The figure demonstrates how effortlessly BI analysts can create dashboards and generate insights by selecting metrics and dimensions

‍

The figure demonstrates how effortlessly Business users can generate insights by providing different business metrics over a period.

Data Conversation Agent (Annie)

To answer the large and constantly changing set of questions that are unanswered by a dashboard, we expose the capabilities of BI's reasoning engine through a conversational interface, called Annie. No longer limited to a fixed set of charts, Annie can learn the underlying data, and flexibly answer user questions with queries and visualisations. It will ask for clarification when needed and propose different paths when appropriate.

The figure demonstrates how effortlessly a business user can generate insights using data conversation chat in natural language, without technical complexity.

But more importantly, Annie is not just an inscrutable black box. The type of questions business users ask can be high-stakes, and they should not blindly trust a blackbox BI multiagent system to provide the answer. As a result, the entire Annie workflow is designed to make the multi agent better over time through human feedback: it provides a suite of tools for analysts to verify assumptions and fill in the gaps as needed. Instructions, validating answers, confidence voting, and quality monitoring help data teams additionally tune, curate, and benchmark Annie's performance, ensuring that what they deliver to the business users will be as trustworthy as possible.

Ready to accelerate your business growth, drive collaboration and uplevel every decision in your organization through next generation AgentOS? Learn more by exploring the types of Agents you can accomplish through DataGOL, and sign up for DataGOL Platform Trial the Box to see it working. If you are looking for an enterprise ready AI platform and would like to learn more about DataGOL, signup for a personalised demo today!

‍