Conversational Dashboard
Multichannel e-commerce
E-commerce leaders need instant answers, but waiting on the data team for ad-hoc reports creates bottlenecks. This two-part BI module pairs an executive Tableau dashboard for daily monitoring with a generative AI chat that builds custom charts on the fly.
285M+
raw behavioural events cleaned and modelled in Python
2
layers: an executive Tableau view and a plain-English chat for ad-hoc questions
0
direct access to the raw database for the AI, keeping data secure and token costs low
The situation
Multichannel e-commerce generates huge amounts of behavioural data across websites, apps and social platforms. Executives need that data to set strategy, but they shouldn’t need a data science degree to ask about top-selling brands or revenue trends.
Key challenges
- Leadership struggles to consolidate performance across sales channels.
- Analysts lose hours building one-off reports for basic business questions.
- Giving an AI unrestricted access to raw databases creates security and cost risks.
How it works
Tame the data
Over 285 million raw behavioural events were cleaned, filtered and reshaped in Python into one focused analytical table that isolates purchase intent and revenue drivers.
Build the executive view
The processed data feeds a Tableau dashboard where leadership tracks revenue trends, channel comparisons and category breakdowns at a glance.
Chat with the data
For questions the dashboard doesn’t cover, users ask a Streamlit app in plain English, and the AI writes the Python code that draws the requested chart.
Keep it secure
The app queries a controlled dictionary version of the data, never the raw database. This cuts token costs, protects the data and shows the generated code for full transparency.
The outcome
Leaders get structured reporting and on-demand conversational analytics in one place.
- Zero-wait reporting: stakeholders create custom visual reports instantly, with far less dependence on the data team.
- Unified visibility: channel performance and revenue drivers are monitored centrally in Tableau.
- Cost and security: the AI never sees the full dataset, keeping costs low and security high.