01 / Workspace
A shared business workspace.
The React frontend organizes Finance, Marketing and Customer Support. Supabase authentication identifies the user making a request.
REACT + SUPABASE AUTHCASE STUDY 02APPLIED AI
An AI-powered business platform in development across Finance, Marketing and Customer Support.
01 / CONTEXT
A small business can have useful information spread across documents, financial records and customer conversations. Moving between separate tools makes it harder to turn that information into a useful answer or plan.
Opsly is a business platform in development across Finance, Marketing and Customer Support. My work centers on Python backend services, a retrieval-augmented assistant, forecasting and analytics.
02 / PERSONAL SCOPE
03 / OUTCOME
Opsly brings Finance, Marketing and Customer Support into one AI-powered business platform, with retrieval and forecasting capabilities in development.
FORECAST WALKTHROUGH · SAMPLE RECORDS
Compare two example spending histories through Opsly’s local forecasting fallback.
Estimated range
$4,386 – $5,934
| Month | Type | Amount |
|---|---|---|
| Jan | Historical record | $4,800 |
| Feb | Historical record | $5,100 |
| Mar | Historical record | $4,900 |
| Apr | Historical record | $5,200 |
| May | Historical record | $5,000 |
| Jun | Historical record | $5,100 |
| Jul | Forecast | $5,160 |
| Aug | Forecast | $5,220 |
| Sep | Forecast | $5,280 |
THE SYSTEM IN PRACTICE
The platform combines a shared product interface with separate workflows for business knowledge and financial data.
FOLLOW THE FLOW
01 / Workspace
The React frontend organizes Finance, Marketing and Customer Support. Supabase authentication identifies the user making a request.
REACT + SUPABASE AUTH02 / Knowledge
The chatbot backend retrieves relevant document context through embeddings and pgvector search. The assistant can use that business information when responding.
DOCUMENTS → RETRIEVAL → ASSISTANT03 / Forecast
The finance workflow groups records by month and produces a forecast from the user’s current history, with different handling when very little data is available.
FINANCIAL RECORDS → MONTHLY SERIES → FORECAST04 / Review
Forecast views separate historical and predicted values. Conversation views let the business review assistant sessions and messages.
CHARTS + CONVERSATION HISTORYENGINEERING CONSIDERATIONS
The forecasting implementation handles a single month of history with an average-based forecast. With more history it uses Prophet, with fallback behavior when model prediction fails. This makes the amount and quality of available data an explicit part of the workflow.
The main backend delegates document retrieval to the chatbot service. Embedding and vector-search work stay together, while other product features can request relevant business context through a defined endpoint.