The local business landscape in the Philippines presents a slow adoption to digitization. There are fears of inaccurate results and limited technical proficiency. Data analytics and artificial intelligence (AI) are crucial for business growth. By understanding the performance of stock-keeping-units (SKU) with technology, businesses can find better ways to handle products to increase profitability. In exploring optical character recognition (OCR) and large language models (LLM), a software pipeline can help businesses analyze handwritten sales data for business intelligence. The research aims to develop a system for translating logbooks into metrics by augmenting manual business processes performed by staff. The application combines Amazon Web Services’ OCR technology with Anthropic’s Haiku 3.0 LLM. The pipeline extracts handwritten text from images and performs few-shot learning-based classification. Data from a local food stall was used for testing. Precision and recall scores were calculated to analyze similarities between original and extracted data. Results showed moderate-low precision but above-average recall. The SKUs yielded average precision and recall scores of 0.32 and 0.62, while sales data stood at 0.55 and 0.54, respectively. These scores indicate that the application struggles with accuracy but captures a fair amount of true values. Improvements are needed to enhance the learning mechanism of the LLM. Despite this, the application holds promise for helping small businesses achieve digitization to supplement manual business processes, taking into account the limited technological literacy of staff. It serves as a potential catalyst for growth by simplifying complex data problems with cost-efficient solutions.