Skip to content

Case Studies

From Problem to Working Solution.

Longer write-ups covering the objective, the approach taken and what the finished build actually does.

  • Digital Food Ordering Experience

    Healthy Kitchen

    A customer-facing ordering experience for a food business: browse the menu, discover suitable meals, build a cart and complete checkout on a phone, with each order captured as a record rather than a message.

    • React
    • TypeScript
    • Tailwind CSS
    • Database
    Read case study: Healthy Kitchen

    What was built

    • Mobile-first ordering flow
    • Structured menu and order model
    • Cart and checkout experience
    • Orders captured as database records
  • Retrieval-Augmented Document Assistant

    GenAI RAG Document Assistant

    A generative AI application where users upload documents and ask questions about them. Answers are produced from passages retrieved out of the uploaded material, keeping responses tied to source content.

    • Python
    • LangChain
    • LangGraph
    • Vector Database
    • LLM
    • Streamlit
    Read case study: GenAI RAG Document Assistant

    What was built

    • Document ingestion and chunking
    • Embeddings and vector retrieval
    • Context-grounded generation
    • Inspectable retrieval step
  • NLP Sentiment Analysis Pipeline

    Airline Sentiment AI

    A natural language processing project that turns airline-related customer text into structured sentiment data so themes can be explored as a dataset rather than read message by message.

    • Python
    • NLP
    • Machine Learning
    • Pandas
    • scikit-learn
    Read case study: Airline Sentiment AI

    What was built

    • Text preprocessing
    • Supervised sentiment classification
    • Held-out evaluation
    • Exploratory analysis of labelled data
  • Regression Modelling for Vehicle Pricing

    Used Cars Price Prediction

    A machine learning project that analyses second-hand vehicle attributes and predicts listing prices, built around a clean dataset and a reproducible evaluation method.

    • Python
    • Pandas
    • Scikit-learn
    • Machine Learning
    • Matplotlib
    Read case study: Used Cars Price Prediction

    What was built

    • Data preprocessing
    • Feature analysis
    • Regression model development
    • Documented evaluation methodology

Want this level of detail on your project?

Tell us the objective and we will walk you through how we would get there.