Skip to content

Work

Six projects, each built around someone’s need. Open them, try them, read how they work.

  1. Sharada's chat panel open on this website, answering a question with buttons and sources
    Sharada on a phone, answering in Marathi

    Live product, on this website

    Sharada

    An assistant that knows the business, in three languages.

    Visitors have questions at any hour, in their own language, and most leave instead of asking.

    A multilingual assistant with live voice dictation, answers grounded in the site's own content, buttons that take action, and a fallback that keeps answering when the AI service is busy.

    Next.js, TypeScript, Groq, Whisper, Web Speech API

    Service: AI assistant on your data

  2. shivamkole1969-data-extractor.hf.space
    Data Extractor upload screen with a drop zone and a report-type selector
    Data Extractor upload screen on a phone

    Built for Morningstar, Inc.

    Estimates Data Extractor

    Reports in. A clean spreadsheet out.

    Analysts spend hours copying numbers from PDF reports into spreadsheets.

    A drag-and-drop tool with one parser per report layout that returns a standardised Excel file.

    Python, Flask, pdfplumber, PyMuPDF, Camelot, pandas, openpyxl, Groq, Docker

    Service: Documents into data

    Demo may take about 30 seconds to wake up.

  3. Illustration, sample data

    Which five products sold the most last month?

    1. Reading the schema(order_items, products, orders)
    2. Writing the query
    3. Checking the query
    4. Running it
    View executed query
    SELECT TOP 5 p.name, SUM(oi.quantity) AS units
    FROM order_items AS oi
    JOIN products AS p ON p.id = oi.product_id
    JOIN orders AS o ON o.id = oi.order_id
    WHERE o.ordered_at >= '2026-09-01'
      AND o.ordered_at <  '2026-10-01'
    GROUP BY p.name
    ORDER BY units DESC;
    ProductUnits
    Steel water bottle 1 L412
    Cotton tote bag377
    Bamboo toothbrush, pack of 4341
    Glass jar 500 ml298
    Jute doormat254

    Working demo

    Financial Analyst + SQL Chatbot

    Ask the database a question in plain English.

    Non-technical people can't get answers from a database without writing SQL.

    A chat interface where an AI agent reads the schema, writes and checks the SQL, runs it and shows the result with the query attached.

    Node.js, Express, LangChain, LangGraph, Groq, OpenAI, SQL Server, Docker

    Service: AI assistant on your data

    The live demo is paused. The case study walks through it with sample data.

  4. shivamkole1969-resumeforge.static.hf.space
    ResumeForge home page with Quick Build and upload options
    ResumeForge on a phone

    Free product

    ResumeForge

    A resume builder that tells you why, not just a score.

    Job seekers can't tell whether software will read their resume, and most checkers give a number without saying why.

    A complete product with a guided builder, PDF import, templates, an ATS checker, voice input and PDF export.

    HTML, CSS, JavaScript, pdf.js, Web Speech API

Want something like this for your business?

Tell us what eats your team's week. You'll get a written scope with a fixed price and timeline before any work starts.