Aakhri Tareekh: An Offline AI That Finds Deadlines in College Notices

A developer built Aakhri Tareekh, an offline-first college notice reader that extracts deadlines and actions from messy PDFs or scanned notices using the open-weight Qwen3.5-4B model running locally through Ollama. The app renders notice pages as images, passes them to the model with a strict extraction prompt, and returns structured JSON with titles, deadlines, actions, audience, fees, documents, summary and evidence, deliberately marking ambiguous dates as unclear rather than guessing. The project is open-sourced on GitHub and was submitted to the Hacktoberfest Weekend Challenge: Build for a Friend.

An offline-first college notice reader for the friend who keeps missing deadlines. This is a submission for the Hacktoberfest Weekend Challenge: Build for a Friend https://dev.to/challenges/hacktoberfest-weekend-2026-10-01 . College notices are often long, messy PDFs or scanned documents. Important dates can be buried inside several pages, and missing one deadline can mean missing a registration, payment, examination, or application. I built Aakhri Tareekh आख़िरी तारीख for a friend who repeatedly discovers important college deadlines too late. The app turns a college notice into a clear set of actions: unclear instead of guessing .ics calendar events The core idea is simple: Turn a messy college notice into one trustworthy next action. The project currently runs locally with Ollama and does not require a cloud AI API. Demo flow: GitHub repository: https://github.com/pratyushmishra9920-ship-it/aakhri-tareekh https://github.com/pratyushmishra9920-ship-it/aakhri-tareekh The project is built with: The repository contains the complete application, setup instructions, requirements, and the dashboard screenshot. The AI core uses the open-weight Qwen3.5-4B model locally through Ollama . A selected notice page is rendered as an image and passed to the local model with a strict extraction prompt. The model returns structured JSON containing the title, deadlines, actions, audience, fees, documents, summary, and evidence. I deliberately designed the extraction process to be conservative. The system is instructed to: null and This matters because a wrong deadline can be worse than no deadline at all. For example, if a notice contains a date range such as 15 July 2026 to 19 July 2026 , the application does not arbitrarily choose one of those dates as the deadline. It preserves the range and marks it as unclear when a single calendar date cannot safely be determined. Using an open-weight model locally changes what this application can do. Privacy: College notices can contain academic, registration, payment, or student information. The document can remain on the user's machine. Offline-first: After downloading the model, notice analysis can run locally without sending documents to a cloud AI service. No per-notice API bill: Local inference means there is no cloud API request for every notice. Model freedom: Because the application communicates with Ollama, the underlying model can be replaced or upgraded later. Custom behavior: The extraction process can be specifically designed around college notices and a strict no-guessing policy rather than relying on a generic document summarizer. The open model is therefore not just a cheaper replacement for a closed API. It gives me control over where the data goes and how the model is used. I used AI coding assistance while developing the project. I did not complete a DevRelay session that I can provide as a verified agent-session artifact for this submission, so I am not claiming a DevRelay-specific category. This submission is for the Overall Winner of the Hacktoberfest Weekend Challenge: Build for a Friend. I am not claiming a partner-specific prize category that requires technology I did not actually use in this project. The project started from a very practical problem. A friend kept missing important college deadlines because the information was buried inside notices that were difficult to scan quickly. I could have built a generic AI document summarizer, but that would not solve the actual problem. Instead, I focused the application on one specific outcome: What do I need to do, and when do I need to do it? That focus influenced the entire design — especially the evidence shown alongside each extracted deadline and the decision to say unclear instead of guessing. The biggest lesson from building Aakhri Tareekh was that an AI application does not always need to be more confident. For a deadline extractor, knowing when not to guess is a feature. Working with a local open-weight vision model also made me think about the complete AI system rather than treating an API call as the whole application. The project started as a simple idea for one friend, but it became a useful example of how local open AI can be combined with a focused workflow to solve a very specific real-world problem. Built for the Hacktoberfest Weekend Challenge: Build for a Friend .