Personal Project · Local-First Research Companion

Ami

I built Ami for my mother. It organizes her PDFs, books, notes, and personal records; searches them on her computer; and shows the original evidence behind each AI-assisted answer.

At a glance

Role

Solo product designer and developer

Platform

Browser-based app packaged for macOS

Core Stack

Python, FAISS, local storage, Codex SDK bridge, HTML/CSS/JS

Purpose

Help my mother organize and search health-research materials

Problem And Approach

My mother had articles, books, photos, lab documents, and personal notes spread across different places. The first problem was organizing that material so she could find useful evidence without managing several tools.

I kept the library and search index on her device. Ami uses AI to summarize selected passages and suggest follow-up questions, while the interface keeps the source pages visible for verification.

Constraints That Mattered

  • - The interface had to be comfortable for a non-technical user.
  • - Documents and the search index needed to remain on the device for privacy and offline access.
  • - Answers needed visible links to source pages and careful wording when evidence was incomplete.
  • - Installation, startup, and shutdown had to work without developer support.

Current Build

Ami manages a private document library, classifies imports, renders PDF page previews, saves settings and answer history, and sends selected evidence to Codex through a local bridge.

  • - Imports PDF, EPUB, TXT, Markdown, and short notes into a searchable local library.
  • - Finds relevant passages, shows page previews, and sends only the selected evidence to the AI.
  • - Stores personal notes and medical files separately while allowing them to be referenced when needed.
  • - Provides saved chats, document previews, suggested next steps, and optional reference images.
  • - Packages the app and its data folder together for portable macOS use.

Product Screens

Current build captures showing saved chats, answers with cited evidence, document previews, optional reference images, and saved preferences.

MacBook Testing

Testing the installed app on my mother's MacBook exposed lifecycle problems that did not appear on my development machine. I used that feedback to simplify relaunching the app and shutting down its background service.

  • - A second launch detects the running server and reopens the interface instead of causing a port conflict.
  • - Browser heartbeat and shutdown signals close the background service after the Ami tab is closed.
  • - Ami.app contains the application; AmiData contains the library, search index, and personal records.
  • - Testing on my mother's MacBook exposed startup and shutdown problems that did not appear during development.

Engineering Scope

I handled product design, document retrieval, local storage, interface implementation, packaging, debugging, and deployment. The project required both system-level decisions and patient iteration with a non-technical user.

It demonstrates experience with private on-device data, evidence-based AI features, cross-platform packaging, and interface design for a stressful research context.

Outcome

I deployed Ami on my mother's MacBook as a portable app with local document search, page-level evidence, saved conversations, and a data folder she can move or back up independently.