Pixal
Slack application implementing generative AI in workspaces. Developed during Adobe Career Academy apprenticeship.
Overview
Pixal is a Slack application that implements generative AI in workspaces. It connects data from your workspace to its knowledge base to answer any question regarding any subject from your Slack workspace.
The Challenge
Teams struggle to find information scattered across Slack channels, threads, and shared documents. Questions get repeated, institutional knowledge is lost, and productivity suffers when information is difficult to locate. Traditional keyword search misses contextual understanding.
The Solution
Built a Slack app that integrates with workspace data to create a searchable knowledge base powered by generative AI. Users can ask questions in natural language—summarizing discussions, finding timestamps, understanding individual perspectives, or identifying who certain individuals are—and Pixal answers based on all public data in the Slack workspace. Developed, tested, and debugged using Python and JavaScript, presented to Adobe staff during the Adobe Career Academy program.
Impact & Results
Seamlessly integrated into existing Slack workflows
Automated knowledge retrieval from workspace conversations
Improved team knowledge sharing and onboarding
Presented to Adobe staff as part of Adobe Career Academy
Processed queries from summarization to individual identification
Technologies
Tags
Alex AI
Winner of 2023 TedAI & Microsoft Hackathon in San Francisco. AI-powered business creation tool that identifies optimal business structures and auto-fills documents.
Legiscan
Stanford Law School / CODEX LLM hackathon project. Compares proposed legislation against status quo using GPT-3.5.