SlothDesk: Stop Scrolling Client Chats. Start With a Clear Work Plan.
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 3: Slow and Steady . A client asks you to change a heading. Ten messages later, they cancel that request and ask you to fix the contact form instead. The next morning, you read the entire thread again to figure out what actually needs doing. I built SlothDesk to prepare that work plan for review. What I Built SlothDesk turns…
SlothDesk aims to simplify client communication by turning messy conversations into a structured work plan. Users paste a conversation or upload a text export, and SlothDesk generates a proposed work plan, including tasks, decisions, clarification questions, and a draft response. The app handles changes in instructions, such as cancelled requests or revised deadlines, by offering a detailed review of proposed changes before acceptance.
This ensures users retain control and avoid incorporating unintended elements into their task list. SlothDesk's strength lies in its reconciliation feature, which reconciles conflicting instructions and maintains a clear record of changes. Built with Next.js, TypeScript, and Tailwind, SlothDesk utilizes Ollama for local AI inference, defaulting to Gemma 3 4B.
The application is MIT licensed and allows users to run open-weight models on their hardware. While the hosted demo is limited by Ollama's unavailability, the local integration enables a fully functional workflow for freelancers, agency owners, and project managers. Open innovation is encouraged by providing access to the extraction prompt and allowing model replacement without the need for proprietary inference providers.
Users should exercise caution when uploading confidential conversations to the hosted website, as privacy cannot be guaranteed.
Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
