Mystery Writer

Status: In Progress

This tool to logically transition the story state with the narrative.

Launch Application GitHub

Why I Built It

This tool was inspired by the HuggingFace dataset dmitriihook/qwq-32b-planning-mystery-7-24k, which is made up of state and verb objects that transition the state. My intent was to create a tool that could capture narrative elements and show the mystery writer the gaps and loose ends within their story. The current version is 90% manual, but I hope to use this dataset in a novel way.

Technology

How to Use It

  1. Sign in, or work as a guest.
  2. Load or import a document.
    1. Works best with .txt or .rtf; .pdf and .docx are supported with some bugs.
    2. If you sign in, you can see documents you've worked on.
    3. A guest can work on a document, export it, and re-import it later.
  3. Once loaded, click twice to specify a range, or click and drag over text.
    1. In the right panel, select the kind of state or action you're labeling.
    2. Open the filter dropdown and hover over terms to see their definitions.
    3. You can add a clarifying note to whatever you labeled.
  4. In the Narrative Engine, add characters and artifacts.
    1. When you seed a state instance, you associate something you labeled with its state type and give it an owner — a person, group, or thing. Example: choose a dialect label, select "dialect" as the state type, and assign it to a person or group.
  5. Once you have a state, you can apply a transition. This is where the tool ties up loose ends, by invalidating/consuming the seed states. Any seed state remaining at the end of the narrative is a loose end.
  6. PLAN import is where the dmitriihook dataset comes in.
    1. Each plan represents a subplot in the narrative.
    2. Select an import and a dropdown appears; each option shows a step-by-step meta resolution.
    3. Most are broken because they're missing a state object.
    4. Match your seed states to a PLAN to figure out what's missing from the narrative.
    5. The Import CSV button is for later expansion.
  7. Mapping profiles (needs work)
    1. You create patterns you can find in your seed states.
  8. Finding: Dangling Elements (needs work)
    1. This tool auto-captures any state object that was never resolved.

Technical Details

Architecture overview and notable implementation details.

Known Limitations