Back to Projects

AI-Assisted Writing Workflow

Local Qwen Chinese Fiction Pipeline

A local Qwen writing pipeline controlled by Python. It experiments with agent-like writing behavior where the model generates questions, answers them, records context, and uses that context for later fiction segments.

Period

May 2026

Tools / Tech

PythonQwenLocal LLMPrompt WorkflowContext Management

Why I built it

Project focus: this was an exploration of prompt workflow, lightweight memory design, and long-form generation control with a local model rather than a cloud API.

Links

What it includes

  • Runs a local Qwen model through a Python-controlled generation loop.
  • Builds a fiction workflow for setting, outline, segmented continuation, context review, and draft output.
  • Uses a lightweight memory mechanism so previous questions, answers, and story context can guide later writing, with manual review for coherence.

What I worked on

  • Designed the self-questioning loop where the model asks, answers, and summarizes its own context before continuing.
  • Built the Python control flow for prompt sequencing, context recording, and staged generation.
  • Manually reviewed generated text for coherence and kept the project framed as a writing workflow experiment.

What I Learned

  • Learned how fragile long-form generation becomes when context is not explicitly managed.
  • Practiced designing memory and prompt steps as a workflow instead of a single prompt.
  • Built intuition for the gap between an agent-like effect and a reliable agent system.