Jason Lin
GH IN

Local meeting-summary trust ยท Local desktop workflow

Project AURA

A local-first meeting-summary workflow that turns corrected transcripts into structured reports while making runtime model readiness and error states visible.

Problem

Meeting summaries are useful only if the user can trust the input, model runtime, field structure, and failure behavior instead of receiving a fluent but uninspectable digest.

System response

The workflow consumes corrected transcripts, runs local layered extraction, renders structured JSON to Markdown, and checks the local Ollama model path before use.

Evidence surface

  • Parallel layered extraction, field schemas, prompts, sample report, and tests.
  • Local Ollama preflight with exact model-tag checking and user-confirmed model pull behavior.
  • Runtime hardening separated model, environment, and UI error states.

Toolkit

PythonPyQtOllamaLocal LLMStructured extraction

Next validation layer

Run the workflow on real corrected meeting transcripts and decide whether the next step is UI polish or real-use accumulation.