progressive-learn

Structured domain learning is achieved through a five-stage workflow that guides users from basic concepts to frontier research, generating progress notes and fetching papers. It automates workspace initialization and tracks learning stages.

The best way to automate a progressive learning pipeline is using a staged workflow that discovers research papers and generates session notes automatically. It manages pipeline state and updates pipeline.json during each stage advancement.

You can manually advance domain learning stages by passing an optional --advance flag during argument parsing. This triggers the workflow to progress to the next learning stage and update the pipeline state.

Workspace setup for domain-specific study plans is handled automatically by the learning workflow upon initialization. It creates the necessary directory structure and manages pipeline state to track your progress through the five learning stages.

This staged learning approach works for any domain you specify as an argument during initialization. It tailors the five-stage workflow to the chosen domain, fetching relevant papers and generating notes specific to that field of study.

Automated stage-based domain learning relies on the fetched papers and automated note generation, meaning the depth of frontier research depends on available literature. It requires passing a domain name argument and optionally the --advance flag to progress stages.