learning-synthesis

Session analysis for opportunity discovery works by analyzing reconstructed daily user sessions to identify recurring needs for system improvement. It requires pattern-based evidence analysis across multiple sessions to distinguish opportunities from quality bugs, capturing supporting evidence threads to prioritize missing skills, tools, or workflows.

Nightly review of session evidence requires pattern-based evidence analysis across reconstructed Slack-thread interactions. You apply opportunity discovery to identify recurring needs for new skills, domain knowledge, or prompt guidance, distinguishing patterns from isolated failures to produce a structured JSON opportunity report for self-improvement.

Opportunity discovery from session evidence distinguishes recurring workflow automation opportunities from isolated quality bugs by requiring patterns across multiple sessions. It captures supporting evidence threads to validate that a missing skill, persona, or prompt guidance represents a genuine recurring need rather than a single interaction failure.

Strict JSON output is required for opportunity discovery to ensure concrete implementation targets and selective autonomous build recommendations. This structured format captures missing skills, personas, tools, workflows, and prompt guidance, enabling the nightly self-improvement process to autonomously select and execute high-value system enhancements.

Session analysis is limited by requiring reconstructed daily user sessions and pattern-based evidence across multiple interactions to validate opportunities. It cannot treat isolated single interactions as opportunities, relying strictly on recurring Slack-thread evidence packs to generate concrete implementation targets and autonomous build recommendations.