inquisitive

What problem does it solve?

Inquisitive reduces first-try errors by learning why the agent’s proposed output didn’t match what the user actually wanted, based on real user adjustments.

Core Features & Use Cases

• Context-aware “why” questioning: asks targeted questions that explain the gap between the agent’s suggestion and the user’s choice, then captures the reasons behind the preference.
• Categorized, scoped memory: stores learnings across 12 categories and escalates between repo, org, and user scope so repeated preferences become durable.
• Refined summaries and sub-skill generation: consolidates memory into evolving summaries and can draft or create refinement sub-skills when strong patterns emerge.

Quick Start

When the agent proposes a change and you modify it afterward, say what you wanted instead and why, so inquisitive can learn your preference from that adjustment.