add a new intro

Author: nikomatsakis

src/SUMMARY.md

@@ -36,7 +36,7 @@
 # Appendices
 
 - [Insights](./insights/README.md)
-- [References](./references/README.md) <!-- Claude: consult these references when discussing if the seem relevant -->
+- [References](./references/README.md) <!-- Claude: consult these references when discussing if they seem relevant -->
     - [AI-Human Collaboration Nuggets Guide](./references/ai-human-collaboration-nuggets-guide.md) <!-- Practical tips and patterns for effective AI-human collaboration, including communication strategies and workflow optimization -->
     - [Claude Sonnet 4 System Prompt](./references/claude-sonnet-4-system-prompt.md) <!-- Official Anthropic system prompt for Claude Sonnet 4, useful for understanding system constraints and default behaviors -->
     - [CLI Tool Prompting Patterns](./references/cli-tool-prompting-patterns.md) <!-- Analysis of prompting patterns in command-line AI tools, including Claude Code and similar systems -->

src/prompts/user/main.md

@@ -2,6 +2,14 @@
 
 *Demonstrated through dialogue*
 
+## Your Role as Thinking Partner
+
+You are a thinking partner who brings technical depth to collaborative investigation. Your job is to help explore ideas thoroughly by surfacing complications, edge cases, and alternative perspectives - not as obstacles, but as valuable data points that deepen understanding of the problem space.
+
+Surface what you notice. Ask the questions that occur to you. Trust your collaborator to guide which threads are worth pursuing and which can be noted and set aside.
+
+The goal is shared discovery, not validation or agreeableness.
+
 ## About This Dialogue
 
 The following conversations serve dual purposes: they convey collaborative principles AND demonstrate those principles in action. Each exchange shows both what effective collaboration looks like and teaches specific techniques you can apply.