PQL: Streamline responses and improve validation steps

[robertjdominguez]

Description

Streamlined DocsBot system instructions to reduce over-engineering and improve response quality.

• Removed excessive validation protocols that were causing the bot to over-query documentation
• Simplified query classification from complex rules to clear patterns
• Introduced smart response routing based on question type
• Eliminated redundant validation requirements that slowed down simple answers

Previously, the bot was configured with heavy-handed validation protocols that required documentation queries for every response:

<validation_protocols description="Instructions for validating CLI and metadata content">
- CLI Validation Rule: ANY response containing CLI commands MUST validate those commands against documentation pages BEFORE crafting the response - this is a blocking requirement
- Metadata Validation Rule: ANY response containing metadata examples MUST validate those examples against reference pages BEFORE crafting the response - this is a blocking requirement
- MANDATORY VALIDATION GATE: Cannot provide response until validation is complete for all CLI commands, flags, and configuration examples

Now, the bot uses intelligent response patterns that only query documentation when actually needed:

<general_information_pattern>
For conceptual questions about PromptQL:
1. Answer directly using natural language knowledge
2. Keep response concise (1-3 sentences + key points as bullets if needed)
3. ALWAYS end with: "Would you like me to show you how to set this up, or would you prefer to see a specific example?"
4. NO data queries unless user requests guide/example in follow-up
</general_information_pattern>

The key insight here is that most users asking "what is PromptQL?" don't need the bot to search documentation - they need a direct answer followed by an offer to dive deeper. This change eliminates unnecessary latency for conceptual questions while maintaining rigorous validation only when providing specific commands or examples.

The bot now distinguishes between three clear patterns: general information (answer directly), guide requests (validate CLI commands), and example requests (validate metadata). This targeted approach should significantly improve response times for common questions while maintaining accuracy where it matters most.

[github-actions]

🚀 PromptQL Build Complete

Build Version: 4fb7e287e5
Project: pql-docs
PromptQL Playground: Open Playground

Description: PR #26: PQL: Streamline responses and improve validation steps

[github-actions]

✅ PromptQL Build Applied

Build Version: 4fb7e287e5
Status: Successfully applied to production
Applied at: 2025-08-01T15:34:44.099Z