learning

Review, block, or regenerate BCOS learned rules from resolution logs.

18|Updated Apr 5, 2026
One-click install
npx skills add https://github.com/walm00/business-context-os --skill learning-walm00
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: learning
Source: https://github.com/walm00/business-context-os/tree/main/.claude/skills/learning
Command: npx skills add https://github.com/walm00/business-context-os --skill learning-walm00

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) and references (resource) components.

What problem does it solve?

It enables users to inspect, edit, and control the rules that BCOS has learned from their resolutions, ensuring transparency and customization in the AI's adaptive behavior.

Core Features & Use Cases

  • Inspect Learned Rules: View rules promoted by the system based on user interactions.
  • Forget or Block Rules: Veto specific learned rules to prevent future suggestions.
  • Regenerate Rules: Recompute learned rules from resolution logs after manual adjustments or updates.
  • Evidence Lookup: Review event logs backing specific rules to verify their accuracy.

Quick Start

Ask the AI to show me the current learned rules or to regenerate the learning data for updated insights.

Frequently Asked Questions about learning

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I review and manage autonomous rules learned by an AI system?

To review and manage autonomous rules learned by an AI system, you can inspect rules promoted from user interactions, view the backing event logs for evidence, and veto specific rules to prevent future suggestions.

Can I block or veto specific automated rules from being suggested again?

Yes, you can block or veto specific automated rules to prevent future suggestions, ensuring safe and predictable updates by maintaining user control over the AI's adaptive behavior and learned knowledge.

How do I regenerate learning rules from resolution logs after making updates?

To regenerate learning rules from resolution logs, you trigger a recompute process that evaluates the updated resolution events, allowing the system to safely recompute and promote new rules based on the latest data.

How do I verify the accuracy of rules promoted through automated self-learning?

You verify the accuracy of rules promoted through automated self-learning by performing an evidence lookup, which allows you to review the specific event logs and JSON artifacts that back each generated rule.

Does controlling self-learning rules require transparent resolution event logs?

Yes, controlling self-learning rules requires transparent resolution event logs and JSON artifacts, as the system leverages these records to recompute rules, verify accuracy, and ensure safe controlled script execution.