AI agents can overcomplicate instructions and create 'AI sprop' (slop/propaganda). To combat this, build a dedicated 'skill editor' skill that runs on other skills to make them more concise, remove repetitive instructions, and maintain clarity in your automations.

Layer a web app over your GitHub skill repository to help non-technical team members visualize skill connections, search for automations, and understand the company's AI capabilities. Usage tracking via hooks can also identify underutilized or obsolete skills, preventing bloat.

To solve the problem of an AI agent creating low-quality memories and skills ("slop") over time, Hermes Agent runs a sub-system called "Hermes Curator." This internal agent automatically and continuously cleans, refines, and improves the main agent's learned skills and memories.

The "Agent Skills" format was created by Anthropic to solve a key performance bottleneck. As capabilities were added, system prompts became too large, degrading speed and reliability. Skills use "progressive disclosure," loading only relevant information as needed, which preserves the context window for the task at hand.

A shared AI knowledge base risks becoming polluted with outdated or contradictory information. A 'gardening agent' solves this by automatically identifying context that is wrong, conflicting, or aged out (e.g., noting an employee has left), ensuring system reliability.

Like a product requirements document (PRD), an AI skill and its evaluation (eval) are never 'done.' As you use the system, you'll learn new things. Continually ask the AI to update its own instructions to build increasingly effective automations over time.

The primary challenge in building Stripe's internal AI, Kai, wasn't the technology, but creating governance structures. This ensures employees across a complex, global business can use AI safely and know it will "do the right thing," making governance the true product.

A common pitfall is over-engineering a second brain with too many pipelines and skills. To maintain focus and effectiveness, deliberately practice cleanup. Periodically review your automations and, as the speaker does, "delete a few skills every couple of weeks" to prevent bloat and stay focused.

Stripe's Kai succeeds by being a skill-building platform, not just a tool. Users can package successful interactions into reusable workflows ("skills") to share across the company. This democratizes automation and transforms the agent into a system for codifying institutional knowledge.