To prevent an AI agent from repeating mistakes across coding sessions, create 'agents.md' files in your codebase. These act as a persistent memory, providing context and instructions specific to a folder or the entire repo. The agent reads these files before working, allowing it to learn from past iterations and improve over time.

To improve an agent's performance on a specific task like prompting the VO3 video model, create a dedicated 'onboarding document'. Use a tool like Perplexity to gather best practices from experts, compile them into a doc, and instruct the agent to reference it. This shortcuts the learning curve and embeds expertise.

"Skills" are markdown files that provide an AI agent with an expert-level instruction manual for a specific task. By encoding best practices, do's/don'ts, and references into a skill, you create a persistent, reusable asset that elevates the AI's performance almost instantly.

A simple, on-premise AI can act as a "buddy" by reading internal documents that employees are too busy for. It can then offer contextual suggestions, like how other teams approach a task, to foster cross-functional awareness and improve company culture, especially for remote and distributed teams.

The 'Claudie' AI project manager reads a core markdown file every time it runs, which acts as a permanent job description. This file defines its role, key principles, and context. This provides the agent with a stable identity, similar to a human employee, ensuring consistent and reliable work.

Instead of siloing agents, create a central memory file that all specialized agents can read from and write to. This ensures a coding agent is aware of marketing initiatives or a sales agent understands product updates, creating a cohesive, multi-agent system.

The `cloud.md` file acts as a project-specific memory and personality for an AI agent like Claude Code. By instructing the agent to save learnings, preferences, and session summaries to this file, you create a self-improving system that gets more effective with each interaction on that project.

AI agents have limited context windows and "forget" earlier instructions. To solve this, generate PRDs (e.g., master plan, design guidelines) and a task list. Then, instruct the agent to reference these documents before every action, effectively creating a persistent, dynamic source of truth for the project.

The paradigm for AI delegation shifts from instructing an agent to curating a knowledge base. Your primary job is ensuring your Obsidian vault accurately reflects your thinking. An autonomous agent pulls from this "source of truth," and you correct its behavior by updating the vault, not the agent.