Over time, prompts become long and complex, accumulating contradictions from multiple contributors. Chip Huyen suggests treating them like a codebase: use another AI to analyze the prompt for inconsistencies and "refactor" it for better performance and clarity.

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.

Modern AI models infer context from the codebase, making detailed `agent.md` files redundant. These files waste tokens on every interaction and are only necessary for highly specific, proprietary information that must always be present in the context.

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.

An unmaintained Agent OS has a shelf life of about eight weeks before context files are outdated and skills become irrelevant. To ensure compounding value, you must periodically conduct retrospectives with your agents, auditing which parts of the system are underutilized or stale and need updating.

Long, continuous AI chat threads degrade output quality as the context window fills up, making it harder for the model to recall early details. To maintain high-quality results, treat each discrete feature or task as a new chat, ensuring the agent has a clean, focused context for each job.

Long-running AI agent conversations degrade in quality as the context window fills. The best engineers combat this with "intentional compaction": they direct the agent to summarize its progress into a clean markdown file, then start a fresh session using that summary as the new, clean input. This is like rebooting the agent's short-term memory.

Long conversations degrade LLM performance as attention gets clogged with irrelevant details. An expert workflow is to stop, ask the model to summarize the key points of the discussion, and then start a fresh chat with that summary as the initial prompt. This keeps the context clean and the model on track.

To get consistent, high-quality results from AI coding assistants, define reusable instructions in dedicated files (e.g., `prd.md`) within your repository. This "agent briefing" file can be referenced in prompts, ensuring all generated assets adhere to a predefined structure and style.