Get your free personalized podcast brief
We scan new podcasts and send you the top 5 insights daily.
When an AI agent like Claude Code nears its context limit where automatic compaction might fail, a useful hack is instructing it to "write a markdown file of your process and your progress and what you have left to do." This creates a manual state transfer mechanism for starting a new session.
Related Insights
AI models like Claude Code can experience a decline in output quality as their context window fills. It is recommended to start a new session once the context usage exceeds 50% to avoid this degradation, which can manifest as the model 'forgetting' earlier instructions.
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.
When an AI coding assistant gets off track, Tim McLear asks it to generate a summary prompt for another AI to take over. This "resume work" prompt forces the AI to consolidate the context and goal. This summary often reveals where the AI misunderstood the request, allowing him to correct the course and restart with a cleaner prompt.
When an AI's context window is nearly full, don't rely on its automatic compaction feature. Instead, proactively instruct the AI to summarize the current project state into a "process notes" file, then clear the context and have it read the summary to avoid losing key details.
Before ending a complex session or hitting a context window limit, instruct your AI to summarize key themes, decisions, and open questions into a "handoff document." This tactic treats each session like a work shift, ensuring you can seamlessly resume progress later without losing valuable accumulated context.
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.
When a coding agent loses context, don't just start over. A power-user technique is to begin a new session and instruct the agent to read the locally stored conversation logs from the previous, failed session to regain context and continue the task.
Building a comprehensive context library can be daunting. A simple and effective hack is to end each work session by asking the AI, "What did you learn today that we should document?" The AI can then self-generate the necessary context files, iteratively building its own knowledge base.
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.
