← Back to Terminology Glossaryanti-patterns

Context Decay

The gradual degradation of AI agent performance in extended chat sessions as earlier instructions, style rules, or constraints are diluted by high token volume.

Understanding Context Decay

Context Decay is a common failure mode in AI-assisted software development. In prompt session #1, an AI agent follows all project guidelines perfectly. By prompt session #15, the agent starts introducing syntax errors, forgetting path aliases, or overwriting existing component files.

This happens because LLM context windows, while vast (200k to 1M+ tokens), suffer from attention dilution and middle-loss syndrome. As the chat log fills with generated code and stack traces, the relative weight assigned to initial prompt instructions decreases.

---

Symptoms of Context Decay

  • Constraint Amnesia: The AI begins using forbidden libraries (e.g. installing Tailwind when Vanilla CSS was specified).
  • Import Erasure: Removing critical module imports when modifying existing components.
  • Style Inconsistency: Writing inconsistent button styles or bypassing established design system tokens.
---

How to Prevent Context Decay

    • Move Rules out of Chat into Root Files: Place persistent instructions in AGENTS.md or CLAUDE.md. AI tools read these files fresh on every invocation.
    • Execute Short, Atomic Prompt Loops: Keep chat threads focused on single feature tasks (e.g., 3-5 prompts per session).
    • Use Reset Commands: In CLI tools like Claude Code, run /compact or /clear regularly to wipe transient chat state while retaining file-based context.
    • Build an Automated Test Harness: Use automated test suites (npm test) to catch regressions the moment context decays.