Context bloat: why long-running agents break
Context bloat is when accumulated tool-call output crowds out an agent's task. Tool calls, not window size, break long-running agents. Here is the fix.
Further reading
Articles about Context Offloading
5 articles from the Wire blog, sorted newest first. Return to the Context Offloading definition for context.
Demand paging for the AI context window
A 2026 systems paper found 21.8% of tokens in agent context windows are wasted. Demand paging treats the AI context window as L1 cache, not full memory.
MCP Tasks: long-running work as context offloading
MCP Tasks let a server return a durable handle instead of a blocking result, keeping a long-running tool call's interim state off the agent's context window.
AI notetakers ship the wrong artifact
AI notetakers ship transcripts, but downstream work needs decisions, drafts, or handoffs. The artifact gap is a context engineering problem, not transcription.
Context offloading: 3 patterns for AI agents
Context offloading keeps an AI agent's working context window small by moving state to a destination outside it. Three patterns, and what each one costs.
Put context into practice
Create your first context container and connect it to your AI tools in minutes.
Create Your First Container