Context Relay
ELI5 — The Vibe Check
Context relay is passing AI context forward across sessions, agents, or tools — the plumbing behind persistent, coherent AI workflows. When Agent A finishes its job and hands findings to Agent B, that handoff is a context relay. When you compress last week's conversation and load it into today's session, that's a context relay. Without it, every AI session starts from zero, like a goldfish with a keyboard.
Real Talk
Context relay refers to the mechanism of serializing, compressing, and forwarding relevant context from one AI interaction to the next. This can be agent-to-agent (via tool call outputs or shared memory stores), session-to-session (via CLAUDE.md files or vector retrieval), or cross-tool (passing Claude's output to GPT-4 or vice versa). Effective relay systems must solve the signal-to-noise problem: what context actually matters downstream?
When You'll Hear This
"The orchestrator handles context relay between the specialist agents." / "Context relay is broken — the second agent doesn't know what the first one did."
Related Terms
Agent
An AI agent is an LLM that doesn't just answer questions — it takes actions.
Auto Memory
Auto memory is AI that saves and recalls context across sessions without being asked — like it actually paid attention last time.
Context Window
A context window is how much text an AI can 'see' at once — its working memory.