Loading patterns…
Sleep-Time Compute(STC)
Use idle time between user interactions to do background reasoning instead of waiting for the next query. The agent reorganizes and compresses memory, precomputes likely-needed inferences, and pre-answers anticipated questions so work is shifted off the latency-critical path. At inference time the answer is largely ready, cutting test-time compute and latency.
In 30 seconds
- What
- Performs reasoning and inference during idle periods between user interactions, precomputing answers and reorganizing memory to reduce latency when queries arrive.
- When to use
- Sporadic user interactions with large, stable context where background compute capacity exists and query patterns are somewhat predictable.
- Watch out
- Precomputed answers become stale or wrong if context changes between idle time and query, wasting both compute and user trust.
Ask the AI expert about this pattern
Opens the assistant with your question prefilled. You review it before sending.
Sleep-Time Compute: Overview
Use idle time between user interactions to do background reasoning instead of waiting for the next query. The agent reorganizes and compresses memory, precomputes likely-needed inferences, and pre-answers anticipated questions so work is shifted off the latency-critical path. At inference time the answer is largely ready, cutting test-time compute and latency.
- Background reasoning during idle windows
- Memory reorganization and compression
- Precomputed inferences over stored context
- Anticipated-query pre-answering
- Cost amortized across future queries
- Latency shifted off the critical path
The Agent Architect
One pattern, one tradeoff, one production failure story. A short weekly briefing for people building agentic systems.
Weekly email, one-click unsubscribe. We only use your address to send the briefing.
References
The papers, specifications, and repositories this pattern is based on.
From the engineer behind this catalog
Get your agent architecture reviewed
This page documents one pattern. Your system runs dozens, and most failures live in how they fit together. Have the whole design reviewed against the 288 patterns in this catalog: architecture, reliability, evaluation and cost, every finding mapped to the pattern that fixes it.
€750 instead of €1,500, one week, written report and walkthrough call, until 30 September