Loading patterns…
Durable Execution & Checkpointing(DE)
Persists workflow and agent state at every step so long-running runs can crash-resume from the last checkpoint, replay deterministically without repeating completed work, pause and resume for human input, and time-travel by forking from an earlier checkpoint. Checkpointer-backed graph engines such as LangGraph and Temporal-style durable engines provide the substrate for reliable, long-lived, human-in-the-loop agents.
In 30 seconds
- What
- Persists workflow state after each step so crashes resume from the last checkpoint, replays skip completed work, and runs fork from earlier points.
- When to use
- Long-running multi-step work where crashes are costly, human approval is needed mid-flow, or you must retry without redoing finished steps.
- Watch out
- Checkpoint storage and serialization overhead can dominate runtime; non-deterministic steps (randomness, external calls) break replay guarantees.
Ask the AI expert about this pattern
Opens the assistant with your question prefilled. You review it before sending.
Durable Execution & Checkpointing: Overview
Persists workflow and agent state at every step so long-running runs can crash-resume from the last checkpoint, replay deterministically without repeating completed work, pause and resume for human input, and time-travel by forking from an earlier checkpoint. Checkpointer-backed graph engines such as LangGraph and Temporal-style durable engines provide the substrate for reliable, long-lived, human-in-the-loop agents.
- State checkpointed after each step
- Crash recovery resumes from the last checkpoint
- Deterministic replay skips completed steps
- Interrupt and resume for human-in-the-loop
- Time-travel: fork alternate runs from any checkpoint
- Durable timers for long waits and retries
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