Agent Systems · core
Durable Agent Execution
Checkpointed loops, resumable tools, idempotency, leases, event histories, retries, and crash recovery.
Mental model
A durable agent records decisions and side-effect identities so it can resume after interruption without repeating irreversible work.
How to study Durable Agent Execution
Begin by restating the mental model in your own words, then connect it to a concrete system you have built or operated. Name the mechanism, the constraint it addresses, and the trade-off it introduces. Use Serverless Workflows with Durable Functions and Netherite, Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows, Workflows, a New Abstraction for Distributed Systems — Dominik Tornow (Strange Loop 2022) to check details, but close the source before writing your explanation. Retrieval is the learning step; rereading is only preparation.
Next, compare Durable Agent Execution with Browser & Computer-use Agents, Agent Permissions & Sandboxing. Ask what changes in correctness, latency, resource use, operability, and failure recovery. Complete Design exercise: Durable Agent Execution and preserve the command, input, output, and one failed attempt as evidence. Finish by explaining the idea without jargon to someone who has not studied the track.
Proof of understanding
- Explain the mechanism from first principles and identify the state it reads or changes.
- Give one situation where the concept is the right choice and one where it is not.
- Predict a realistic failure mode before running the drill, then compare the prediction with evidence.
- Connect the result to a roadmap or build artifact instead of treating the concept as isolated trivia.
Learn from primary sources
- Serverless Workflows with Durable Functions and Netherite (doc)
- Atomix: Timely, Transactional Tool Use for Reliable Agentic Workflows (doc)
- Workflows, a New Abstraction for Distributed Systems — Dominik Tornow (Strange Loop 2022) (video)
- Durable Functions: Semantics for Stateful Serverless (OOPSLA '21) (paper)
- Temporal — Understanding Temporal (Durable Execution) (doc)
Practice and explain it back
Design exercise: Durable Agent Execution
Checkpointed loops, resumable tools, idempotency, leases, event histories, retries, and crash recovery. Implement designOutline() returning non-empty values for: checkpoint, idempotency, resumeProtocol. Each value must name a concrete mechanism or decision.
Expected evidence: A design outline with checkpoint, idempotency, resumeProtocol plus an explicit failure mode or trade-off.
Open the interactive drill →Review prompts
- An agent crashes after calling a payment API but before recording the result. What makes recovery safe?
Build evidence
Synthesize: Agent Systems
Engineer useful agents with bounded loops, tools, memory, protocols, durability, permissions, and long-running control. Produce one working system, benchmark, or evidence-backed design that integrates the path.
- Implements or precisely models the core mechanisms from all three milestones
- Includes at least one injected failure or adversarial case and demonstrates recovery
- Reports quality, latency, resource, reliability, or usability measurements relevant to the domain
- Ships a concise architecture note explaining decisions, trade-offs, and remaining risks