Agent Systems · core
Long-running & Scheduled Agents
Cron triggers, queues, leases, heartbeats, deadlines, cancellation, checkpoints, notifications, and cost budgets.
Mental model
Long-running agents are jobs with model decisions inside. They still need ownership, schedules, leases, cancellation, deadlines, observability, and bounded spend.
How to study Long-running & Scheduled Agents
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 Effective context engineering for AI agents (Anthropic), Long-running Claude for Scientific Computing, Scaling Long-Horizon LLM Agent via Context-Folding to check details, but close the source before writing your explanation. Retrieval is the learning step; rereading is only preparation.
Next, compare Long-running & Scheduled Agents with Agent Permissions & Sandboxing. Ask what changes in correctness, latency, resource use, operability, and failure recovery. Complete Design exercise: Long-running & Scheduled Agents 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
Practice and explain it back
Design exercise: Long-running & Scheduled Agents
Cron triggers, queues, leases, heartbeats, deadlines, cancellation, checkpoints, notifications, and cost budgets. Implement designOutline() returning non-empty values for: trigger, leaseHeartbeat, budget. Each value must name a concrete mechanism or decision.
Expected evidence: A design outline with trigger, leaseHeartbeat, budget plus an explicit failure mode or trade-off.
Open the interactive drill →Review prompts
- What does a lease give a scheduled agent that a cron entry alone does not?
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