Long-horizon agents can automate complex tasks that take days or weeks to complete and involve multiple exchanges with people and external systems. Many things can go wrong during this time, including process crashes, network failures, and unanticipated real-world behavior. Kiran Prakash explains durable execution: an emerging pattern that helps agents recover from these failures and move towards their goal. In this programming model, the runtime keeps a record of the result of each step that interacts with the outside world so that, when a failure occurs, the program runs again, completed steps are skipped, and the program's state is rebuilt from the record.
AI & ML
Source:https://martinfowler.com/articles/durable-execution-agents.html
Long-horizon agents and durable execution
Martin Fowler0 views
PreviousAWS Free Tier in 2026: What's Actually Free (and What Quietly Suspends Your Account)NextAdobe adds more AI to its products and launches an MCP
Related posts
The three-line stub
0dev.to
Hierarchical KV sharing reduces transformer memory usage
0dev.to
Every document you send to an AI vendor is data they now hold: 6 controls
0dev.to
DPDP Phase 2 has started: a six-month checklist for document-heavy teams
0dev.to
Your Subagents Are Carrying Your Whole Brain for a One-Line Job
0dev.to
Does model size matter for LLM agent reliability? 11 open models, 1.5B to 32B: host-held state exact on 10 of 11
0dev.to
