Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: Temporal
Agent Frameworks Reason, Temporal Survives: Durable Execution for Agents
LangGraph, CrewAI and AutoGen orchestrate LLM calls but not crashes or week-long waits. How Temporal's durable execution fills that gap, and when it's overkill.
11 min readHarness, Loop, Graph: Three Layers Behind Most Production Agent Failures
Production agent failures rarely come from the model. Separate the tool harness, the loop's stop condition and the LangGraph graph topology, each with an owner.
24 min readReplay-Safe Agents: Keeping LLM Calls Out of the Workflow With Temporal
Why an agent that crashes mid-run must not re-fire its LLM: activities as a non-determinism boundary, replay mechanics, heartbeats, retries and stateless graphs.
16 min readChoosing an Agent Framework by Workload Shape: Six Axes and a Decision Path
Pick an agent framework by workload shape: LangGraph, CrewAI, AutoGen, Temporal or none, judged on determinism, lifetime, idempotency, audit and cost.
11 min readLayered Retries for Production AI Agents
Layered retries for production AI agents: LLM call backoff, tool-error recovery, checkpoints and durable workflows, so flaky APIs and crashes don't kill runs.
10 min readSeven Native JavaScript Features That Replace Utility Dependencies
How Temporal, using declarations, Map upserts, Math.sumPrecise, iterator helpers, Set methods and Promise.withResolvers remove common JavaScript boilerplate.
9 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.