4d ago · 11 min read · Most AI agent frameworks share a quiet assumption: the process will stay alive. Set off a multi-step research agent, and the code assumes the LLM API will respond, the network will behave, and your machine will keep running until the job finishes. In...
Join discussion
May 4 · 18 min read · Part 1 of 2 — This article walks through Temporal's non-determinism problem, the Workflow.getVersion() fix, and where that fix hits its limits. Part 2 covers Worker Versioning in production → You pu
Join discussionMay 4 · 10 min read · Why Your AI Agent Dies in Production (And What to Do About It) You deploy an AI research agent. It works perfectly in demos. It searches the web, calls APIs, writes files, loops through 50 documents. Then on day three, the server restarts mid-task. T...
Join discussion
May 4 · 10 min read · Why Your AI Agent Dies in Production (And What to Do About It) You deploy an AI research agent. It works perfectly in demos. It searches the web, calls APIs, writes files, loops through 50 documents. Then on day three, the server restarts mid-task. T...
Join discussionApr 19 · 11 min read · Github repo: https://github.com/SubhanshuMG/agents-as-state-machines The thesis in one paragraph Stop calling them agents. They are state machines that invoke LLMs at certain transitions. The multi-a
Eermastondang71-lang commented
Mar 3 · 9 min read · Temporal.io: Durable Workflow Orchestration for Microservices Distributed systems fail. Networks drop, services crash, deployments restart processes, and databases hit timeouts. The question isn't whether your multi-step business process will encount...
Join discussionMar 3 · 11 min read · Background Job and Workflow Tools: BullMQ, Temporal, and Celery Every non-trivial application eventually needs to do work outside the request-response cycle. Send an email after signup. Generate a PDF invoice. Process a video upload. Sync data with a...
Join discussion
