The event-driven pattern means an assistant can sit dormant instead of polling a model continuously, cutting cost without cutting capability. Builders of proactive assistants, notification bots, and workflow automation should study how inbox, timer, memory, permissions, and an outbound queue combine into a safe loop. The advice to start with low autonomy and human approval on important actions is a practical guardrail for anyone deploying agents against real user accounts.
#developer tutorials
5 stories · 2 in 7 days · 2 in 30 days
Stories, products and papers tagged "developer tutorials", newest first.
Nov 14
Anthropic Explains Five Building Blocks of Always-On AI Agents
Nov 10
Chinese contentLangChain Academy 讲解评估驱动开发:三步改进智能体
LangChain 团队把“怎么让智能体越改越好”拆成了三步评估流程,还配了完整博文。自己搭智能体的开发者照着做,能避免改动后效果退化的问题。
Oct 15
Chinese contentxAI 发布官方 Cookbook,Grok API 教程与示例代码汇总
xAI 把 Grok API 的教程和示例代码汇成了官方 Cookbook,想接 Grok 做开发直接翻这本照着抄就行。
Oct 10
Sep 23
LangChain and TypeSafe host live session on building agent harnesses
Agent harnesses are the runtime layer that turns LLM calls into reliable production agents, so seeing one assembled live with a specific toolchain exposes patterns you can copy. Developers building agents should sign up on events.langchain.com and attend, since the walkthrough covers architecture choices rather than basic prompting.