Tag
作者提出评估 AI agent 使用水平的新视角：能否在并行运行多个 agent 会话的同时仍掌握工作全局。文章强调任务边界、看板状态、交付约定以及定时任务可见性的重要性，指出代理数量翻倍若带来翻倍的监督和整理成本，说明工作流仍需改进。
A design checklist of five failure cases to test before trusting multi-agent coding workflows: post-review requirement changes, stale worker claims, lost external write responses, approval scope drift, and restart without conversation context. The author frames these as tests to distinguish 'a run ended' from 'this result was accepted against the current task' while building Backplane.
A practitioner asks the community how to handle crashes, retries, and runaway loops in long-running AI agent workflows without double-paying for model calls, and what orchestration tools people use in production.
Flowise is an open-source generative AI development platform that provides visual builders for creating AI agents and LLM workflows, with features like agentflow orchestration, integration nodes, and flexible deployment.
pi-workflow is a workflow orchestration tool designed for the Pi AI assistant, enabling it to execute multi-step, repeatable workflows, including deep research, code review, specification check, and impact assessment. It defines workflows as JSON stage graphs and supports multiple execution modes.
Mistral Devs published a tutorial on building a medical document processing workflow using Mistral OCR, Agents, and Workflows, including a human-in-the-loop step for low-confidence classifications.
A developer asks for advice on building a reliable company OS where AI agents and humans collaborate in production, focusing on long-term memory, workflow state, and agent handoffs. They share their current tool stack and question whether RAG, event sourcing, or custom memory systems are the missing piece.
Evo ported its autoresearch loop onto Anthropic's dynamic workflows in Claude Code, moving orchestration from in-context memory to deterministic JavaScript, solving long-horizon instruction adherence and enabling self-evolving workflows.
OpenSquilla is an open-source, locally runnable AI agent that uses MetaSkill technology to automatically organize multiple skills into workflows and achieve cross-vendor intelligent model routing, significantly reducing usage costs.
Discusses the conversational AI copilot approach for video creation, using Higgsfield supercomputer and Invideo Agent One as examples, and questions whether this orchestrated workflow is more valuable than using underlying models directly.
Google Antigravity 2.0 is a desktop app for orchestrating multi-agent AI workflows, allowing users to manage and coordinate multiple AI agents from a single interface.
Sim is an open-source platform that enables building and orchestrating AI agents with over 1,000 integrations and large language models, offering a visual workflow builder and copilot assistance.
The author shares a browser-based tool that reverse-engineers enterprise AI agent architectures from companies like Lemonade and CrowdStrike into runnable visual templates. These templates allow developers to explore complex multi-agent workflows for insurance, manufacturing, cybersecurity, education, and retail without coding.
Friday Studio is an open-source agent runtime that compiles natural language workflows into explicit, version-controlled YAML state machines. It allows developers to build AI agents via chat but ship them as stable configuration files for reliable production use.
A developer seeking recommendations on advanced AI workflow orchestration tools and patterns, including LangChain, LangGraph, and AWS Step Functions, to build more robust and future-proof systems.
Prefect is an open-source workflow orchestration framework for building and automating data pipelines in Python.
DataTalksClub is offering a free 9-week data engineering zoomcamp course covering containers, orchestration, data warehousing, analytics, batch and streaming processing.