Tag
ContextWeave is a new longitudinal benchmark that evaluates whether recalled memory improves downstream agent performance in realistic office-work streams, using privacy-preserved multi-month workflows of 14 participants to create 1,005 executable tasks.
The author argues that AI is shifting from answering questions to autonomously performing tasks, marking the start of an 'AI Agent' era that will change how software is built.
Coze Studio is an all-in-one visual development tool for building AI agents, apps, and workflows using no-code/low-code approaches, with support for plugins, knowledge bases, and integration with services like OpenAI and Volcengine.
Keystroke is a product for building powerful AI agents and workflows.
A practical guide to AI agents, workflows, and modern application practices, covering evaluation frameworks, context engineering, and team redesign for AI adoption.
The article compares ChatGPT and Claude for data science workflows in 2026, noting that both models now rely on native Python execution for calculations. ChatGPT excels in raw data processing and statistical modeling, while Claude dominates interactive visualization and large-context integration.
Screencap turns your team's real workflows into AI training data.
The author reflects on building an open-source n8n workflow repository that has evolved into a community-driven effort to document the engineering behind AI workflows, including trade-offs and design decisions.
Genkit is an open-source framework that provides unified model APIs, structured workflows, and multi-language SDKs to simplify building full-stack AI applications.
The article argues that the true value of enterprise AI lies in agentic workflows rather than chatbots, suggesting a shift in focus.
A 14-step roadmap for transforming linear multi-agent workflows into efficient graph architectures using Claude Code's dynamic workflows, emphasizing data-dependent parallelism and contract-based node design.
This paper investigates whether agentic mechanisms such as reflection and memory lead to controllable improvements over fixed LLM workflows for information extraction from scholarly PDFs, using conference-paper dataset extraction as a testbed.
A reflective article questioning whether anyone has successfully implemented multi-agent AI workflow orchestration without resorting to makeshift solutions.
This article discusses the growing need for multi-agent orchestration in AI coding workflows, highlighting several tools like AutoGen, Claude Code, and CrewAI that enable agents to collaborate, coordinate, and share information to handle complex tasks beyond manual management.
The article discusses how AI transformation in the enterprise requires changing underlying workflows and deploying agents against business processes, rather than just rolling out tools to end users. It emphasizes deep domain expertise, data organization, and comprehensive evaluations for ROI.
A community discussion asking for real-world, production-grade automations, AI agents, or feedback loops that solve day-to-day problems, excluding one-off prototypes.
Noofy is an open-source app that simplifies complex ComfyUI workflows by turning them into easy-to-use dashboards.
An open-source workspace designed for AI agents and workflows, facilitating development and integration.
Peter Gostev compares Fable and GPT-5.6-Sol, describing Fable as more intelligent and eloquent but less reliable, while GPT-5.6-Sol is a diligent workhorse that excels at executing tasks and maintaining code patterns. He provides detailed observations on UI, writing, robustness, and other features.
Swarm is a Swift framework for building agentic workflows and multi-agent systems, with type-safe tool calling, durable checkpointing, and support for multiple LLM providers.