Tag
This article provides an in-depth analysis of the popular Forward Deployed Engineer (FDE) role, emphasizing that the AI model itself is not a moat—the real competitive edge lies in how models are deployed into real business workflows—and offers a 30-day path to building FDE capabilities.
Screenpipe is an open-source, local-first tool that records your work and converts it into searchable memory and SOPs for AI agents, enabling personalized automation.
User shares the WorkBuddy tool, which automatically extracts highlighted content from WeChat Reading and writes it into Markdown documents, eliminating the manual copy-paste steps into Obsidian.
This thread describes a method to reduce cognitive load in Obsidian by automating language learning workflow using Lineage to map grammatical relationships as a graph, cutting study time from 45 to 10 minutes per session.
A startup founder asks the community which AI agents they pay for and why, seeking real-world use cases beyond the hype.
The author shares a personal experience of using harness engineering and free NVIDIA NIM endpoints to build AI agents capable of automating complex multi-step workflows, such as creating AI video series and hotel booking systems, suggesting that web crawling services can be replaced by free frontier models.
A tool that records repetitive tasks via screen recording and compiles them into reusable agent skills following the agentskills.io standard, shipping as an MCP server for cross-platform use.
A detailed tier list ranking no-code AI agent builder platforms from S to D tier, comparing capabilities like multi-agent handoff, compliance, and ease of use.
A tip for using Claude Code: paste an article into the session and instruct the AI to audit your installed skills, remove duplicates, and install better replacements, thereby optimizing context window usage.
An open-source MCP workflow app that can improve itself using its own capabilities, with instructions for using it in your own projects.
LemonLime is a tool that automates existing workflows with a single prompt.
This blog post by Lilian Weng explores the concept of recursive self-improvement in AI, focusing on how harness engineering—the system surrounding base models—enables automation and improvement of AI agents through workflow design and evaluation.
A B2B SaaS company explains their stack for converting trial users, using an AI agent (Aimdoc AI) to handle inbound and trial setup, combined with a single human email and automated feedback loops that ship fixes before trial ends.
Lilian Weng's blog post explores the concept of harness engineering as a key component for recursive self-improvement in AI systems, discussing design patterns, workflow automation, and the analogy to operating systems.
The author critiques AI meeting notes for generating summaries that don't automate follow-up actions, and praises a desktop app that pushes action items into tools like Linear and Gmail.
The article describes a fundamental shift in AI from chatbots to autonomous AI workers that deliver outcomes, transforming hardware, software, developer roles, product management, search, and pricing models.
A masterclass guide on setting up Hermes Agent as a self-improving operating system for agent workflows, covering skills, tools, memory, and automation loops to turn the agent into a compounding productivity system.
Detailed introduction to the most practical prompt engineering tips before Fable5 goes offline, including letting the model run experiments autonomously, optimizing workflows, and reducing token consumption through subagent allocation, along with other practical experiences.
shadcn released the Agent Skill project improve, which has high-cost models perform code auditing and planning while low-cost models execute, forming an installable, orchestrated system with an execution closed loop.
Superpowers 6 open-source project shows that AI can not only write code but also autonomously optimize development workflows (such as auditing, merging tasks, reducing waste). This marks the beginning of AI managing its own workflow, more rigorously than human managers. The article emphasizes that an honest evaluation system (eval) is key to avoiding self-deception.