TFThe Flux Readinthefluxread.hashnode.dev·6h ago · 9 min readHow to Build Autonomous AI Workflows for Enterprise AutomationFor the past several years, enterprise adoption of artificial intelligence was largely defined by passive interaction: employees typing prompts into chat interfaces, generating text summaries, or exec00
DSDA SEINindaseinsblog.hashnode.dev·2d ago · 8 min readDeepSeek Harness Deep Dive (2): Everything Is a Plugin — But What Exactly Is a Plugin?As discussed earlier, a mature Harness needs to handle at least tool execution, Context management, Session persistence, and execution control. But once Agents begin taking on more complex tasks, that00
KMKartik Mehtainwriter.mrmehta.in·4d ago · 8 min readAgents should be Self-ishWhy the next trust primitive on the agentic web isn't a smarter model. It's a passport scan! At 2:00 AM UTC on March 18, 2025, an AI agent with 460,000 followers sent 55.5 ETH, roughly $104,000, to a 20
KMKartik Mehtainwriter.mrmehta.in·Aug 10 · 15 min readSubagents vs A2A: One Is a Pattern, One Is a ProtocolI get asked to compare these two often enough that it is worth writing down properly. The short answer is that subagents and A2A are not competing, and treating them as alternatives leads people to bu20
RRe:zZCinzzc123456.hashnode.dev·Aug 10 · 8 min readWhere the Agent Skills ecosystem actually stopsThree of the twenty fastest-growing GitHub repos in the last week of July 2026 were agent skills. graphify added roughly 4,900 stars in seven days by turning codebases, docs, and PDFs into a queryable00
LWLeo Wanginleo-wang.hashnode.dev·Aug 5 · 2 min readThe Prompt Is Not a Spell — It's Structured Context Injection "10 magic openings that boost GPT's IQ by 50." "Add this one sentence and your output quality jumps 200%." That's the typical content on Xiaohongshu, Zhihu, and paid prompt communities — and 95% of th00
MMaverickinjyanshu.hashnode.dev·Aug 4 · 14 min readAPI vs MCP: Interoperability Trade-offs for AI SystemsThe Core Question When building agentic AI systems, one of the earliest architectural decisions you'll face is: How do my agents and LLMs talk to the outside world — through REST APIs, or through MCP01C
SMSafiyev Maratinheyagent.hashnode.dev·Aug 3 · 3 min readI Built an Open-Source AI Agent That Actually Controls Your ComputerAI agents are everywhere in 2026. Most of them can answer questions, generate code, or automate simple workflows. But once you ask them to interact with a real computer—browsers, desktop applications,00
PGPrasad Gaikwadinblog.prasadgaikwad.dev·Aug 2 · 6 min readConversation Memory with LangChain4j: Keeping Context Across TurnsIn our previous post, we built a simple command-line chat with LangChain4j. It worked, but there was one big limitation: the model had no memory. Every question was answered in isolation, as if the co00
MMMarrouchi Mohamedinblog.hexabot.ai·Jul 31 · 8 min readHexabot 3.4.0: rebuilding RAG around helpers and the databaseHexabot 3.4.0 is now available. It brings a more responsive admin experience, workflow and agent reliability fixes, improved graph layouts, and a substantial round of dependency updates. At the center00
