ENElie Nehméinelie29.hashnode.dev·13h ago · 36 min readOntology-Based Context Engineering: When RAG Is Not EnoughNote: Originally published on Medium In my previous articles, I discussed Context Engineering and the BMAD method. Today, I want to take it one step further and introduce Ontology-based Context Engin13M
SStatewaveinstatewave.hashnode.dev·6h ago · 6 min readAI agent memory vs RAG — what's the difference?Most teams building on LLMs end up with two patterns in the same codebase: RAG for looking things up in a corpus, and some hand-rolled memory for remembering what the agent has done or what the user h00
HSHaithem Slimiinnightthoughts.hashnode.dev·6h ago · 16 min readHow to Put Boundaries on Your AI AgentOpenClaw Policies for WhatsApp, Telegram, Gmail, and Everything Else This is the second article in a series. The first one, I Turned My Mac Mini Into a Local AI Workstation, covered how to set up the 00
SVShravin Vivekinshravinvivek.hashnode.dev·5h ago · 4 min readWhy the Agent That Ran a Test Shouldn't Grade ItI'm Shravin, and I build TestAutomate, an agentic regression-testing tool that isn't released yet. This is a condensed version of one design decision we made. The full write-up, including when determi00
AGAleksei Grebenkininavgrebenkin.hashnode.dev·7h ago · 7 min readThree Reports, One Break-in: The Hugging Face Incident From Three SidesIn July 2026, software agents built by OpenAI broke into Hugging Face, the platform where the world's open AI models and datasets are published. On 26 August two documents came out at once: OpenAI's 300
HSHaithem Slimiinnightthoughts.hashnode.dev·14h ago · 2 min readThe End of Software Engineering: What the Paper Actually Says (and Why It Walks It Back)A paper with a provocative title landed on arXiv in June 2026. "The End of Software Engineering" sounds like war on the profession. But its argument is more measured than the title suggests. The Core 00
SDSagnik Deyinstop-gate.hashnode.dev·1d ago · 12 min readWhat a frontier coding agent actually does when the tests are wrongEveryone building in this space cites ImpossibleBench: frontier models exploit test cases in a large fraction of runs where the specification and the tests conflict. Far fewer people run a detector ag02A
Ttechpotionsintechpotions.hashnode.dev·1d ago · 7 min readHow to Self-Host an Open Source LLM: A Practical Setup GuideOriginally published at techpotions.com. Learning how to self-host an open-source LLM means trading API convenience for control, and a set of infrastructure decisions you can't afford to get wrong. Un10
NINikhil Ikharinnik-hil.hashnode.dev·1d ago · 9 min readAgents Zero to Hero #1: Building an AI Agent from Scratch with Tool CallingBuilding an AI agent sounds deceptively simple. Call an LLM. Give it a prompt. Get an answer. But that is not really an agent. An LLM becomes an agent when it can decide to take actions, invoke capabi00
CDCoding Dropletsincodingdroplets.com·1d ago · 12 min readAzure OpenAI Content Filter Errors in .NET APIs: Causes and FixesThe first time an Azure OpenAI content filter error hit one of our production .NET APIs, it did not look like a content filter error at all. It looked like a flaky provider: a burst of 400 Bad Request00
