DDhwanit Shah2h ago · 10 min readDecision Models: AI That Picks Instead of WritesIf you've built anything with an LLM, you have probably written a prompt like this: "Read this support ticket. Reply ONLY with valid JSON: {"category": "billing" | "bug" | "feature"}. No explanation.dhwanitisshah.hashnode.dev
PPugazhenthi Elangovan1h ago · 12 min readWhy Neural Network works ?Neural Network Natural Language / Image / Audio Processing are rising as major workloads along with traditional computations. So, Neural network architectures getting embedded into all software eitherscalability.hashnode.dev
AAmit Shukla40m ago · 5 min readYour own private ChatGPT: Open WebUI and Ollama with one Docker Compose fileEvery time you paste a client contract, a log file or a piece of internal code into a cloud chatbot, it leaves your machine. Sometimes that is fine. Often it isn't, and you only realize it after you pamitshuklabag.hashnode.dev
MMemorySync55m ago · 6 min readAdd persistent memory to a LlamaIndex agent (Memory, memory blocks and a retriever)Disclosure: I'm Mohammed, founder of MemorySync. I drafted this article with AI assistance and reviewed it for accuracy against the official MemorySync and LlamaIndex docs. The code is adapted from thmemorysync.hashnode.dev
MMemorySync56m ago · 7 min readPersistent memory for CrewAI 1.x: keep crew memory across runs and redeploysDisclosure: I'm Mohammed, founder of MemorySync. I drafted this article with AI assistance and reviewed it for accuracy against the official MemorySync and CrewAI docs. The code is adapted from the domemorysync.hashnode.dev
BBlu Parrot Ventures9h ago · 6 min readWhat Is Agentic AI? A Practical Guide for B2B EnterprisesAgentic AI is one of the most overused terms in enterprise technology, and one of the least clearly explained. This guide explains what agentic AI is, how AI agents differ from chatbots and scripts, wbluparrot.hashnode.dev
NNeeraj Sharma2h ago · 9 min readNotion's Router Claims 90% Cheaper Agents. The Math Needs a 90/8/2 Traffic MixOn 19 October Notion shipped the sixth generation of the harness behind Notion Agent and Custom Agents. The headline numbers: a single task can now run for more than 24 hours, up from five minutes, anaxionry.hashnode.dev
AAlisa Hester2h ago · 17 min readWhat Is LFM2.5-24B-A2B, and Can It Run Your Agent Locally?Liquid AI released LFM2.5-24B-A2B on October 13, 2026, calling it "a 24B-parameter reasoning model with just 2B active parameters, built for fast, private agents on-device." If your product has a locaekline.hashnode.dev
CCrypto Money Maker3h ago · 7 min readA 30-line safety gate: scan every web page your agent reads for prompt injectionDisclosure: we built both services used here, WebRead (URL to Markdown) and InjectScan (prompt-injection scanner), and paid calls go to our own wallet. We're Crypto Money Maker, a builder project run cryptomoneymakr.hashnode.dev
YYong Yu3h ago · 7 min readOpenAI Decisions API Is GA: First /v1/decisions Shape, Free Output Tokens, and When to Prefer It Over ResponsesAttributed compile + one small offline smoke testPrimary sources (OpenAI, 2026-10-22): Build more responsive apps with the Decisions API (OpenAI blog), Decisions (developer guide), Decisions API is noyongboyu.hashnode.dev
