Most Popular
3,528 documents
An Image is Worth 16X16 Words: Transformers for Image Recognition at Scale
Introduces the Vision Transformer (ViT) that applies a standard Transformer directly to image patches for classification, outperforming CNNs when pre-trained at scale.
Building SupportX AI Assist: A Multi-Agent IT Support System
Describes building a multi-agent IT support system with AutoGen, Azure AI Search, and Gemini embeddings for instant issue resolution and automatic escalation.
Late Chunking Strategy
Explains late chunking for RAG: embed entire documents first, then split into context-aware chunks to preserve cross-references.
OCI Retrieval-Augmented Generations (RAG) with Generative AI Agents Service
Walks through setting up OCI Generative AI Agents with Object Storage, OpenSearch, or Autonomous Database 23AI for RAG chatbots.
🏠 Local AI Vision Support - Ollama + LLaVA Integration
Adds a free local AI vision provider (Ollama + LLaVA) alongside OpenAI GPT-4o, with a UI toggle, multi-image upload, and structured ad extraction for a screenshot intelligence feature.
Cat Mode Protocol
Forces the agent to roleplay as a domestic cat, rejecting all complex tasks and using only cat sounds and actions.
Partie 2 : Pipeline RAG
Guides a student through forking, cloning, Dockerizing, and running a RAG chatbot with Streamlit, ChromaDB, and Google Gemini.
RWE Inclusion/Exclusion Optimizer
Defines a multi-agent system that converts clinical trial inclusion/exclusion criteria text into executable SQL cohort queries over real-world data.
T20_enhancement_proposals
Proposes 7 categories of enhancements for the T20 multi-agent framework, including new agents, model integration, planning, and debugging.
Windsurf Rules Support
Documents how to create, install, publish, and convert Windsurf AI editor rules using the PRPM package manager.
SunCube AI - Comprehensive Documentation
Documents a React/TypeScript EduTech platform's architecture, PostgreSQL migration, and development workflows for CTET exam prep.
Content Brief Template
Provides a structured template for planning SEO-optimized content, covering keyword strategy, SERP analysis, and promotion.
SECURITY IN ORDERS OF DIFFICULTY
Presents a 55-level security hardening checklist from basic password hygiene to abandoning the internet entirely.
On-Call Policy
Defines a weekly on-call rotation, escalation matrix, paging procedures, and shift handoff process for engineering teams.
Journey from Concept to Code: Transforming Cursor into a Devin-like AI Assistant
Documents the creation of aicode.cursorrules, a set of rules that turns Cursor/Windsurf into a Devin-like AI assistant with automated planning and self-evolution.
Cursor Development Environment
Documents a Docker-based dev container setup with test commands and OpenClaw agent configuration for the ClawDrive project.
RFC-053: Schematized Topic-Based Microservice Pipelines
Proposes a Prism pattern for discovering, tracing, debugging, and testing Kafka topic-based microservice pipelines with schema-aware tooling.
ppx_minidebug CLI Documentation
Documents 20+ CLI commands for exploring ppx_minidebug trace databases, including search, navigation, export, and interactive TUI modes.
Code Span Semantic Chunking Executive Summary
Recommends an AST-driven chunking strategy for code retrieval, preserving function/class boundaries to improve precision and reduce token waste.
Cross-ISA Semantic Code Embedding: A Complete Implementation Blueprint
Describes how to build a cross-ISA binary embedding system using IR lifting and contrastive learning, with architecture, training, and deployment details.
UI Preview Guide
Lists six ways to preview UI components locally, including a dedicated mock-data preview page and optional Storybook setup.
🎯 PrizmAI Features - Complete Guide
Documents 12 advanced AI features for project management, including explainability, coaching, burndown charts, and conflict detection.
GitHub Operations
Maps 20+ GitHub API operations to MCP tool calls for repository, issue, PR, workflow, and security management.
coding: utf-8
Collates GPT-4.1 prompting tips from internal testing, covering agentic workflows, long context, chain of thought, and instruction following.