implementation▌

Complete Retrieval-Augmented Generation systems with LangChain4j for knowledge-enhanced AI applications. \n \n Document ingestion pipelines with configurable chunking, metadata management, and embedding generation using OpenAI or custom embedding models \n Vector search and content retrieval with filtering, re-ranking, and configurable similarity thresholds for precise context matching \n RAG-enabled AI services that automatically inject retrieved context into chat models, with support for multi

Convert Notion specs into linked implementation plans, tasks, and progress tracking. \n \n Automates the workflow from spec discovery through task creation: search and fetch specs, parse requirements, generate implementation plans, and create tracked tasks in Notion. \n Includes templates for quick vs. full implementation plans, task creation patterns, and progress update cadences to match project scope. \n Provides reference guides for requirement extraction, task sizing (1–2 day chunks), depen

Complete reference for implementing Prisma v7 driver adapters with transaction lifecycle, error mapping, and type conversion details. \n \n Covers four required interfaces: SqlDriverAdapter , Transaction , SqlMigrationAwareDriverAdapterFactory , and SqlQueryable , with full method signatures and lifecycle requirements \n Transaction commit() and rollback() are lifecycle hooks only; Prisma sends SQL via executeRaw , not these methods \n Includes argument mapping (string→int/bigint/float, base64→b

Implement rate limiting and throttling mechanisms to protect your services from abuse, ensure fair resource allocation, and maintain system stability under load.

Build knowledge-grounded LLM applications with vector databases, semantic search, and retrieval strategies. \n \n Supports six vector database options (Pinecone, Weaviate, Milvus, Chroma, Qdrant, pgvector) and six embedding models optimized for different use cases and providers \n Covers five advanced retrieval patterns: hybrid search combining dense and sparse retrieval, multi-query generation, contextual compression, parent document retrieval, and HyDE (hypothetical document embeddings) \n Inc

Update implementation plan files with new requirements for features, refactoring, or infrastructure changes. \n \n Generates machine-readable, deterministic plans structured for autonomous execution by AI agents or humans \n Enforces atomic phases with measurable completion criteria, parallel-executable tasks, and explicit file paths and function names \n Requires strict adherence to a mandatory template with front matter, requirements, implementation phases, alternatives, dependencies, affected

Industry-standard authentication and authorization patterns for building secure, scalable access control systems. \n \n Covers JWT (with refresh token flow), session-based, and OAuth2/social login strategies with production-ready code examples \n Includes role-based access control (RBAC), permission-based authorization, and resource ownership validation patterns \n Provides password hashing with bcrypt, rate limiting, and security best practices including token expiration and secure cookie flags

Deploy and configure a service mesh to manage microservice communication, enable advanced traffic management, implement security policies, and provide comprehensive observability across distributed systems.

Detailed feature implementation plan generator following Epoch monorepo conventions. \n \n Generates comprehensive markdown implementation plans with system architecture, database schema, and API design specifications \n Includes Mermaid diagrams for system architecture, entity relationships, and component hierarchies with shadcn/ui integration \n Covers frontend component structure, state management patterns, backend service design, and deployment strategies \n Outputs structured plans to /docs

Combine vector and keyword search for improved retrieval in RAG systems and search engines. \n \n Provides four fusion methods: Reciprocal Rank Fusion (RRF) for general use, linear combination for tunable balance, cross-encoder reranking for highest quality, and cascade filtering for efficiency \n Includes production-ready templates for PostgreSQL with pgvector, Elasticsearch with dense vectors, and custom Python pipelines with parallel search execution \n Handles score normalization, metadata f