patterns▌

Evidence-based patterns for configuring LLM parameters, based on APOLLO and Godel-Prover research.

Annotation-based and programmatic tool system for LangChain4j agents to execute external functions, APIs, and services. \n \n Define tools using @Tool annotations with parameter descriptions via @P , automatically registered with AI services for LLM invocation \n Supports static tool registration, dynamic tool provisioning based on context, concurrent execution, and immediate-return tools for quick responses \n Includes error handling strategies, tool execution monitoring, memory context integra

Multi-agent architectures distribute work across multiple agent invocations, each with its own focused context. When designed well, this distribution enables capabilities beyond single-agent limits. When designed poorly, it introduces coordination overhead that negates benefits. The critical insight is that sub-agents exist primarily to isolate context, not to anthropomorphize role division.

React UI patterns for loading states, error handling, and async data in components. \n \n Three core patterns: show loading indicators only when data is absent, always surface errors to users, and disable buttons during async operations to prevent duplicate submissions \n Includes decision trees and component examples for skeleton vs. spinner selection, error state hierarchy (inline, toast, banner, full screen), and empty state requirements for all collections \n Covers form submission workflows

Master proven backend architecture patterns including Clean Architecture, Hexagonal Architecture, and Domain-Driven Design to build maintainable, testable, and scalable systems.

Comprehensive testing patterns for Spring Boot applications covering unit, slice, integration, and container-based tests. \n \n Covers four test types with performance targets: unit tests (< 50ms), slice tests (< 100ms), integration tests (< 500ms), and full context tests with Testcontainers \n Includes patterns for Mockito-based unit testing, JPA/MVC slice testing with focused Spring contexts, and REST API testing with MockMvc and WebTestClient \n Demonstrates Spring Boot 3.5+ @S

Standardized MCP server implementation patterns with LangChain4j for extending AI capabilities. \n \n Provides tool providers, resource providers, and prompt template patterns to expose custom capabilities through the Model Context Protocol \n Supports multiple transport mechanisms including stdio for local processes and HTTP for remote servers \n Includes Spring Boot integration, multi-server configuration, and dynamic tool discovery with context-aware filtering \n Implements security patterns

Type-safe AI services in Java using interface-based patterns, annotations, and declarative configuration. \n \n Define AI capabilities as plain Java interfaces with @SystemMessage and @UserMessage annotations, eliminating manual prompt construction and response parsing \n Built-in memory management for multi-turn conversations with per-user or per-session isolation using @MemoryId and configurable chat memory providers \n Tool integration enables AI services to call external functions and execut

Modern SwiftUI patterns for iOS 26+ with MV architecture, state management, and view composition. \n \n Covers @Observable ownership rules, @State / @Bindable / @Environment wiring, and view decomposition best practices for clean, performant UIs \n Includes async data loading with .task , custom ViewModifier styling, environment value patterns, and granular state tracking that only re-renders affected views \n Provides iOS 26+ API updates (scroll edge effects, background extensions, @Animatable

Architects design workloads by integrating platform services, functionality, and code to meet both functional and nonfunctional requirements. To design effective workloads, you must understand these requirements and select topologies and methodologies that address the challenges of your workload's constraints. Cloud design patterns provide solutions to many common challenges.