CodeGuides.io
|
React
React Native
Node.js
Python
Rust
PostgreSQL
Solana
Claude
AI Agents
Go
AI Agents Guide
Perguntas frequentes
Search docs...
⌘K
EN
ES
PT
/
/
Buscar na documentação...
⌘K
Buscar na documentação
Busque em todas as páginas da documentação
AI Agents
/
Tags
/
Explainer
#Explainer
93 pages
Pages tagged
Explainer
across 49 sections.
Protocolos A2A
A2A's Transport Layer: HTTP, SSE, and JSON-RPC 2.0
The Broader Protocol Stack: MCP, A2A, ACP, and WebMCP
What A2A Solves That MCP Doesn't
Arquiteturas de Agente
Multi-Agent Handoff: Specialist Agents Passing Work to Each Other
Plan-and-Execute: Separating Planning from Execution
ReAct: Reasoning and Acting in an Interleaved Loop
The Three Core Agent Architecture Patterns, Compared
Estudos de Caso
What a Case Study Should Capture for Future Reference
CI/CD e Ciclo de Vida
What "Continuous Deployment" Means for a Prompt-Driven System
Regras Fundamentais
Why Fundamentals Rules Prevent Early Agent Project Failures
Loops e Raciocínio
How Context Shapes Every Decision an Agent Makes
Inside the Agent Loop: Perceive, Reason, Act, Observe
Planning vs Reacting: Two Philosophies for Agent Decision-Making
Reasoning Traces: How Agents "Think" Before Acting
Stopping Conditions: How an Agent Knows When It's Done
Observabilidade
Pairing Agent Observability with Infrastructure Monitoring
What Agent Observability Actually Needs to Capture
Confiabilidade
Setting SLOs for Agent Latency, Success Rate, and Cost
Why Agents Fail Differently Than Traditional Services
Regras de Agentes
How Opinionated Rules Prevent Agent Production Incidents
Segurança de Agentes
Never Grant Blanket Shell Access in Production: What to Do Instead
The Principle of Least Privilege Applied to Agent Tools
Memória de Curto Prazo
Short-Term Memory: What an Agent Actually Needs Within One Run
Visão Geral de Casos de Uso
Task Shape Matters More Than Industry When Picking a Use Case
The Four Broad Categories of AI Agent Use Cases
Where Agents Outperform Traditional Automation (and Where They Don't)
Decisões de Arquitetura
Why Agent Systems Need Their Own ADR Discipline
Agentes On-Chain
Key Management for Agent-Controlled Wallets: Fireblocks and Alternatives
Why On-Chain Agents Need Different Guardrails Than Other Tools
Construindo MCP
Anatomy of an MCP Server: Handlers, Schemas, and Transport
Negócios e Pesquisa
Data Analysis Agents: From Spreadsheet to Insight
How Knowledge-Work Agents Differ from Coding Agents
Internal Knowledge-Base Agents with RAG Grounding
Market & Competitive Intelligence Agents
Escolhendo um Framework
Framework-Free vs Framework-Based: When to Roll Your Own
What Actually Differs Between Agent Frameworks
Casos de Uso de Código
Autonomous Bug-Fixing Agents: From Issue to Verified Patch
DevOps Agents: Deployment, Incident Triage, and Runbook Execution
How Coding Agents Changed Day-to-Day Software Development
Test-Generation and Coverage Agents
CrewAI
The CrewAI Mental Model: Roles, Tasks, and Crews
Runtimes Customizados
Why Some Teams Build a Custom Agent Runtime Instead of Adopting a Framework
Ferramentas Customizadas
What Makes an Internal API a Good Agent Tool
Deploy de Agentes
Choosing a Deployment Target for an Agent Workload
Cold Starts and Long-Running Agent Loops: A Serverless Mismatch
Git, Linux e Onboarding
Why Agent Teams Still Need Solid Git and Linux Fundamentals
Human-in-the-Loop
Privilege Rings: Scoping What an Agent Can Do Without Asking
Casos de Uso por Indústria
Financial Services Agents: Fraud Triage, Reporting, and Trading Support
Healthcare Agents: Clinical Documentation and Patient Triage Support
Why Industry Context Changes an Agent's Risk Profile
LangChain e LangGraph
The LangGraph Mental Model: Agents as State Graphs
LlamaIndex
The LlamaIndex Mental Model: Documents, Indexes, and Query Engines
LLMs por Trás dos Agentes
How an LLM's Context Window Bounds What an Agent Can Do
Local & Self-Hosted Models with Ollama for Agent Workloads
Tokens, Pricing, and Why Agent Costs Add Up Fast
Why Model Choice Is a Runtime Decision, Not a One-Time One
Memória de Longo Prazo
Long-Term Memory: What Should Survive Between Agent Sessions
Memory Extraction: Deciding What's Worth Remembering
Conceitos de MCP
MCP Tunnels: Connecting to Private-Network MCP Servers
stdio vs HTTP vs SSE: MCP's Transport Options
What MCP Standardizes and Why It Won the Tool-Connection Wars
Microsoft Agent Framework
From AutoGen and Semantic Kernel to Microsoft Agent Framework 1.0
Governance and Enterprise Controls in Microsoft Agent Framework
Arquitetura Multiagente
Peer-to-Peer Agent Collaboration Without a Central Orchestrator
Why Split One Agent Into Many Specialized Agents
Multimodal e Browser
How Vision Models Extend an Agent Beyond Text
Orquestração No/Low-Code
When Visual Workflow Tools Beat Writing Custom Agent Code
OpenAI Agents SDK
What Native Provider Agent Primitives Give You Over a Framework
Custo e Fallback
How OpenRouter's Provider Fallback Actually Protects Uptime
Fundamentos do OpenRouter
Bring Your Own Key (BYOK): Using Your Own Provider Accounts via OpenRouter
How OpenRouter's Credit and Billing Model Works
How OpenRouter's Unified API Normalizes Different Providers
OpenRouter's Data Policies and Why They Matter for Enterprises
What OpenRouter Actually Is: One API for 300+ Models
Agentes em Produção
Architecting an Agent Around a Model-Agnostic Gateway
Setup e Roteamento
How Model Routing Actually Works Under an OpenRouter Request
Pessoal e Consumidor
Email and Calendar Agents: Triage, Drafting, and Scheduling
Shell-Access Personal Agents: Power and Risk
What a Personal AI Agent Actually Does Day to Day
Why Self-Hosting a Personal Agent Appeals to Privacy-Conscious Users
Prompt Injection
How Prompt Injection Attacks Actually Work
Pydantic AI e Instructor
Why Structured Output Matters More as Agents Get Autonomous
Escala de Agentes
What Actually Bottlenecks an Agent System at Scale
Agentes Self-Hosted
The Self-Hosted Personal Agent Mental Model
Testando Agentes
Why Testing an Agent Differs from Testing Deterministic Code
Uso de Ferramentas
How Function Calling Actually Works Under the Hood
Parallel Tool Calls: When and How Models Call Multiple Tools at Once
Vector DB e RAG
Chunking Strategies That Affect Retrieval Quality
How Vector Search Gives Agents a Searchable Memory
Vercel AI SDK
The Vercel AI SDK Mental Model: Streaming UI Meets Agent Loops
O Que É um Agente
Agents vs Chatbots vs Assistants vs Copilots: What's the Difference
What Actually Makes Software an "Agent"?
What an Agent Can and Can't Do Reliably Today
Related tags
Python
Advanced
Agent Loop
Agent Loops Reasoning
Mcp
Openrouter Fundamentals
Agent Architectures
Agents
Voltar ao topo