Single Agent
A single agent receives a goal or message, consults its context, and produces an answer or action. This is the smallest useful unit in the catalog.
Pattern catalog
Encuentra el agentic pattern correcto
Explora los chapters generados como catálogo. Elige el pattern por decisión técnica y revisa tradeoffs, failure modes, evals y production guidance.
Agent Loop
The agent loop turns a model call into an agent: observe state, decide the next action, act, evaluate the result, and stop when the goal is complete or a limit is reached.
Goals and State
Goals define success; state records progress. Together they make agent work resumable, inspectable, and easier to evaluate.
Tool Use
Tool use gives an agent controlled access to external capability such as calculators, search, databases, files, code execution, APIs, or business systems.
Structured Output
Structured output constrains model responses to typed data that software can validate and consume.
Planning and Execution
Planning separates deciding what to do from doing it. The planner creates steps; the executor runs them, reports progress, and handles errors.
ReAct
ReAct alternates reasoning and acting. The agent reasons about current state, takes an action, observes the result, and repeats.
Reflection
Reflection asks an agent or evaluator to inspect prior output and identify concrete improvements.
Evaluator-Optimizer
Evaluator-Optimizer pairs a generator with an evaluator. The generator proposes; the evaluator scores; the optimizer revises or stops.
Self-Improvement
Self-improvement uses feedback from prior runs to improve future runs through reviewed changes to prompts, tools, retrieval, policies, tests, or skills.
Self-Healing Workflows
Self-healing workflows detect failed steps and recover through retry, fallback, re-planning, or escalation.
Context Engineering
Context engineering controls what the model sees: instructions, state, retrieval results, tool documentation, memory, examples, and prior messages.
Memory-Augmented Agent
Memory gives an agent continuity, but it also creates a durable trust boundary.
Long-Term Episodic Memory
Long-term episodic memory stores events: what happened, when, who was involved, and why it mattered.
Semantic Recall and RAG
Semantic recall retrieves relevant material by meaning rather than exact keywords. RAG injects retrieved material into context before generation.
Working Memory
Working memory is compact, typed task state the agent can update and consult during a run.
Knowledge-Bound Agents
Knowledge-bound agents ground answers and actions in approved sources, policies, and citation rules.
Skills
Skills package procedural knowledge as discoverable, versioned folders of instructions, references, scripts, templates, assets, and tests.
MCP-first Tool Use
MCP-first tool use separates tool capability from agent logic through manifests, validation, invocation, and structured results.
A2A Agent Interoperability
A2A makes agents discoverable and callable across process, team, runtime, and vendor boundaries.
Secure Agent Communication
Secure communication protects messages between agents with authentication, integrity, confidentiality, and policy checks.
Human Approval Gates
Human approval gates pause execution before sensitive, expensive, destructive, or externally visible actions.
Task Delegation
Task delegation assigns bounded subtasks to specialized workers and combines their outputs.
Supervisor / Worker
Supervisor/Worker centralizes goal ownership, task state, routing, and quality gates while workers perform bounded specialist work.
Debate and Consensus
Debate and consensus use multiple independent proposals, critiques, votes, or rankings before producing a final answer.
Parallel Agents
Parallel agents run independent work concurrently, then merge results through a fan-out/fan-in control point.
CrewAI Flows and Crews
CrewAI Flows own state and execution order. Crews group specialized agents that collaborate on delegated work inside the flow.
Durable Workflows
Durable workflows make agentic systems resumable and auditable by owning retries, checkpoints, approvals, compensation, and long-running state.
Observability and Evals
Observability records what happened. Evals decide whether behavior is good enough. Release gates decide whether a change is allowed to ship.
Policy Enforcement
Policy enforcement constrains what the agent may say or do through permissions, data-access rules, business rules, safety rules, and escalation.
Event-Triggered Agents
Event-triggered agents run in response to webhooks, queues, schedules, or domain events.
Mastra Runtime
Mastra is a TypeScript runtime pattern for applications that need agents, workflows, tools, memory, evals, and observability in one framework.