Elegir un modelo de Claude
El equilibrio entre Opus/Sonnet/Haiku y cómo elegir sin adivinar.
Tokens, contexto y precios
Cuenta los tokens correctamente, max_tokens frente a la ventana de contexto, y cómo estimar el coste.
Tu primera llamada a la API
Instala el SDK, autentícate y haz una llamada real a Claude en Python, TypeScript o cURL.
Streaming y conversaciones multiturno
Transmite respuestas en streaming y gestiona el historial en una API sin estado.
Uso de herramientas / Llamada a funciones
Define herramientas, ejecuta el bucle agéntico y gestiona los resultados.
Code Execution Tool — Sandboxed Bash, Files, and Python
Anthropic's server-side sandbox lets Claude run Bash, edit files, and execute Python — with 5 GiB of RAM, 30-day container reuse, and a 1,550-hour monthly free tier. The three tool versions, what each adds, when it's free, and the file-capture gotcha nobody documents.
Visión, PDF y entrada de archivos
Envía imágenes y documentos, y reutiliza las subidas mediante file_id.
Salida estructurada
Obtén JSON que cumple un esquema y en el que puedes confiar, no 'pide y reza'.
Pensamiento extendido y esfuerzo
Razonamiento adaptativo y el control de esfuerzo: elegir la profundidad según la carga de trabajo.
Effort tuning: 5 levels, model defaults, and the cache trap
The July 2026 effort parameter has five levels — low, medium, high, xhigh, max — and lives inside output_config, not at the top level. It affects tool calls (not just thinking), invalidates prompt cache when changed mid-conversation, and each model has a different recommended starting point. The practical tuning guide.
The advisor tool: Sonnet does the work, Fable does the thinking
The advisor server-tool (beta advisor-tool-2026-03-01) lets a fast executor model consult a stronger model mid-turn. Full field reference, the token-accounting trap most integrators miss, the model pairing matrix, and the exact prompts Anthropic ships in production.
Task Budgets — Advisory Token Caps That Make Agents Finish Gracefully
The March 2026 Messages-API beta gives Claude a token budget for the whole agentic loop — thinking, tool calls, tool results, output — so long-running agents self-regulate and wrap up cleanly instead of running away. How the countdown works, why it's advisory not enforced, and how to size it so it doesn't cause refusal-like behavior.
Almacenamiento en caché de prompts y optimización de costos
Reutiliza un prefijo de prompt estable para reducir costo y latencia, y el detalle que lo arruina.
Message Batches — Async Jobs at 50% Off
Cut cost in half and lift throughput by moving bulk work to the async Batches API — with the gotchas that trip people up.
Mid-Conversation System Messages
Steer a long agent session without blowing up the prompt cache — the new system role you can append after any user turn.
Mid-Conversation Tool Changes
Add and retire tools between turns without invalidating the prompt cache — the Opus 5 beta that fixes the biggest hidden tax on long agent sessions.
Crear agentes con la API
Llamada única vs. flujo de trabajo vs. agente personalizado: el test de decisión y el diseño del bucle.
Agentes gestionados
Bucle de agente alojado por Anthropic: agentes vs. sesiones, entornos, memoria, vaults y despliegues programados (cron).
Managed Agents Memory Stores
The July 2026 beta — server-side persistent memory that mounts into a Managed Agents sandbox, with versioning, audit trail, and redaction.
Managed Agents Session Budgets
The August 2026 beta — hard dollar caps on a Managed Agents session, enforced at public list rates, with the budget_reached stop reason, the one-request overshoot, and the pause-and-resume model.
Managed Agents Domain Restrictions
The August 26, 2026 beta — allowed_domains, blocked_domains, max_content_tokens, and user_location on web_search and web_fetch inside Managed Agents. Format rules, multiagent semantics, mid-session updates, and the url_not_allowed error.
Cowork y equipos de agentes
El espacio de trabajo agéntico de escritorio y la colaboración multiagente como productos.
MCP y conexión a herramientas
Declara servidores MCP en las solicitudes y dónde encaja MCP frente a otros tipos de herramientas.
MCP 2026-07-28: The Stateless Spec
The biggest MCP revision since launch: the session is gone, every request self-describes, and any server instance can answer any call. What actually changed on July 28, 2026, and how to migrate without breaking today's servers.
MCP Apps: Interactive UIs Inside a Tool Call
MCP Apps (SEP-1865) lets an MCP server ship an HTML UI that the client renders inside a sandboxed iframe — with every action still routed through the standard JSON-RPC audit path. What the spec actually says, what to build with it, and what to refuse to build.
MCP Tasks: Long-Running Work Without the Session
The 2026-07-28 stateless MCP spec killed the session — so how do you model a 20-minute CI job, a batch import, or a human approval gate? With the official Tasks extension (SEP-2663). Full lifecycle, wire protocol, migration from the old experimental Tasks API, and the polling/notification patterns that actually work in production.
Playwright MCP: The Deep Practical Guide (2026)
Microsoft's Playwright MCP is now the #1 MCP server in the world — ahead of GitHub and Figma. The bit almost nobody teaches: the default accessibility-snapshot mode is not just faster than vision, it's a completely different automation paradigm. Profiles, opt-in caps, browser-extension mode that attaches to your real Chrome, the token-cost fight against Playwright-as-a-Skill, and the security line you must not cross.
Seguridad, rechazos y planes de respaldo
Gestiona los rechazos con elegancia y distínguelos de los bloqueos del clasificador.
Server-Side Fallbacks & Fallback Credit
The Opus 5 beta that turns a Fable 5 / Opus 5 refusal into a normal answer inside one API call — plus the credit token that stops you from paying the prompt cache twice on the retry.
Errores, límites de tasa y fiabilidad
El mapa de errores, reintentos con backoff, niveles de límite de tasa y migración de modelos.
Memoria y edición de contexto
Da a los agentes memoria persistente y contexto autopodado: la herramienta memory del lado del cliente más la edición de contexto que limpia resultados de herramientas obsoletos para sobrevivir a ejecuciones largas.
Programmatic Tool Calling
Let Claude call your tools from Python inside the code-execution sandbox — cutting round-trips and keeping intermediate results out of context.
The Admin API: automate your Claude org
The operator's guide to Anthropic's Admin API — list members, invite users, run RBAC groups, offboard cleanly. Console + Claude Enterprise, with the seat-pool and SSO gotchas that trip real teams.
Inference Hooks: inline DLP for Claude Enterprise
The operator's guide to Claude Enterprise Inference Hooks — the HTTPS webhook that lets your DLP server allow or deny every prompt across chat, Claude Code, and Cowork, before the model sees it. Full spec, verdict schema, signing, rollout playbook.