agents▌

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

Build text and voice agents with tools, multi-agent handoffs, guardrails, and human-in-the-loop patterns. \n \n Supports text agents, realtime voice agents with WebRTC, and multi-agent workflows with automatic delegation via handoffs \n Define tools using Zod schemas for type-safe parameter validation; includes structured output support for predictable JSON responses \n Implements input/output guardrails for safety validation, human approval workflows for sensitive operations, and streaming supp

Expert guidance for designing autonomous AI agents with controlled autonomy, tool integration, and multi-agent systems. \n \n Covers core agent patterns: ReAct loops for step-by-step reasoning, Plan-and-Execute for task decomposition, and dynamic tool registries for flexible capability management \n Addresses critical failure modes including infinite loops, tool overload, memory bloat, and fragile output parsing with specific mitigation strategies \n Balances agent autonomy with oversight, helpi

Skill by ara.so — Daily 2026 Skills collection.

Comprehensive platform for building, deploying, and managing continuous AI agents through a visual interface or development toolkit.

Build production-ready conversational AI voice agents with ElevenLabs Platform. \n \n Supports React, React Native, Swift, and JavaScript SDKs with dashboard or CLI-based agent configuration \n Add client-side and webhook-based server tools, upload knowledge bases for RAG, and configure voice, LLM, system prompt, and first message \n Includes signed URL authentication pattern, agent versioning for A/B testing, and dynamic variable injection for user context \n CLI provides init, deploy, test, an

Production AI agent patterns using Trigger.dev's durable execution for orchestration, parallelization, routing, and self-refinement workflows. \n \n Five core patterns: prompt chaining with validation gates, routing to appropriate models, parallel LLM execution, orchestrator-worker fan-out/fan-in, and evaluator-optimizer self-refining loops \n Includes typed batch execution across multiple tasks, recursive self-calls with feedback, and error handling with per-task result inspection \n Integrates

Architectural patterns and guardrails for building reliable autonomous agents that start constrained and earn autonomy through proven reliability. \n \n Covers three core agent loop patterns: ReAct (alternating reasoning and action), Plan-Execute (separated planning and execution phases), and Reflection (self-evaluation and iterative improvement) \n Emphasizes guardrails-first approach with hard cost limits, step count reduction, and least-privilege API access to prevent runaway behavior \n Iden

Orchestrate subagents, plan multi-step tasks, and require human approval for sensitive operations. \n \n Delegate work to specialized subagents via the task tool; custom subagents support isolated tool sets and system prompts, while the default \"general-purpose\" subagent inherits main agent configuration \n Plan and track complex workflows with write_todos , organizing tasks across pending, in-progress, and completed states; requires a thread_id for persistence across invocations \n Implement

Build stateful AI agents on Cloudflare Workers with persistent state, RPC methods, scheduling, and workflow orchestration. \n \n Core features include SQLite-backed state management, callable RPC methods via @callable() , one-time and recurring task scheduling, and durable multi-step workflows \n Supports MCP server integration (both client and server modes), email routing with secure replies, and streaming chat with resumable streams on disconnect \n Includes React hooks ( useAgent , useAgentCh