Your cart is empty
Add prompt packs to continue
Master the future of business automation with our definitive collection of AI Agent prompts. This resource has been meticulously designed for prompt engineers and solutions architects looking to deploy high-performance autonomous systems using cutting-edge technologies such as Claude, GPT-4, n8n, and CrewAI. Each instruction is optimized to maximize operational efficiency and accuracy in autonomous decision making. From multi-agent orchestration to deep integration with messaging ecosystems like WhatsApp and Telegram, this collection provides the logical frameworks needed to build RAG-powered assistants, automated sales pipelines, and 24/7 customer support systems. Elevate your technical capabilities and transform manual processes into intelligent, scalable, results-oriented workflows with the most complete guide on the market.
100 resources included
He acts as a Senior Automation Architect with a specialty in n8n and distributed systems. Your goal is to design a robust, scalable and modular error handling architecture for a complex workflow that uses AI agents. The design must contemplate the capture of exceptions both at the individual node level and at the global workflow level through an 'Error Trigger'. The solution should enable automatic classification of faults (network errors, syntax errors, API rate limits, or model hallucinations) and execute corrective actions in real time. For the logical structure in n8n, use an 'Error Trigger' node that captures [Workflow_ID], [Error_Message], [Node_Name] and [Timestamp]. This information must pass through a transformation node (Code Node) that applies data cleaning using JavaScript to extract the most relevant metadata. Subsequently, it integrates an AI node that analyzes the 'stack trace' of the error and determines if it is a transient error that allows an automatic retry (Retry) or if it requires immediate human intervention based on the criticality of the [Nivel_Prioridad] process. The flow must include conditional branches (If Nodes) to manage the notification path. If the error occurs in a critical [Nombre_Aplicacion] backend process, you should fire a webhook towards [URL_Sistema_Alertas] and send a structured message to Slack/Discord with a 'Manual Re-Run' button. If the error is minor, it should be silently logged to an external database such as [Herramienta_Base_Datos_Logs] for later trend analysis. Ensure that the prompt for the diagnostic AI agent includes instructions to avoid brainstorming solutions and to simply identify the specific HTTP error code or code exception. Finally, it implements a 'Circuite Breaker' logic to avoid infinite retry loops. If a node fails more than [Numero_Maximo_Reintentos] times, the flow must change the task status to 'FAILED' in the status management system and notify the technical administrator. The expected end result is a configuration JSON or a detailed technical description of each node necessary for a mid-level developer to replicate this resiliency system on n8n unambiguously.
Acts as a Senior Systems Architect specialized in the CrewAI framework. Your mission is to design and execute a multi-agent orchestration for [PROJECT_OR_MAIN_OBJECTIVE]. You should establish a "Process.sequential" configuration where the flow of information is strictly unidirectional and cumulative, ensuring that each agent receives the complete, sanitized context of the previous step before starting its execution. The success of this synchronization depends on the precision of the hand-offs between tasks. The first agent is [INVESTIGATOR_AGENT_NAME]. Its fundamental role is to extract raw data and conduct exhaustive research on [RESEARCH_TOPIC]. Your output should be a structured technical report that will serve as the single source of truth for the next link in the chain. This agent is prohibited from making creative inferences or skipping validation steps; Its approach is purely analytical, fact-based and geared toward collecting solid evidence. The second agent in the sequence is [STRATEGIC_AGENT_NAME]. This agent will receive the detailed report from the first agent and must transform it into [INTERMEDIATE_DELIVERSABLE_TYPE]. Your critical capacity is essential to identify patterns, risks and opportunities that were not explicitly mentioned in the research phase, but that are logically derived from the data provided. It should act as a value-added bridge, synthesizing complexity into actionable plans. The third and final agent is [ENDER_AGENT_NAME]. Your task is the consolidation and final refinement of the entire workflow. You must take the strategy produced by the second agent and polish it so that it meets the quality standards of [DESIRED_STYLE_OR_TONE]. Its primary objective is to ensure that the final product is cohesive, does not present redundancies with respect to previous phases and responds directly to the user requirements originally defined. For the technical configuration of this Crew, use the following mandatory directives: set 'verbose=True' to monitor agents' Chain of Thought in real time, enable 'memory=True' so that historical context is maintained consistently during sequential execution, and implement the 'Sequential Process'. Each defined task must include a detailed description of the 'expected_output' to avoid any ambiguity in the transfer of data between the agents involved. Finally, it generates the configuration code or detailed simulation of the entire workflow. It includes the definition of specific tools for each agent, such as [LIST_OF_REQUIRED_TOOLS], and ensures that interactions are managed logically. The result should be a robust orchestration structure, ready to be deployed in a production environment where precision and synchronization of sequential tasks are critical.
Acts as an Expert Data Architect specializing in Airtable infrastructure and relational database management systems (RDBMS). Your mission is to design a data transformation and cleansing process to convert a raw data column named [Nombre_Columna_Origen] into a format strictly compatible with Airtable's 'Multiselect' field type in table [Nombre_Tabla_Destino]. This process is critical to maintaining referential integrity and data hygiene in complex automation environments. Carefully analyze the input list provided in [Datos_Crudos]. Identifies the delimiters used (for example: commas, semicolons, line breaks, or horizontal bars) defined in [Delimitador_Actual]. Your task is to decompose each record, remove unnecessary leading or trailing whitespace (trimming), and normalize the capitalization according to the business rules established in [Regla_Capitalizacion] to ensure that no semantic duplicates are created (e.g. 'IA' vs 'ia'). Cross-reference the resulting data with the list of pre-existing options in Airtable: [Lista_Opciones_Existentes]. If you find new values that are not on the official list, you should categorize them under the [Etiqueta_Nuevos_Valores] tag or propose their creation based on the [Logica_Creacion_Opciones] logic. It is imperative that the end result be a clean array of strings or a comma-separated string that the Airtable API can interpret without schema validation errors. Finally, generate a detailed report that includes: 1) The final mapping of the transformed data. 2) A list of inconsistencies detected and resolved. 3) The JSON format ready to be sent via a PATCH or POST request to the Airtable API, ensuring that the [Nombre_Campo_Airtable] field contains the correct IDs or option names. Use a professional, technical tone aimed at the efficiency of automated processes.