planeta ai logo
Darmowy szablon automatyzacji

Generuj komunikaty AI za pomocą Google Gemini i przechowuj je w Airtable

1398
26 dni temu
11
bloków


Opis workflow automatyzacji generowania promptów AI

Ten szablon automatyzacji służy do generowania promptów dla agentów AI i przechowywania ich w Airtable. Proces rozpoczyna się od odbioru wiadomości czatu, przetworzenia jej w strukturalny prompt, skategoryzowania i zapisania w Airtable.

Instrukcja konfiguracji

Wymagania wstępne

  • Model AI (np. Gemini, OpenAI)
  • Baza i tabela w Airtable lub innym narzędziu do przechowywania danych

Przewodnik krok po kroku

  1. Klonowanie workflow: Skopiuj dostarczony JSON i zaimportuj go do swojej instancji n8n
  2. Konfiguracja poświadczeń: Skonfiguruj dane dostępowe do Google Gemini(PaLM) API oraz token dostępu do Airtable
  3. Mapowanie Airtable: Utwórz kopię Prompt Library w Airtable i zmapuj odpowiednią bazę oraz tabelę w węźle Airtable
  4. Dostosowanie szablonu promptu: Edytuj węzeł 'Create prompt', aby dostosować szablon do swoich potrzeb

Opcje konfiguracji

  • Szablon promptu: Możliwość dostosowania w węźle 'Create prompt'
  • Mapowanie Airtable: Należy upewnić się, że baza i tabela są poprawnie zmapowane

Uruchamianie i rozwiązywanie problemów

Uruchamianie workflow

  1. Wyślij wiadomość czatu, aby uruchomić workflow
  2. Monitoruj wykonanie w interfejsie n8n
  3. Sprawdź, czy prompt został zapisany w Airtable

Rozwiązywanie problemów

  • Problemy z API: Sprawdź poprawność konfiguracji poświadczeń
  • Mapowanie danych: Zweryfikuj poprawność mapowania bazy i tabeli w Airtable
  • Szablon promptu: Sprawdź, czy nie zawiera błędów

Przykłady zastosowań

Ten workflow jest szczególnie przydatny w scenariuszach wymagających automatyzacji generowania i zarządzania promptami dla agentów AI. Oto kilka potencjalnych zastosowań:

  • Szybkie prototypowanie agentów AI - generowanie i testowanie różnych promptów
  • Tworzenie treści - generowanie promptów do tworzenia postów na bloga, artykułów lub treści mediów społecznościowych
  • Automatyzacja obsługi klienta - tworzenie promptów dla chatbotów obsługujących zapytania klientów
  • Narzędzia edukacyjne - tworzenie promptów dla asystentów nauki i tutorów AI
  • Generowanie pomysłów - automatyzacja procesu tworzenia koncepcji i pomysłów
  • Personalizacja treści - tworzenie spersonalizowanych promptów dla różnych grup odbiorców
  • Optymalizacja procesów - usprawnienie wewnętrznych procesów biznesowych poprzez automatyzację generowania instrukcji

Wartość praktyczna

  • Oszczędność czasu - automatyzacja procesu generowania promptów
  • Lepsza jakość promptów - wykorzystanie Google Gemini i zasad inżynierii promptów
  • Centralne zarządzanie promptami - przechowywanie w Airtable dla łatwego dostępu i organizacji


   Skopiuj kod szablonu   
{"meta":{"instanceId":"db80165df40cb07c0377167c050b3f9ab0b0fb04f0e8cae0dc53f5a8527103ca","templateCredsSetupCompleted":true},"nodes":[{"id":"ed5363cf-1fb6-4662-b12c-073b2b3a3576","name":"When chat message received","type":"@n8n/n8n-nodes-langchain.chatTrigger","position":[-240,140],"webhookId":"ebe97b63-ae4b-40e7-9738-b7cf7ffbc8b6","parameters":{"options":{}},"typeVersion":1.1},{"id":"e47a166f-3e70-433e-ad0d-2100309cac92","name":"Google Gemini Chat Model","type":"@n8n/n8n-nodes-langchain.lmChatGoogleGemini","position":[-60,500],"parameters":{"options":{"topP":1},"modelName":"models/gemini-2.0-flash-lite"},"credentials":{"googlePalmApi":{"id":"Xp5T9q3YYxBIw2nd","name":"Google Gemini(PaLM) Api account✅"}},"typeVersion":1},{"id":"5474805f-8d18-4a09-a3ea-5602af97a5de","name":"Auto-fixing Output Parser","type":"@n8n/n8n-nodes-langchain.outputParserAutofixing","position":[500,360],"parameters":{"options":{}},"typeVersion":1},{"id":"d9a0eadc-54c7-4980-b4f8-79fd77627c32","name":"Structured Output Parser","type":"@n8n/n8n-nodes-langchain.outputParserStructured","position":[600,520],"parameters":{"jsonSchemaExample":"{nt"name": "Name of the prompt",n "category" : "the prompt category"n}"},"typeVersion":1.2},{"id":"898f64cd-2332-42ad-9bac-a817dd9bf3d7","name":"Edit Fields","type":"n8n-nodes-base.set","position":[220,140],"parameters":{"options":{},"assignments":{"assignments":[{"id":"9c5fec90-b7f0-45f3-81a3-22e0956fc3bf","name":"text","type":"string","value":"={{ $json.text }}"}]}},"typeVersion":3.4},{"id":"4bbd160a-98bd-4622-a54e-77b61ff91b46","name":"Google Gemini Chat Model1","type":"@n8n/n8n-nodes-langchain.lmChatGoogleGemini","position":[380,540],"parameters":{"options":{"topP":1},"modelName":"models/gemini-2.0-flash-lite"},"credentials":{"googlePalmApi":{"id":"Xp5T9q3YYxBIw2nd","name":"Google Gemini(PaLM) Api account✅"}},"typeVersion":1},{"id":"f45cbed4-c2b8-4f1b-8026-4686324a714a","name":"Return results","type":"n8n-nodes-base.set","position":[960,140],"parameters":{"options":{},"assignments":{"assignments":[{"id":"40aba86b-57b7-4c74-8e9f-d09cd2f344c5","name":"text","type":"string","value":"={{ $('Generate a new prompt').item.json.text }}"}]}},"typeVersion":3.4},{"id":"25650ec5-b559-4bfc-a95a-f81c674bc680","name":"Categorize and name Prompt","type":"@n8n/n8n-nodes-langchain.chainLlm","position":[360,140],"parameters":{"text":"={{ $json.text }}","messages":{"messageValues":[{"message":"=Categorize the above prompt into a category that it can fall into"}]},"promptType":"define","hasOutputParser":true},"typeVersion":1.5},{"id":"c324d952-0722-40aa-981c-fcb2007b43b9","name":"set prompt fields","type":"n8n-nodes-base.set","position":[660,140],"parameters":{"options":{},"assignments":{"assignments":[{"id":"cbf3b587-67fd-4f08-b50f-53561e869827","name":"name","type":"string","value":"={{ $json.output.name }}"},{"id":"7fda5833-9a3b-4c8a-b18d-4c31b35dae94","name":"category","type":"string","value":"={{ $json.output.category }}"},{"id":"50f06ab3-97d5-43cb-83ff-1a6aac45251b","name":"Prompt","type":"string","value":"={{ $('Edit Fields').item.json.text }}"}]}},"typeVersion":3.4},{"id":"97ad8d84-141e-4c21-8ce4-930dbe921f76","name":"add to airtable","type":"n8n-nodes-base.airtable","position":[800,140],"parameters":{"base":{"__rl":true,"mode":"list","value":"app994hU3fOw0ssrx","cachedResultUrl":"https://airtable.com/app994hU3fOw0ssrx","cachedResultName":"Prompt Library"},"table":{"__rl":true,"mode":"list","value":"tbldwJrCK2HmAeknA","cachedResultUrl":"https://airtable.com/app994hU3fOw0ssrx/tbldwJrCK2HmAeknA","cachedResultName":"Prompt Library"},"columns":{"value":{"Name":"={{ $json.name }}","Prompt":"={{ $json.Prompt }}","Category":"={{ $json.category }}"},"schema":[{"id":"Name","type":"string","display":true,"removed":false,"readOnly":false,"required":false,"displayName":"Name","defaultMatch":false,"canBeUsedToMatch":true},{"id":"Prompt","type":"string","display":true,"removed":false,"readOnly":false,"required":false,"displayName":"Prompt","defaultMatch":false,"canBeUsedToMatch":true},{"id":"Created ON","type":"string","display":true,"removed":true,"readOnly":true,"required":false,"displayName":"Created ON","defaultMatch":false,"canBeUsedToMatch":true},{"id":"Updated","type":"string","display":true,"removed":true,"readOnly":true,"required":false,"displayName":"Updated","defaultMatch":false,"canBeUsedToMatch":true},{"id":"Category","type":"string","display":true,"removed":false,"readOnly":false,"required":false,"displayName":"Category","defaultMatch":false,"canBeUsedToMatch":true}],"mappingMode":"defineBelow","matchingColumns":[],"attemptToConvertTypes":false,"convertFieldsToString":false},"options":{},"operation":"create"},"credentials":{"airtableTokenApi":{"id":"CAa937hASXcJZWTv","name":"Airtable Personal Access Token account✅"}},"typeVersion":2.1},{"id":"516dc434-25d9-4011-9453-bb28521823ca","name":"Generate a new prompt","type":"@n8n/n8n-nodes-langchain.chainLlm","position":[-80,140],"parameters":{"messages":{"messageValues":[{"message":"=You are an **expert n8n prompt engineer**, specializing in creating highly optimized, context-aware prompts for AI agents in n8n workflows. Your primary goal is to ensure AI agents execute well-defined tasks **accurately, autonomously, and efficiently**. nn### Instructions n1. **Define the AI Agent's Role and Rules** n - Use a structured role definition format: n `"You are a [SPECIFIC ROLE] working for [SPECIFIC BUSINESS CONTEXT]."` n - Clearly specify the agent's responsibilities and scope. nn2. **Provide Task Instructions** n - Use a **step-by-step** numbered list to outline the process. n - Ensure the instructions allow for flexibility but prevent errors. nn3. **Set Rules to Guide AI Behavior** n - Enumerate key constraints such as: n - Timezone requirements n - Prohibitions on making assumptions n - Required formatting for responses nn4. **Use Few-Shot Prompting** n - Provide clear examples of desired outputs inside `` tags. nn5. **Include Additional Context** n - Define relevant business details, the current date/time, and any required environmental context. nn---nn## Input Layer n### Structuring User Inputs n1. **Define Input Type** n - Specify whether inputs come from a human user (chat-based) or an external system (API calls). nn2. **Handle Dynamic Inputs** n - Use placeholders (e.g., `{customer_name}`, `{appointment_date}`) for adaptable prompts. nn3. **Ensure Personalization** n - Format prompts naturally while maintaining clarity and specificity. nn4. **Merge Static & Dynamic Data** n - Concatenate fixed prompt structures with real-time system data from n8n. nn---n## Action Layer n### Tool and Function Calling n1. **Standardized Tool Naming** n - Use `snake_case` names for tools (e.g., `check_calendar_availability`). nn2. **Provide Clear Tool Descriptions** n - Example: n `"Use the `fetch_customer_data` tool to retrieve details about a specific user based on their email address."` nn3. **Specify Tool Parameters & Expected Responses** n - Define required inputs, expected formats, and error handling strategies. nn4. **Avoid Hallucinations** n - AI should **only** use tools for their defined purposes. If information is missing, request clarification instead of guessing. nn---n## Example Prompt for an AI Agent in n8n nn```yamln# System Layern## RolenYou are a **Scheduling Assistant** working for a **beauty salon**. Your role is to help customers book appointments. nn## Instructionsn1. Ask the user for their preferred appointment date. n2. Use `check_calendar_availability` to find open slots. n3. If no slots are available, ask the user to select another day. n4. Capture the user’s **full name** and **email**. n5. Use `create_calendar_appointment` to confirm the booking. n6. Notify the user with appointment details. nn## Rulesn- Always use **UTC+1 timezone**. n- Do not assume details—ask if unsure. n- If asked about non-scheduling topics, respond: `"I can only assist with booking appointments."` nn## Few-shot Example nn"I have successfully booked your appointment:n- Date & Time: **Wednesday, 15 March 2025, 14:00 (UTC+1)**n- Booking Email: **jane.doe@example.com**nIf you need to cancel, please call +49 123 456 789."nn```n---n## Key Considerations n✅ **Avoid vague roles** (e.g., "You are an assistant"). Always specify **business context**. n✅ **Keep task steps structured** but flexible. n✅ **Provide explicit tool instructions** in a separate section. n✅ **Enable AI to ask clarifying questions** instead of making assumptions. n✅ **Use examples to guide expected outputs.** nnn"}]}},"typeVersion":1.5}],"pinData":{},"connections":{"Edit Fields":{"main":[[{"node":"Categorize and name Prompt","type":"main","index":0}]]},"add to airtable":{"main":[[{"node":"Return results","type":"main","index":0}]]},"set prompt fields":{"main":[[{"node":"add to airtable","type":"main","index":0}]]},"Generate a new prompt":{"main":[[{"node":"Edit Fields","type":"main","index":0}]]},"Google Gemini Chat Model":{"ai_languageModel":[[{"node":"Generate a new prompt","type":"ai_languageModel","index":0}]]},"Structured Output Parser":{"ai_outputParser":[[{"node":"Auto-fixing Output Parser","type":"ai_outputParser","index":0}]]},"Auto-fixing Output Parser":{"ai_outputParser":[[{"node":"Categorize and name Prompt","type":"ai_outputParser","index":0}]]},"Google Gemini Chat Model1":{"ai_languageModel":[[{"node":"Categorize and name Prompt","type":"ai_languageModel","index":0},{"node":"Auto-fixing Output Parser","type":"ai_languageModel","index":0}]]},"Categorize and name Prompt":{"main":[[{"node":"set prompt fields","type":"main","index":0}]]},"When chat message received":{"main":[[{"node":"Generate a new prompt","type":"main","index":0}]]}}}
  • LangChain
  • json
  • zod
Planeta AI 2025 
magic-wandmenu linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram