planeta ai logo
Darmowy szablon automatyzacji

Unikaj zadawania zbędnych pytań dzięki dynamicznie generowanym formularzom przy użyciu OpenAI

2414
27 dni temu
19
bloków

Unikaj zadawania zbędnych pytań dzięki dynamicznym formularzom z OpenAI

Dla kogo jest ten workflow

Ten szablon automatyzacji został stworzony dla osób, które potrzebują formularza do zbierania jak największej ilości danych oraz odpowiedzi na wcześniej zdefiniowane pytania, jednocześnie optymalizując doświadczenie użytkownika poprzez eliminację zbędnych pytań.

Jak to działa

Workflow wymaga od użytkownika wprowadzenia podstawowych informacji, a następnie odpowiedzi na otwarte pytanie. Specyficzne pytania na kolejnej stronie formularza będą tylko tymi, na które użytkownik nie odpowiedział w części otwartej.

Odpowiedź na otwarte pytanie (oraz powiązane podstawowe informacje) jest analizowana przez model językowy (LLM), który określa, na które konkretne pytania nie udzielono odpowiedzi. Wykorzystuje się tutaj łańcuchowe rozumowanie (chain-of-thought reasoning), a struktura wyjściowa jest określana za pomocą Structured Output Parser.

Pytania, na które już udzielono odpowiedzi, są filtrowane w węzłach. Pozostałe elementy są wykorzystywane do wygenerowania ostatniej strony formularza. Po wypełnieniu ostatniej strony użytkownik widzi stronę potwierdzającą ukończenie formularza.

Przykłady zastosowań

Ta automatyzacja może być szczególnie przydatna w następujących scenariuszach:

  • Zbieranie leadów w firmach konsultingowych
  • Ankiety marketingowe i badania rynku
  • Formularze rekrutacyjne i aplikacyjne
  • Systemy wsparcia klienta i zgłaszania problemów
  • Kwestionariusze medyczne i diagnostyczne
  • Formularze zgłoszeniowe na wydarzenia
  • Ankiety satysfakcji klienta

Konfiguracja

  1. Dodaj swoje dane uwierzytelniające OpenAI
  2. Przejdź do węzła Get Basic Information i kliknij Test Step
  3. Wypełnij formularz, aby przetestować ogólny przypadek użycia
  4. Zmodyfikuj prompt w Analyse Response, aby dopasować go do swojego przypadku użycia

Kolejne kroki

  • Dodaj dodatkowe węzły do wysyłania e-maila do właściciela formularza
  • Dodaj kolejne wywołanie LLM do analizy odpowiedzi z formularza - kwalifikowane osoby powinny otrzymać możliwość umówienia spotkania

   Skopiuj kod szablonu   
{"id":"ZkIH2ygj2BNSfMOh","meta":{"instanceId":"ac63467607103d9c95dd644384984672b90b1cb03e07edbaf18fe72b2a6c45bb","templateCredsSetupCompleted":true},"name":"Dynamic Form with AI","tags":[],"nodes":[{"id":"5893c244-22b0-4699-a286-0ce121ccc427","name":"OpenAI Chat Model","type":"@n8n/n8n-nodes-langchain.lmChatOpenAi","position":[-340,240],"parameters":{"model":{"__rl":true,"mode":"list","value":"gpt-4o-mini"},"options":{}},"credentials":{"openAiApi":{"id":"1OMpAMAKR9l3eUDI","name":"OpenAi account"}},"typeVersion":1.2},{"id":"e7e333d4-42e5-4e6a-b78b-a3a45c31f37c","name":"Clarification Questions","type":"n8n-nodes-base.form","position":[1100,-60],"webhookId":"61936e5d-a2d3-447f-bf2f-722be2e1eb17","parameters":{"options":{},"defineForm":"json","jsonOutput":"={{ $json.data }}"},"typeVersion":1},{"id":"4b2bbc17-0e74-499d-ac6f-6c94ce3eb5ee","name":"Get Basic Information","type":"n8n-nodes-base.formTrigger","position":[-880,-60],"webhookId":"5256b332-3d3c-486a-8449-85fa44961bb8","parameters":{"options":{},"formTitle":"Get in Touch","formFields":{"values":[{"fieldLabel":"Name","placeholder":"John Smith","requiredField":true},{"fieldLabel":"Company Name","placeholder":"Company Limited","requiredField":true},{"fieldLabel":"Job Title","placeholder":"CEO","requiredField":true},{"fieldType":"email","fieldLabel":"Email","placeholder":"john.smith@company.com","requiredField":true}]}},"typeVersion":2.2},{"id":"b2eb9da9-571d-44ee-9944-a787f8d6cd50","name":"Get Business Overview","type":"n8n-nodes-base.form","position":[-640,-60],"webhookId":"16216db0-6150-4ac7-b1f7-7fd6c2eb74c5","parameters":{"options":{},"formFields":{"values":[{"fieldType":"textarea","fieldLabel":"Please describe your current situation and why you are interested in automating with AI","requiredField":true}]}},"typeVersion":1},{"id":"93c96c45-9512-46c2-9fe0-c4558b93e9d6","name":"End Form","type":"n8n-nodes-base.form","position":[1320,-60],"webhookId":"eb756213-2fae-4b29-85b3-727d3cf53b90","parameters":{"options":{},"operation":"completion","completionTitle":"Form Completed","completionMessage":"Thank you for answering these questions. We'll be in touch soon!"},"typeVersion":1},{"id":"123b688b-adae-4fe2-85cf-fc066175d96f","name":"Structured Output Parser","type":"@n8n/n8n-nodes-langchain.outputParserStructured","position":[-120,240],"parameters":{"jsonSchemaExample":"{n "response": [n {n "question": "What is the biggest challenge facing their business at present?",n "has_been_answered": false,n "reasoning": "put your reason here"n },n {n "question": "Does the company have any existing automation workflows already in place?",n "has_been_answered": true,n "reasoning": "put your reason here"n },n {n "question": "Is the respondent a decision-maker in the business? (This can be inferred from their job title if it indicates a leadership position such as CEO, Founder, Director, etc.)",n "has_been_answered": false,n "reasoning": "put your reason here"n },n {n "question": "Which specific business functions or departments are they looking to automate? (Examples: Sales, Marketing, HR, Finance, Customer Service, Supply Chain, etc.)",n "has_been_answered": true,n "reasoning": "put your reason here"n },n {n "question": "What does their current IT infrastructure look like?",n "has_been_answered": false,n "reasoning": "put your reason here"n }n ]n}n"},"typeVersion":1.2},{"id":"3a2d86a3-62ed-4003-a012-bfdabc9eafc8","name":"Remove Already Answered Questions","type":"n8n-nodes-base.filter","position":[340,-60],"parameters":{"options":{},"conditions":{"options":{"version":2,"leftValue":"","caseSensitive":true,"typeValidation":"strict"},"combinator":"and","conditions":[{"id":"40bc4f8b-7fd3-4149-af5d-aca71eb9b034","operator":{"type":"boolean","operation":"false","singleValue":true},"leftValue":"={{ $json.has_been_answered }}","rightValue":""}]}},"typeVersion":2.2},{"id":"a97d53ae-1649-4809-8793-5e4a815016cb","name":"Analyse Response","type":"@n8n/n8n-nodes-langchain.chainLlm","position":[-280,-60],"parameters":{"text":"=## Analysis TasknnAnalyze the following customer response to the question "Please describe your current situation and why you are interested in automating with AI." nnCustomer Information:n- Job Title: {{ $('Get Basic Information').item.json['Job Title'] }}n- Response: {{ $json['Please describe your current situation and why you are interested in automating with AI'] }}nn## Required InformationnIdentify whether the customer's response clearly addresses each of these critical questions:nn1. What specific goals are you looking to achieve with automation?n2. Does the company have any existing automation workflows already in place?n3. Is the respondent a decision-maker in the business? (This can be inferred from their job title if it indicates a leadership position such as CEO, Founder, Director, etc.)n4. Which specific business functions or departments are you looking to automate? (Examples: Sales, Marketing, HR, Finance, Customer Service, Supply Chain, etc.)n5. What does your current IT infrastructure look like?nn## Output FormatnAnalyse each question with whether you believe that the question has already been answered. Go step by step and use reasoning. ","promptType":"define","hasOutputParser":true},"typeVersion":1.5},{"id":"12b8cc80-ff5e-4ebd-a72d-2629f743355e","name":"Split Out Analysis","type":"n8n-nodes-base.splitOut","position":[120,-60],"parameters":{"options":{},"fieldToSplitOut":"output.response"},"notesInFlow":false,"typeVersion":1},{"id":"c28929cf-7590-4e32-be20-f9065920ed80","name":"Prepare For Form Generation","type":"n8n-nodes-base.set","position":[580,-60],"parameters":{"options":{},"assignments":{"assignments":[{"id":"ae1dbc1e-6005-4b5e-acbe-c3fda6d4413f","name":"fieldLabel","type":"string","value":"={{ $json.question }}"},{"id":"c46276bc-018e-4edb-82e0-f6a4dc9d4953","name":"requiredField","type":"boolean","value":true},{"id":"b060ed04-a99c-475b-a5b6-6cb5d57ea2ff","name":"fieldType","type":"string","value":"textarea"}]}},"typeVersion":3.4},{"id":"33d55396-e716-41c5-bf25-d0bfcfadf167","name":"Aggregate For Form Generation","type":"n8n-nodes-base.aggregate","position":[840,-60],"parameters":{"options":{},"aggregate":"aggregateAllItemData"},"typeVersion":1},{"id":"15b39119-08d6-45bf-9323-09fa5b59a64e","name":"Sticky Note4","type":"n8n-nodes-base.stickyNote","position":[-1660,-300],"parameters":{"width":700,"height":780,"content":"# Avoid Asking Redundant Questions with Dynamically Generated Forms using OpenAI n## Target AudiencenThis workflow has been built for those who require a form to capture as much data as possible as well as the answers to predefined questions, whilst optimising the user experience by avoiding asking redundant questions.n## Use CasenWhen creating a form to capture information, it can be useful to give the user an opportunity to input a long answer to a large, open-ended question. We then want to drill down to answer specific questions that we require the answer to. When doing this, we don't want to ask duplicate questions. This particular scenario imagines an AI consultancy capturing leads.n## What it DoesnThis workflow requires users to input basic information and then answer an open ended question. The specific questions on the next page will only be those that weren't answered in the open-ended question.n## How it Worksn1. The open-ended question (and relevant basic information) is analysed by an LLM to determine which specific questions have not been answered. Chain-of-thought reasoning is utilised and the output structure is specified with the **Structured Output Parser**.n2. Those questions that have already been answered are filtered out nodes. The remaining items are then used to generate the last page of the form.n3. Once the user has filled in the final page of the form, they are shown a form completion page.n## Next Stepsn- Add additional nodes to send an email to the form ownern- Add a subsequent LLM call to analyse the form response - those that are qualified should be given the opportunity to book an appointment"},"typeVersion":1},{"id":"e9270776-97f0-4aa4-8797-92a235f7760e","name":"Sticky Note5","type":"n8n-nodes-base.stickyNote","position":[-940,-300],"parameters":{"width":480,"height":140,"content":"## Setupn1. Add your **OpenAI** credentialsn2. Go to the **Get Basic Information** node and click **Test Step**n3. Complete the form to test the generic use casen4. Modify the prompt in **Analyse Response** to fit your use case"},"typeVersion":1},{"id":"6db4d121-f08a-4509-82fd-5d91d1dcbc82","name":"Sticky Note","type":"n8n-nodes-base.stickyNote","position":[-940,-140],"parameters":{"color":7,"width":480,"height":240,"content":"## 1. Initial Form Pagesnn"},"typeVersion":1},{"id":"3ecaaf11-8bc7-415e-8eb3-245f7bcedda7","name":"Sticky Note1","type":"n8n-nodes-base.stickyNote","position":[-440,-220],"parameters":{"color":7,"width":480,"height":620,"content":"## 2. Analyse Responsenn"},"typeVersion":1},{"id":"1e2e100e-ac64-45b1-aa3b-318996783a79","name":"Sticky Note8","type":"n8n-nodes-base.stickyNote","position":[-420,140],"parameters":{"color":5,"width":220,"height":240,"content":"### ModificationnReplace this sub-node nto use a different language model"},"typeVersion":1},{"id":"e6f92fbb-7f41-4e02-9316-06e7480c0306","name":"Sticky Note6","type":"n8n-nodes-base.stickyNote","position":[-300,-160],"parameters":{"color":5,"width":300,"height":240,"content":"### ModificationnModify the prompt to suit your use case"},"typeVersion":1},{"id":"1bcca0c9-a4b3-493f-a188-7ecc00fec36e","name":"Sticky Note2","type":"n8n-nodes-base.stickyNote","position":[60,-140],"parameters":{"color":7,"width":920,"height":260,"content":"## 3. Clean Up Analysisnn"},"typeVersion":1},{"id":"ffcee0f4-364b-46a5-9deb-cbd005a3b6fc","name":"Sticky Note3","type":"n8n-nodes-base.stickyNote","position":[1000,-140],"parameters":{"color":7,"width":520,"height":260,"content":"## 4. Generate Final Form Page & End Formnnn"},"typeVersion":1}],"active":true,"pinData":{},"settings":{"executionOrder":"v1"},"versionId":"336f5d17-d556-4e9f-8785-9c55c0b5d918","connections":{"End Form":{"main":[[]]},"Analyse Response":{"main":[[{"node":"Split Out Analysis","type":"main","index":0}]]},"OpenAI Chat Model":{"ai_languageModel":[[{"node":"Analyse Response","type":"ai_languageModel","index":0}]]},"Split Out Analysis":{"main":[[{"node":"Remove Already Answered Questions","type":"main","index":0}]]},"Get Basic Information":{"main":[[{"node":"Get Business Overview","type":"main","index":0}]]},"Get Business Overview":{"main":[[{"node":"Analyse Response","type":"main","index":0}]]},"Clarification Questions":{"main":[[{"node":"End Form","type":"main","index":0}]]},"Structured Output Parser":{"ai_outputParser":[[{"node":"Analyse Response","type":"ai_outputParser","index":0}]]},"Prepare For Form Generation":{"main":[[{"node":"Aggregate For Form Generation","type":"main","index":0}]]},"Aggregate For Form Generation":{"main":[[{"node":"Clarification Questions","type":"main","index":0}]]},"Remove Already Answered Questions":{"main":[[{"node":"Prepare For Form Generation","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