create e-mail responses with fastmail and OpenAI
Generate personalized email responses efficiently with this n8n workflow, automating the creation of draft emails in Fastmail using the power of OpenAI. This workflow connects your Fastmail account via HTTP requests and IMAP to retrieve incoming emails, then sends relevant details to OpenAI for intelligent response generation. It then filters for the drafts folder and uploads the generated content as a new draft email back into Fastmail, ready for review and sending. This is ideal for marketing teams, customer support, or anyone managing a high volume of email correspondence, allowing them to quickly draft replies to common inquiries, feedback, or outreach, significantly reducing the manual effort and time spent on email composition. By automating the initial draft creation, users can focus on refining and personalizing responses, saving valuable time and ensuring consistent, high-quality communication.
Workflow JSON
{"meta": {"instanceId": "04ab549d8bbb435ec33b81e4e29965c46cf6f0f9e7afe631018b5e34c8eead58"}, "nodes": [{"id": "082d1828-72b1-48c0-8426-c8051c29f0db", "name": "Session", "type": "n8n-nodes-base.httpRequest", "position": [-20, -20], "parameters": {"url": "https://api.fastmail.com/jmap/session", "options": {}, "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth"}, "credentials": {"httpHeaderAuth": {"id": "", "name": "[Your httpHeaderAuth]"}}, "typeVersion": 4.2}, {"id": "d7dc4c50-c8fc-4999-918d-5d357567ed14", "name": "Get Mailbox IDs", "type": "n8n-nodes-base.httpRequest", "notes": "https://api.fastmail.com/.well-known/jmap\n\nhttps://api.fastmail.com/jmap/session", "position": [200, -20], "parameters": {"url": "https://api.fastmail.com/jmap/api/", "method": "POST", "options": {}, "jsonBody": "={\n \"using\": [\"urn:ietf:params:jmap:core\", \"urn:ietf:params:jmap:mail\"],\n \"methodCalls\": [\n [\n \"Mailbox/get\",\n {\n \"accountId\": \"{{ $('Session').item.json.primaryAccounts['urn:ietf:params:jmap:mail'] }}\"\n },\n \"c0\"\n ]\n ]\n }", "sendBody": true, "sendHeaders": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": {"parameters": [{"name": "Content-Type", "value": "application/json"}, {"name": "Accept", "value": "application/json"}]}}, "credentials": {"httpHeaderAuth": {"id": "", "name": "[Your httpHeaderAuth]"}}, "typeVersion": 4.2}, {"id": "31be3c1c-f4c5-4309-92b3-2fd0a3fcecc6", "name": "Split Out", "type": "n8n-nodes-base.splitOut", "position": [400, -20], "parameters": {"options": {}, "fieldToSplitOut": "methodResponses[0][1].list"}, "typeVersion": 1}, {"id": "93de4dad-70d6-4e16-b351-7c540c3a4bfa", "name": "Email Trigger (IMAP)", "type": "n8n-nodes-base.emailReadImap", "position": [-20, -240], "parameters": {"options": {"customEmailConfig": "[\"UNSEEN\"]"}, "postProcessAction": "nothing", "downloadAttachments": true}, "credentials": {"imap": {"id": "", "name": "[Your imap]"}}, "typeVersion": 2}, {"id": "41e77a60-622f-426c-a50c-e0df03c53208", "name": "Get fields from source email", "type": "n8n-nodes-base.set", "position": [200, -240], "parameters": {"options": {}, "assignments": {"assignments": [{"id": "a9d425bd-e576-4e38-a251-b462240d3e2d", "name": "textPlain", "type": "string", "value": "={{ $json.textPlain }}"}, {"id": "7071a252-fcad-4aa1-953f-205c3e403497", "name": "from", "type": "string", "value": "={{ $json.from }}"}, {"id": "c4b0ed1b-590c-4d7f-b494-a0f34304cc1a", "name": "subject", "type": "string", "value": "={{ $json.subject }}"}, {"id": "7e0badd1-02be-4149-b9ff-286f0943f051", "name": "metadata['message-id']", "type": "string", "value": "={{ $json.metadata['message-id'] }}"}, {"id": "f87c7c15-c1d3-4696-bcd4-6677e5ddb240", "name": "metadata['reply-to']", "type": "string", "value": "={{ $json.metadata['reply-to'] }}"}]}}, "typeVersion": 3.4}, {"id": "f9d1a529-1377-456b-8357-d37fb3fe74f9", "name": "OpenAI", "type": "@n8n/n8n-nodes-langchain.openAi", "position": [400, -240], "parameters": {"modelId": {"__rl": true, "mode": "list", "value": "gpt-4o", "cachedResultName": "GPT-4O"}, "options": {}, "messages": {"values": [{"content": "=Please analyze the following personal email and draft a casual response based solely on its content. Return only the response text without any additional introductions or formatting. The response should include appropriate greetings (e.g., \"Hi\", \"Hallo\", \"Moin\" in German or \"Hi\", \"Hello\" in English) and sign-offs (e.g., \"Gru\u00df\", \"Lieben Gru\u00df\" in German or \"Regards\" in English). Add a thanks if appropriate. Use \"Du\" only if appropriate; if the email contains \"Sie\", maintain the same formality.\n\nSubject: {{ $json.subject }}\nEmail Content: {{ $json.textPlain }}"}]}}, "credentials": {"openAiApi": {"id": "", "name": "[Your openAiApi]"}}, "typeVersion": 1.5}, {"id": "c421ddc9-b230-499c-a11d-a20a68d30c5b", "name": "Filter for drafts folder", "type": "n8n-nodes-base.filter", "position": [560, -20], "parameters": {"options": {}, "conditions": {"options": {"version": 2, "leftValue": "", "caseSensitive": true, "typeValidation": "strict"}, "combinator": "and", "conditions": [{"id": "4e4c63d1-40fe-4314-bfe7-4fee62c78b88", "operator": {"name": "filter.operator.equals", "type": "string", "operation": "equals"}, "leftValue": "={{ $json.role }}", "rightValue": "drafts"}]}}, "typeVersion": 2.2}, {"id": "ef19fde4-cf8c-4e19-912e-822611c18056", "name": "upload draft email", "type": "n8n-nodes-base.httpRequest", "notes": "https://api.fastmail.com/.well-known/jmap\n\nhttps://api.fastmail.com/jmap/session", "position": [1000, -120], "parameters": {"url": "https://api.fastmail.com/jmap/api/", "method": "POST", "options": {}, "jsonBody": "={\n \"using\": [\"urn:ietf:params:jmap:core\", \"urn:ietf:params:jmap:mail\"],\n \"methodCalls\": [\n [\n \"Email/set\",\n {\n \"accountId\": \"{{ $('Session').item.json.primaryAccounts['urn:ietf:params:jmap:mail'] }}\",\n \"create\": {\n \"newDraft\": {\n \"mailboxIds\": {\n \"{{ $json.draftsId }}\": true\n },\n \"keywords\": {\n \"$draft\": true\n },\n \"inReplyTo\": [\"{{ $json.metadata['message-id'] }}\"],\n \"references\": [\"{{ $json.metadata['message-id'] }}\"],\n \"from\": [{\n \"name\": \"\",\n \"email\": \"{{ $('Session').item.json.username }}\"\n }],\n \"to\": [{\n \"name\": \"{{ $json['to-friendly'] }}\",\n \"email\": \"{{ $json.to }}\"\n }],\n \"subject\": \"{{ $json.subject }}\",\n \"bodyValues\": {\n \"textBody\": {\n \"value\": \"{{ $json.message.content.replace(/\\n/g, '\\\\n') }}\"\n }\n },\n \"bodyStructure\": {\n \"partId\": \"textBody\"\n }\n }\n }\n },\n \"c1\"\n ]\n ]\n}", "sendBody": true, "sendHeaders": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": {"parameters": [{"name": "Content-Type", "value": "application/json"}, {"name": "Accept", "value": "application/json"}]}}, "credentials": {"httpHeaderAuth": {"id": "", "name": "[Your httpHeaderAuth]"}}, "typeVersion": 4.2}, {"id": "f4ecb64a-c978-4aa3-943e-c4a7f0592b91", "name": "gather data for draft email", "type": "n8n-nodes-base.set", "position": [800, -120], "parameters": {"options": {}, "assignments": {"assignments": [{"id": "78885ad0-fa62-407e-82de-f297190265be", "name": "draftsId", "type": "string", "value": "={{ $json.id }}"}, {"id": "fcb31dde-0881-4b98-8bc2-e3e215148a5c", "name": "to-friendly", "type": "string", "value": "={{ $('Get fields from source email').item.json.from.match(/[^<]+/)[0].trim().replaceAll(/\\\"/g, \"\") }}"}, {"id": "84c80af6-68dd-44bd-97ba-fde78a42e88a", "name": "subject", "type": "string", "value": "=Re: {{ $('Get fields from source email').item.json.subject }}"}, {"id": "590e9856-9c6f-4d23-af42-8a0a1384ac00", "name": "message.content", "type": "string", "value": "={{ $('OpenAI').item.json.message.content }}"}, {"id": "4f24e071-24e3-4101-a423-ad5bbcca9fc7", "name": "metadata['message-id']", "type": "string", "value": "={{ $('Get fields from source email').item.json.metadata['message-id'] }}"}, {"id": "80c92734-0296-4299-9f98-15cc62e93d44", "name": "to", "type": "string", "value": "={{ $('Get fields from source email').item.json.metadata['reply-to'].match(/<([^>]+)>/)[1] ?? $('Get fields from source email').item.json.from.match(/<([^>]+)>/)[1] }}"}]}}, "typeVersion": 3.4}, {"id": "ca868672-85bd-4e2e-b2c6-6c6c69b78b24", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [-580, -560], "parameters": {"width": 493.9330818092735, "height": 695.2489786026621, "content": "## Workflow Description:\nThis n8n workflow automates the drafting of email replies for Fastmail using OpenAI's GPT-4 model. Here\u2019s the overall process:\n\n1. **Email Monitoring**: The workflow continuously monitors a specified IMAP inbox for new, unread emails.\n2. **Email Data Extraction**: When a new email is detected, it extracts relevant details such as the sender, subject, email body, and metadata.\n3. **AI Response Generation**: The extracted email content is sent to OpenAI's GPT-4, which generates a personalized draft response.\n4. **Get Fastmail Session and Mailbox IDs**: Connects to the Fastmail API to retrieve necessary session details and mailbox IDs.\n5. **Draft Identification**: Identifies the \"Drafts\" folder in the mailbox.\n6. **Draft Preparation**: Compiles all the necessary information to create the draft, including the generated response, original email details, and specified recipient.\n7. **Draft Uploading**: Uploads the prepared draft email to the \"Drafts\" folder in the Fastmail mailbox."}, "typeVersion": 1}, {"id": "c4273cc2-1ac2-43f4-bcd1-7f42d3109373", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [-40, -560], "parameters": {"color": 3, "width": 722.928660826031, "height": 285.5319148936168, "content": "## Prerequisites:\n1. **IMAP Email Account**: You need to configure an IMAP email account in n8n to monitor incoming emails.\n2. **Fastmail API Credentials**: A Fastmail account with JMAP API enabled. You should set up HTTP Header authentication in n8n with your Fastmail API credentials.\n3. **OpenAI API Key**: An API key from OpenAI to access GPT-4. Make sure to configure the OpenAI credentials in n8n."}, "typeVersion": 1}], "pinData": {}, "connections": {"OpenAI": {"main": [[{"node": "Session", "type": "main", "index": 0}]]}, "Session": {"main": [[{"node": "Get Mailbox IDs", "type": "main", "index": 0}]]}, "Split Out": {"main": [[{"node": "Filter for drafts folder", "type": "main", "index": 0}]]}, "Get Mailbox IDs": {"main": [[{"node": "Split Out", "type": "main", "index": 0}]]}, "Email Trigger (IMAP)": {"main": [[{"node": "Get fields from source email", "type": "main", "index": 0}]]}, "Filter for drafts folder": {"main": [[{"node": "gather data for draft email", "type": "main", "index": 0}]]}, "gather data for draft email": {"main": [[{"node": "upload draft email", "type": "main", "index": 0}]]}, "Get fields from source email": {"main": [[{"node": "OpenAI", "type": "main", "index": 0}]]}}}How to Import This Workflow
- 1Copy the workflow JSON above using the Copy Workflow JSON button.
- 2Open your n8n instance and go to Workflows.
- 3Click Import from JSON and paste the copied workflow.
Don't have an n8n instance? Start your free trial at n8nautomation.cloud
Related Templates
Send specific PDF attachments from Gmail to Google Drive using OpenAI
Automatically extract and categorize specific PDF attachments from incoming Gmail emails and upload them to designated Google Drive folders based on their content, leveraging OpenAI's advanced text analysis capabilities. This marketing workflow begins with the Gmail trigger "On email received," which then checks if the email "Has attachments?" If attachments are present, the workflow iterates through them, identifying if each is a PDF. For each identified PDF, the "Read PDF" node extracts its textual content. This content is then evaluated by the "Is text within token limit?" node to ensure it's suitable for OpenAI processing. If within limits, the "OpenAI matches PDF textual content" node analyzes the text against predefined criteria. Based on whether the PDF is "matched" by OpenAI, the "Upload file to folder" node in Google Drive stores the relevant PDFs, while unmatched or non-PDF attachments are handled accordingly. This workflow is ideal for marketing teams needing to automatically sort client contracts, campaign reports, or specific vendor invoices received via email, ensuring critical documents are filed correctly without manual intervention. It significantly reduces the time spent on document organization and improves data accessibility, allowing teams to focus on strategic marketing initiatives rather than administrative tasks.
Auto categorize wordpress template
Automatically categorize your WordPress posts with the power of AI. This workflow connects your WordPress site with OpenAI's advanced language models to intelligently analyze your content and assign appropriate categories. When you manually trigger this workflow, it first retrieves all your WordPress posts using the "Get All Wordpress Posts" node. This data then flows into an AI Agent, which leverages the "OpenAI Chat Model" to understand the context and content of each post. Based on this analysis, the AI Agent then interacts with your WordPress site to update the categories of your posts, streamlining your content management. This is incredibly useful for bloggers, content marketers, and website administrators who manage large volumes of content and want to ensure their posts are consistently and accurately categorized without manual effort. It saves significant time and reduces the potential for human error in content organization, making your website more navigable and improving SEO.
Effortless Email Management with AI
Automate your email management by intelligently processing incoming messages, summarizing their content, and drafting personalized replies with AI. This powerful workflow connects your Gmail inbox via an IMAP trigger to a Text Classifier that categorizes emails, then uses OpenAI for summarization and drafting responses, and Qdrant for vector storage of relevant documents from Google Drive. It’s ideal for marketing teams, customer support, or busy professionals who need to efficiently handle high volumes of correspondence, saving significant time on reading, understanding, and responding to emails by leveraging AI to streamline communication and ensure timely, relevant replies. The system also allows for reviewing AI-generated drafts before sending, ensuring quality control while drastically reducing manual effort.