使用Dumpling AI实现Telegram到邮件通讯自动化
高级
这是一个Multimodal AI领域的自动化工作流，包含 16 个节点。主要使用 Wait, Gmail, SplitOut, Aggregate, HttpRequest 等节点。 使用Dumpling AI和GPT根据Telegram关键词生成邮件通讯
前置要求
- •Google 账号和 Gmail API 凭证
- •可能需要目标 API 的认证凭证
- •Telegram Bot Token
- •OpenAI API Key
使用的节点 (16)
分类
工作流预览
可视化展示节点连接关系，支持缩放和平移
导出工作流
复制以下 JSON 配置到 n8n 导入，即可使用此工作流
{
"id": "36Ag52lg9PbHbEC3",
"meta": {
"instanceId": "a1ae5c8dc6c65e674f9c3947d083abcc749ef2546dff9f4ff01de4d6a36ebfe6",
"templateCredsSetupCompleted": true
},
"name": "使用Dumpling AI实现Telegram到邮件通讯自动化",
"tags": [],
"nodes": [
{
"id": "1b978cc3-984c-4964-a732-ade35e5087d1",
"name": "简单记忆",
"type": "@n8n/n8n-nodes-langchain.memoryBufferWindow",
"position": [
-3136,
0
],
"parameters": {
"sessionKey": "={{ $json.message.from.id }}",
"sessionIdType": "customKey"
},
"typeVersion": 1.3
},
{
"id": "e3a409e6-2225-4ecc-8f19-3b2b9ef1b34e",
"name": "搜索新闻",
"type": "n8n-nodes-base.httpRequestTool",
"position": [
-2944,
0
],
"parameters": {
"url": "https://app.dumplingai.com/api/v1/search-news",
"method": "POST",
"options": {},
"jsonBody": "={\n \"query\": \"{{ $fromAI('suggestion', 'Autocomplete suggestion to search in Google News', 'string') }}\"\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"toolDescription": "use this to Search Google News using the autocomplete suggestions as input. Use this after getting results from Google_autocomplete to find recent news articles on those suggested queries."
},
"credentials": {
"httpHeaderAuth": {
"id": "RLFzAcGRepr5eXZB",
"name": "Dumpling AI-n8n"
}
},
"typeVersion": 4.2
},
{
"id": "3f1bc79c-e630-4cda-b41a-28b54e26a71f",
"name": "Google自动补全",
"type": "n8n-nodes-base.httpRequestTool",
"position": [
-2704,
-48
],
"parameters": {
"url": "https://app.dumplingai.com/api/v1/get-autocomplete",
"method": "POST",
"options": {},
"jsonBody": "={\n \"query\": \"{{ $fromAI('keyword', 'Keyword to get autocomplete suggestions', 'string') }}\"\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth",
"toolDescription": "use this to Fetche autocomplete suggestions from Google based on a keyword and returns the response data"
},
"credentials": {
"httpHeaderAuth": {
"id": "RLFzAcGRepr5eXZB",
"name": "Dumpling AI-n8n"
}
},
"typeVersion": 4.2
},
{
"id": "b4501237-6712-4da9-a753-351aa6667d78",
"name": "等待",
"type": "n8n-nodes-base.wait",
"position": [
-1920,
-240
],
"webhookId": "7c8e4b1e-f085-488f-9428-eb06602c32cf",
"parameters": {},
"typeVersion": 1.1
},
{
"id": "74009d0d-f5a0-4d21-b2fe-6b12b9f8d2f2",
"name": "开始：从Telegram接收关键词",
"type": "n8n-nodes-base.telegramTrigger",
"position": [
-3360,
-256
],
"webhookId": "fb142d0e-75be-4ed6-afd7-e8c3318ed0d8",
"parameters": {
"updates": [
"message"
],
"additionalFields": {}
},
"credentials": {
"telegramApi": {
"id": "hv5o1OogajIIiMlt",
"name": "Telegram account"
}
},
"typeVersion": 1.2
},
{
"id": "f7d45172-ebc9-410b-8da5-2aab5ad6edcd",
"name": "AI Agent：扩展关键词并编排工具",
"type": "@n8n/n8n-nodes-langchain.agent",
"position": [
-2992,
-256
],
"parameters": {
"text": "=Keyword: {{ $json.message.text }}",
"options": {
"systemMessage": "=You are a helpful assistant connected to multiple tools in n8n. Your main job is to take a keyword provided by the trigger, expand it into relevant search terms, and then find the most recent news related to those terms. Here is how you should use the tools:\n\nGoogle_autocomplete tool (Dumpling AI Autocomplete):\n\nAlways call this first when you receive a keyword from the trigger.\n\nInput: the keyword or phrase provided.\n\nOutput: a list of popular search suggestions related to that keyword.\n\nPurpose: to understand what people are actually searching for and generate multiple angles of interest on the keyword.\n\nGoogle_News tool (Dumpling AI Google News):\n\nAfter you receive autocomplete suggestions, pass those suggestions directly into the Google_News tool.\n\nInput: each autocomplete suggestion as a search term.\n\nOutput: recent articles, headlines, or updates from Google News related to those suggestions.\n\nPurpose: to gather fresh and relevant information tied to what people are searching for.\n\nFlow Logic:\n\nTrigger sends a keyword → Call Google_autocomplete → Take results → Feed results into Google_News → Return the final set of news articles.\n\nIf no autocomplete results are found, use the original keyword directly in Google_News.\n\nGuidelines:\n\nDo not skip the autocomplete step unless it returns no results.\n\nUse the autocomplete suggestions exactly as they are for Google News searches.\n\nAlways structure your output in a clean and easy-to-read format so results can be reused in later steps of the automation.\n\nReturn result in a structured JSON,here is the example JSON:\n{\n \"articles\": [\n {\n \"category\": \"string\",\n \"title\": \"string\",\n \"url\": \"string\",\n \"source\": \"string\",\n \"summary\": \"string\",\n \"published\": \"string\"\n }\n ]\n}\n"
},
"promptType": "define",
"hasOutputParser": true
},
"typeVersion": 1.9
},
{
"id": "b8f6aae2-3c9b-4c04-9650-a7c206a24a22",
"name": "LLM：语言模型",
"type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
"position": [
-3344,
-16
],
"parameters": {
"model": {
"__rl": true,
"mode": "list",
"value": "gpt-4o-mini"
},
"options": {}
},
"credentials": {
"openAiApi": {
"id": "dd8NvMC6rvx8RITo",
"name": "OpenAi account 2"
}
},
"typeVersion": 1.2
},
{
"id": "334cf258-1045-4e30-8d9e-9420d9ac6990",
"name": "解析器：格式化新闻JSON",
"type": "@n8n/n8n-nodes-langchain.outputParserStructured",
"position": [
-2416,
-48
],
"parameters": {
"jsonSchemaExample": "{\n \"articles\": [\n {\n \"category\": \"string\",\n \"title\": \"string\",\n \"url\": \"string\",\n \"source\": \"string\",\n \"summary\": \"string\",\n \"published\": \"string\"\n }\n ]\n}\n"
},
"typeVersion": 1.2
},
{
"id": "a9673a47-600f-4571-a2cc-605480741a4e",
"name": "拆分文章",
"type": "n8n-nodes-base.splitOut",
"position": [
-2464,
-256
],
"parameters": {
"options": {},
"fieldToSplitOut": "output.articles"
},
"typeVersion": 1
},
{
"id": "beed3081-737a-4ca7-8a10-2fedfbaede46",
"name": "循环：处理每篇文章",
"type": "n8n-nodes-base.splitInBatches",
"position": [
-2240,
-256
],
"parameters": {
"options": {}
},
"typeVersion": 3
},
{
"id": "e2f661cc-c28c-454f-b202-f8ee60c92819",
"name": "爬虫：清理文章内容",
"type": "n8n-nodes-base.httpRequest",
"position": [
-1648,
-240
],
"parameters": {
"url": "https://app.dumplingai.com/api/v1/scrape",
"method": "POST",
"options": {},
"jsonBody": "={\n \"url\": \"{{ $json.url }}\",\n \"cleaned\": true\n}\n",
"sendBody": true,
"specifyBody": "json",
"authentication": "genericCredentialType",
"genericAuthType": "httpHeaderAuth"
},
"credentials": {
"httpHeaderAuth": {
"id": "RLFzAcGRepr5eXZB",
"name": "Dumpling AI-n8n"
}
},
"typeVersion": 4.2
},
{
"id": "2605c6e3-b4ad-475e-9119-3c0da295470d",
"name": "聚合：合并文章内容",
"type": "n8n-nodes-base.aggregate",
"position": [
-2016,
-464
],
"parameters": {
"include": "specifiedFields",
"options": {},
"aggregate": "aggregateAllItemData",
"fieldsToInclude": "content",
"destinationFieldName": "content"
},
"typeVersion": 1
},
{
"id": "f4e40d07-48b6-457e-a83d-48a3a6c3baf4",
"name": "生成新闻通讯",
"type": "@n8n/n8n-nodes-langchain.openAi",
"position": [
-1808,
-464
],
"parameters": {
"modelId": {
"__rl": true,
"mode": "list",
"value": "gpt-4.1-mini",
"cachedResultName": "GPT-4.1-MINI"
},
"options": {},
"messages": {
"values": [
{
"role": "system",
"content": "=You are an assistant that writes newsletters from provided source content. Use only the content I give you. Do not invent facts. If something is missing, omit it.\n\nGOAL:\nCreate a high quality newsletter in HTML and a strong email subject line.\n\nOUTPUT FORMAT:\nReturn only valid JSON with this exact schema and nothing else:\n{\n \"newsletter\": \"html\",\n \"subject\": \"string\"\n}\n\nSUBJECT RULES:\n• Write a clear subject under 60 characters.\n• Make it specific and benefit driven.\n• No clickbait. No emojis. Use simple grammar.\n\nNEWSLETTER HTML RULES:\n• Produce production ready HTML suitable for email.\n• Include a clear header title, a short intro paragraph, two to six story sections, and a closing call to action.\n• Use simple inline CSS only. No external styles, no scripts.\n• Use a single column layout with readable fonts, clear spacing, and mobile friendly widths.\n• For each story, include a headline, two to three sentence summary, and a source link if present in the input.\n• Group similar items together and remove duplicates.\n• Keep links as plain anchor tags. Open in same tab.\n• Add a brief footer with sources list using the available links from the input, and an unsubscribe placeholder.\n\nTONE AND STYLE:\n• Write in clear, friendly, professional language.\n• Keep sentences short and direct.\n• Avoid jargon and filler.\n\nCONSTRAINTS:\n• Use only information found in INPUT_CONTENT.\n• If there is conflicting info, pick the most recent or most credible item and note it briefly.\n• If there are no valid items, return an empty newsletter with a short note in the intro explaining that no recent updates were found.\n\nVALIDATION:\n• Ensure the JSON is valid.\n• Escape quotes inside the HTML as needed.\n• Do not include markdown. Do not include code fences. Output JSON only.\n"
},
{
"content": "=INPUT_CONTENT:\n\"{{ JSON.stringify($json.content) }}\""
}
]
},
"jsonOutput": true
},
"credentials": {
"openAiApi": {
"id": "dd8NvMC6rvx8RITo",
"name": "OpenAi account 2"
}
},
"typeVersion": 1.8
},
{
"id": "e2ea6b10-bcc3-4e28-bafc-ff5db1c874f3",
"name": "通过邮件发送新闻通讯",
"type": "n8n-nodes-base.gmail",
"position": [
-1424,
-464
],
"webhookId": "5934a129-e113-47d2-9cd3-a5162e55164f",
"parameters": {
"sendTo": "=",
"message": "={{ $json.message.content.newsletter }}",
"options": {},
"subject": "={{ $json.message.content.subject }}"
},
"credentials": {
"gmailOAuth2": {
"id": "j70r3RTMED1pgN3R",
"name": "Gmail account 2"
}
},
"typeVersion": 2.1
},
{
"id": "41135b73-722e-4287-8a65-cd62e72777a8",
"name": "便签",
"type": "n8n-nodes-base.stickyNote",
"position": [
-3360,
-480
],
"parameters": {
"width": 820,
"height": 280,
"content": "## Agent分支"
},
"typeVersion": 1
},
{
"id": "e08fdd8d-4864-4480-b9f0-7bbdcdf99720",
"name": "便签1",
"type": "n8n-nodes-base.stickyNote",
"position": [
-2096,
-640
],
"parameters": {
"color": 3,
"width": 780,
"height": 300,
"content": "## Newsletter分支"
},
"typeVersion": 1
}
],
"active": false,
"pinData": {
"Scraper: Clean Article Content": [
{
"json": {
"url": "https://www.retailtouchpoints.com/features/executive-viewpoints/the-future-of-agentic-ai-ecosystems-in-retail",
"title": "The Future of Agentic AI Ecosystems in Retail - Retail TouchPoints",
"format": "markdown",
"cleaned": true,
"content": "Emerald Media Network\n\n[Advertise](https://www.retailtouchpoints.com/marketing-advertising-media-kit)\n\n[](https://retailtouchpoints.com/)\n\n[](https://retailtouchpoints.com/designretail)\n\n[](https://www.retailinnovationconference.com/)\n\n[Linkedin](https://www.linkedin.com/company/retail-touchpoints)[X-twitter](https://twitter.com/rtouchpoints)[Facebook](https://www.facebook.com/RetailTouchPoints/)[Instagram](https://www.instagram.com/rtouchpoints/)[Youtube](https://www.youtube.com/retailtouchpoints)\n\nAdvertisement\n\n- Trending\n\n[Why Intellectual](https://www.retailtouchpoints.com/features/industry-insights/why-intellectual-property-concerns-could-cause-a-hiccup-in-retail-ai)\n\n[Cornell to Leave Top Target Post; Retailer Chooses COO Fiddelke as Replacement](https://www.retailtouchpoints.com/features/retail-movers-and-shakers/cornell-to-leave-top-target-post-retailer-chooses-coo-fiddelke-as-replacement)\n\n[Listen Now: Inside ThredUp’s Surge — What’s Fueling Resale’s Rise](https://www.retailtouchpoints.com/topics/digital-commerce/listen-now-inside-thredups-surge-whats-fueling-resales-rise)\n\n[Consumers Love AI Search and In-Store Shopping — and Retailers Need to Deliver Both](https://www.retailtouchpoints.com/topics/omnichannel-alignment/consumers-love-ai-search-and-in-store-shopping-and-retailers-need-to-deliver-both)\n\n[Research Reveals Many Consumers Misunderstand What ‘Made in the USA’ Labels Actually Mean](https://www.retailtouchpoints.com/topics/supply-chain-sourcing/research-reveals-many-consumers-misunderstand-what-made-in-the-usa-labels-actually-mean)\n\n[Columbia CEO Comments on Challenges and Downsizing in U.S., International Growth, and Tariff Turmoil](https://www.retailtouchpoints.com/topics/market-news/columbia-ceo-comments-on-challenges-and-downsizing-in-u-s-international-growth-and-tariff-turmoil)\n\nSearch\n\nSearch\n\n# The Future of Agentic AI Ecosystems in Retail\n\n- August 22, 2025 at 9:03 AM EDT\n- By Greg Zakowicz, Omnisend\n\nWanan-stock.Adobe.com\n\nAgentic AI, where autonomous agents perform actions on behalf of people, may be relatively new, but it’s advancing at a rapid pace. In ecommerce, we’re beginning to see these agents built and deployed to browse and buy products for people. This technology is so transformative that we may be on the edge of a new era of ecommerce.\n\nUnlike Alexa’s early promise of a new way to shop, this evolution is happening within a visual medium already familiar to consumers: websites. But are consumers ready for it? A survey published by Omnisend showed that [66% of consumers](https://www.omnisend.com/blog/ai-trust-and-data-privacy-ecommerce/) refuse to let AI make purchases for them, even if it promises better deals.\n\nWhile this is likely still true for the majority, the tide is changing. Remember, adoption takes time, and as users become more familiar with the tools these agents are built on, like ChatGPT, adoption can escalate quickly.\n\nLet’s look at what’s already familiar to consumers.\n\nAdvertisement\n\n**Amazon**. Its [Buy For Me](https://www.aboutamazon.com/news/retail/amazon-shopping-app-buy-for-me-brands) feature, released in beta in April, allows customers to purchase products autonomously from other websites while still on Amazon. While Buy For Me still requires human involvement up to the point of purchase, it’s only the beginning.\n\n**Walmart and Mastercard**. Mastercard released its [Agent Pay](https://www.mastercard.com/news/press/2025/april/mastercard-unveils-agent-pay-pioneering-agentic-payments-technology-to-power-commerce-in-the-age-of-ai/) feature while Walmart [is developing](https://corporate.walmart.com/news/2025/05/29/inside-walmarts-strategy-for-building-an-agentic-future) an agentic AI tool to help shoppers navigate the purchase journey, including “shopping journey completion.”\n\n**ChatGPT and** [**Perplexity Shopping**](https://www.perplexity.ai/shopping) features are designed for users to conduct research on products and discover the “best” product options. Users can interact with the tool and refine results based on requests.\n\nThese are all companies that are well-known to consumers. But here’s where it gets interesting from an ecommerce standpoint.\n\nOpenAI’s [Operator](https://openai.com/index/introducing-operator/) combines its own browser into the request process. With Operator, a user can prompt the tool to search for a product using as many defined criteria as they like and watch as it autonomously navigates websites on the same screen, completing tasks, including making purchases. This is a major next step in the evolution, and we can all see where this is heading.\n\nAnd then there’s Google. Its [AI Mode](https://blog.google/products/shopping/google-shopping-ai-mode-virtual-try-on-update/) is the closest yet to a true agentic AI shopping experience. Users can virtually try on products using their own likenesses, track and set purchase prices and make purchases themselves. Considering Google’s importance to the current shopping environment, this is massive.\n\nSo how long before Target, Apple, Meta and other AI platforms take the next step in their already-developing AI commerce solutions?\n\nConsumers may not be ready just yet, but that doesn’t mean they won’t be, and it isn’t stopping companies from going all in on it. They want to be ready the moment consumers are, and even before.\n\nThis is the race companies want to win.\n\n### **But What Does Winning Look Like?**\n\nThis is what concerns me most. Are we looking at an eventual consolidated ecosystem? If so, will it be a good thing, and for whom?\n\nAs we see, there is no shortage of companies trying to own the AI shopping ecosystem, but how will this affect consumers? What happens if one AI agent rules them all? Who then has the power, the retailer or the AI?\n\nRight now, it’s looking like a race to own the ecosystem. When we talk about owning the ecosystem, we talk about the biggest players on the market, including Google, Amazon, Walmart, widely adopted AI platforms and even financial institutions.\n\nBut here’s the rub: if you own the ecosystem, you own the data. If the AI agent is controlled by the same company that owns the marketplace, the data layer, the payment stack and possibly even the fulfillment network, competition becomes almost impossible. It may no longer deliver the best results for the query, “What’s the best size 13 running shoe for a casual runner?” Instead, it may deliver results based on what’s best for the agent’s creator.\n\nWill a closed system like this reduce shoppers’ exposure to products simply because an ecommerce company didn’t pay to be included in the results? Or will it return results based on volumes of available content, and if so, will this favor large companies like Walmart?\n\nI pondered this same consolidated ecosystem back in 2017 when Alexa was dominating headlines. I thought we might be looking at a future where companies like Apple, Google and Amazon tried to “own” homes — WiFi networks, thermostats, home security, internet browsers, entertainment channels and smart devices. It appears this is where shopping AI agents are heading.\n\nIf the market consolidates, I can’t see how it helps ecommerce brands or shoppers. Will small brands be able to compete?\n\n### **Would an Open Agentic AI Ecosystem be More Beneficial?**\n\nGenerally, giving consumers a choice is a good thing, but would that be the case with AI agents in ecommerce? If the marketplace were to remain fragmented, made up of both large and small companies, consumers would need to choose their preferred platform. This invites a slew of questions.\n\nWould all agents be able to operate across all websites and platforms? If not, would consumers need to use multiple agents to execute different tasks? How will they decide which one to use, and for what purposes — after all, you can’t have two agents looking to purchase the same products at the same time. Will one agent feature different product and brand results than another?\n\nThis seems to create more friction in the shopping journey than less.\n\nWe can’t talk about online shopping without talking about discounts. How will shoppers know whether or not they got a good deal on a product? Sure, an agent can monitor prices and report that the price is lower than normal, but this would presumably be for the listed price. Will the agent be able to apply discounts, such as those received for signing up for an email program, that would bring a higher listed price lower than the less expensive price?\n\nIf these questions can’t be adequately addressed, a fragmented ecosystem might encourage consumers to abandon shopping AI agents altogether, If this happens, AI shopping agents might transform into product discovery and deal-finder tools rather than transactional ones, leaving the current shopping process altered but mostly the same.\n\nThere are so many unknowns.\n\n### **Looking Ahead**\n\nAt the end of the day, it’ll be fascinating to watch how this all shapes up. Agentic AI has the potential to shift how consumers interact with brands. Consumers may have brand loyalty but agents won’t, unless, presumably, directed by individuals to favor those brands. If a shopper directs an agent to purchase a product and references brands whose products they typically like, this is what the agent will find. If you’re a lesser-known brand, how will you be discovered by the agent (unless, of course, it’s pay-to-play)?\n\nWe may need to redefine customer loyalty, from the traditional definition to simply being a “preferred option.” This means building a brand will be more important than ever, causing brands to focus more on the post-purchase experience than they do now, which is primarily an acquisition-first approach. The downstream effects may heighten the importance of first-party channels like email and SMS for post-purchase and product discovery communications.\n\nThe agentic AI revolution in ecommerce is happening, and brands need to think about how it will impact them. My advice: start now.\n\n* * *\n\n_Greg Zakowicz is Ecommerce and Retail Advisor for_ [_Omnisend_](https://nam10.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.omnisend.com%2F&data=05%7C02%7CAdam.Blair%40EmeraldX.com%7Ccd238dead60e449b285d08ddd9ac0b31%7C661c8d9be19e4330b41275dce2d26154%7C0%7C0%7C638906055142782035%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=I4xto%2BrI0v9rKpVXwr3%2B%2BJ9kLOi4%2F%2BSqknbxx2cpQ8Q%3D&reserved=0) _, an email and SMS marketing automation platform. With nearly 20 years of experience as a practitioner, consultant and analyst, Zakowicz has helped countless brands optimize their digital marketing strategies. He’s a frequent speaker at industry events, a published writer on ecommerce trends, has been featured in top-tier media outlets and has served as an industry expert witness for trial._\n\n- Posted In: [AI & Machine Learning](https://www.retailtouchpoints.com/topics/data-analytics/ai-machine-learning), [Customer Experience](https://www.retailtouchpoints.com/topics/customer-experience), [Data & Analytics](https://www.retailtouchpoints.com/topics/data-analytics), [Digital Commerce](https://www.retailtouchpoints.com/topics/digital-commerce), [Digital Marketing](https://www.retailtouchpoints.com/topics/digital-marketing), [E-commerce Experience](https://www.retailtouchpoints.com/topics/digital-commerce/e-commerce-experience), [E-commerce Security](https://www.retailtouchpoints.com/topics/digital-commerce/e-commerce-security), [Executive ViewPoints](https://www.retailtouchpoints.com/features/executive-viewpoints), [Loyalty](https://www.retailtouchpoints.com/topics/loyalty), [Personalization](https://www.retailtouchpoints.com/topics/personalization), [Pricing](https://www.retailtouchpoints.com/topics/pricing)\n- Tagged With: [agentic AI](https://www.retailtouchpoints.com/tag/agentic-ai), [Alexa](https://www.retailtouchpoints.com/tag/alexa), [Amazon Buy for Me](https://www.retailtouchpoints.com/tag/amazon-buy-for-me), [chatgpt](https://www.retailtouchpoints.com/tag/chatgpt), [Google AI Mode](https://www.retailtouchpoints.com/tag/google-ai-mode), [Greg Zakowicz](https://www.retailtouchpoints.com/tag/greg-zakowicz), [Mastercard Agent Pay](https://www.retailtouchpoints.com/tag/mastercard-agent-pay), [Meta](https://www.retailtouchpoints.com/tag/meta), [Omnisend](https://www.retailtouchpoints.com/tag/omnisend), [OpenAI Operator](https://www.retailtouchpoints.com/tag/openai-operator), [Perplexity Shopping](https://www.retailtouchpoints.com/tag/perplexity-shopping), [Target](https://www.retailtouchpoints.com/tag/target), [Walmart](https://www.retailtouchpoints.com/tag/walmart)\n\n### Feature Your Byline\n\nSubmit an Executive ViewPoints.\n\n[Learn More](https://g3communications.wufoo.com/forms/retail-touchpoints-executive-viewpoints/)\n\nFeatured Experience\n\n[](https://www.retailtouchpoints.com/hub/retail-thinktank)\n\n- [Aired: March 2025](https://webinars.retailtouchpoints.com/retail-strategy-and-planning-series/2024/?partnerref=RTP_Website)\n- [Digital Event](https://webinars.retailtouchpoints.com/retail-strategy-and-planning-series/2024/?partnerref=RTP_Website)\n\nGet ready for the holidays with the **Holiday ThinkTank**! Find must-read articles, webinars, videos, and expert tips on everything from trends to marketing, in-store ideas, ecomm, fulfillment, and customer service. It’s all free and available anytime—so you can plan, prep, and win the season your way.\n\n[Access Now](https://www.retailtouchpoints.com/hub/retail-thinktank)\n\nAdvertisement\n\nSubscribe Today\n\nGet access to exclusive content including newsletters, reports, research, videos, podcasts, and much more.\n\nFirst Name\n\nEmail\n\nBusiness Type\n\nBusiness TypeRetailer: Apparel/Footwear/AccessoriesRetailer: Automotive AftermarketRetailer: C-StoreRetailer: CE/Office SupplyRetailer: Consumer GoodsRetailer: Department/Mass MarketRetailer: eCommerce/DirectRetailer: Food/Beverage/RestaurantsRetailer: GroceryRetailer: Home Center/HardwareRetailer: Home FurnishingsRetailer: HospitalityRetailer: SpecialtyRetailer: Sporting Goods/OutdoorsRetailer: OtherConsumer Product SupplierNon-Retailer: Analyst/ConsultantNon-Retailer: Solution ProviderNon-Retailer: Student/FacultyNon-Retailer: Other\n\nRetail TouchPoints is a brand of Emerald X LLC. By clicking the button and submitting information, you acknowledge and agree that your information may be shared with corporate affiliates of Emerald X LLC, and other organizations such as event hosts, speakers, sponsors, and partners. Please read our [Privacy Policy](https://www.emeraldx.com/privacy-policy/) and [Terms of Use](https://www.emeraldx.com/terms-of-use/) for more information on our policies.\n\nreCAPTCHA\n\nRecaptcha requires verification.\n\nI'm not a robot\n\nreCAPTCHA\n\n[Privacy](https://www.google.com/intl/en/policies/privacy/) \\- [Terms](https://www.google.com/intl/en/policies/terms/)\n\nSubscribe\n\nGeneral\n\nArticles\n\nResources\n\nAbout Us\n\nContact Us\n\n**Address:**\n\n100 Broadway, 14th Floor\n\nNew York, NY 10005\n\n**Phone:**\n\n1.888.603.3626\n\n**Email:**\n\ninfo \\[at\\] retailtouchpoints.com\n\n**Social:**\n\n[Linkedin](https://www.linkedin.com/company/retail-touchpoints)[Facebook](https://www.facebook.com/RetailTouchPoints/)[Instagram](https://www.instagram.com/rtouchpoints/)[Youtube](https://www.youtube.com/retailtouchpoints)\n\n[](https://emeraldx.com/)\n\n[ABOUT](https://www.emeraldx.com/about/ \"about\") [CAREERS](https://www.emeraldx.com/careers/ \"careers\") [AUTHORIZED SERVICE PROVIDERS](http://emeraldx.com/authorized-service-providers/ \"authorized-service-providers\") [Your Privacy Choices](https://www.retailtouchpoints.com/features/executive-viewpoints/the-future-of-agentic-ai-ecosystems-in-retail# \"your-privacy-choices\") [TERMS OF USE](https://www.emeraldx.com/terms-of-use/ \"terms-of-use\") [PRIVACY POLICY](https://www.emeraldx.com/privacy-policy/ \"privacy-policy\")\n\n© 2025 [Emerald X, LLC.](https://www.emeraldx.com/) All Rights Reserved",
"metadata": {
"ogUrl": "https://www.retailtouchpoints.com/features/executive-viewpoints/the-future-of-agentic-ai-ecosystems-in-retail",
"author": "Adam Blair",
"robots": "index, follow, max-image-preview:large, max-snippet:-1, max-video-preview:-1",
"ogImage": "https://www.retailtouchpoints.com/wp-content/uploads/2025/08/VP_Omnisend.png",
"ogTitle": "The Future of Agentic AI Ecosystems in Retail - Retail TouchPoints",
"language": "en-US",
"ogSiteName": "Retail TouchPoints",
"description": "In ecommerce, we’re beginning to see agentic AI agents built and deployed to browse and buy products for people.",
"ogDescription": "In ecommerce, we’re beginning to see agentic AI agents built and deployed to browse and buy products for people."
}
}
}
]
},
"settings": {
"executionOrder": "v1"
},
"versionId": "ef12c48d-5bdb-4348-b42d-f1ac5851a3e3",
"connections": {
"Wait": {
"main": [
[
{
"node": "Scraper: Clean Article Content",
"type": "main",
"index": 0
}
]
]
},
"Search_news": {
"ai_tool": [
[
{
"node": "AI Agent: Expand Keyword & Orchestrate Tools",
"type": "ai_tool",
"index": 0
}
]
]
},
"Simple Memory": {
"ai_memory": [
[
{
"node": "AI Agent: Expand Keyword & Orchestrate Tools",
"type": "ai_memory",
"index": 0
}
]
]
},
"Split Articles": {
"main": [
[
{
"node": "Loop: Process Each Article",
"type": "main",
"index": 0
}
]
]
},
"Generate Newsletter": {
"main": [
[
{
"node": "Send Newsletter via Email",
"type": "main",
"index": 0
}
]
]
},
"Google_autocomplete": {
"ai_tool": [
[
{
"node": "AI Agent: Expand Keyword & Orchestrate Tools",
"type": "ai_tool",
"index": 0
}
]
]
},
"LLM: Language Model": {
"ai_languageModel": [
[
{
"node": "AI Agent: Expand Keyword & Orchestrate Tools",
"type": "ai_languageModel",
"index": 0
}
]
]
},
"Parser: Format News JSON": {
"ai_outputParser": [
[
{
"node": "AI Agent: Expand Keyword & Orchestrate Tools",
"type": "ai_outputParser",
"index": 0
}
]
]
},
"Send Newsletter via Email": {
"main": [
[]
]
},
"Loop: Process Each Article": {
"main": [
[
{
"node": "Aggregate: Combine Article Content",
"type": "main",
"index": 0
}
],
[
{
"node": "Wait",
"type": "main",
"index": 0
}
]
]
},
"Scraper: Clean Article Content": {
"main": [
[
{
"node": "Loop: Process Each Article",
"type": "main",
"index": 0
}
]
]
},
"Aggregate: Combine Article Content": {
"main": [
[
{
"node": "Generate Newsletter",
"type": "main",
"index": 0
}
]
]
},
"Start: Receive Keyword from Telegram": {
"main": [
[
{
"node": "AI Agent: Expand Keyword & Orchestrate Tools",
"type": "main",
"index": 0
}
]
]
},
"AI Agent: Expand Keyword & Orchestrate Tools": {
"main": [
[
{
"node": "Split Articles",
"type": "main",
"index": 0
}
]
]
}
}
}常见问题
如何使用这个工作流？
复制上方的 JSON 配置代码，在您的 n8n 实例中创建新工作流并选择「从 JSON 导入」，粘贴配置后根据需要修改凭证设置即可。
这个工作流适合什么场景？
高级 - 多模态 AI
需要付费吗？
本工作流完全免费，您可以直接导入使用。但请注意，工作流中使用的第三方服务（如 OpenAI API）可能需要您自行付费。
相关工作流推荐
使用 Dumpling AI + GPT-4o 将 Reddit 痛点转化为漫画广告
使用Dumpling AI和GPT-4o将Reddit痛点转换为漫画广告
If
Set
Reddit
+12
31 节点Yang
内容创作
💥 使用NanoBanana、Seedream 4、ChatGPT Image和Veo 3自动化视频广告 - VIDE
使用AI（NanoBanana、Seedream、GPT-4o、Veo 3）自动化和发布视频广告活动
Set
Code
Wait
+16
63 节点Dr. Firas
内容创作
1. 播放列表详情设置机器人副本
使用 Suno、GPT-4、Runway 和 Creatomate 创建 AI 生成的 YouTube 音乐播放列表
If
Set
Code
+22
203 节点Joseph
内容创作
使用 GPT-4 和 Dumpling AI 从 Telegram 创建 LinkedIn 内容
使用 Whisper、GPT-4 和 Dumpling AI 从 Telegram 语音/文本创建 LinkedIn 内容
Set
Switch
Airtable
+10
16 节点Yang
杂项
在可视化参考库中探索n8n节点
在可视化参考库中探索n8n节点
If
Ftp
Set
+93
113 节点I versus AI
其他
使用GPT-4、Dumpling AI和Google Drive生成广告图片变体
使用GPT-4、Dumpling AI和Google Drive生成广告图片变体
Split Out
Form Trigger
Google Drive
+8
14 节点Yang
内容创作
