Slack chatbot powered by AI
This workflow offers an effective way to handle a chatbot's functionality, making use of multiple tools for information retrieval, conversation context storage, and message sending. It's a setup tailored for a Slack environment, aiming to offer an interactive, AI-driven chatbot experience. Note that to use this template, you need to be on n8n version 1.19.4 or later.
By n8n TeamExtract and process information directly from PDF using Claude and Gemini
Overview This workflow helps you compare Claude 3.5 Sonnet and Gemini 2.0 Flash when extracting data from a PDF This workflow extracts and processes the data within a PDF in one single step, instead of calling an OCR and then an LLM” How it works The initial 2 steps download the PDF and convert it to base64. This base64 string is then sent to both Claude 3.5 Sonnet and Gemini 2.0 Flash to extract information. This workflow is made to let you compare results, latency, and cost (in their dedicated dashboard). How to use it Set up your Google Drive if not already done Select a document on your Google Drive Modify the prompt in "Define Prompt" to extract the information you need and transform it as wanted. Get a Claude API key and/or Gemini API key Note that you can deactivate one of the 2 API calls if you don't want to try both Test the Workflow
By Agent StudioUse any LangChain module in n8n (with the LangChain code node)
LangChain is a framework for building AI functionality that users large language models. By leveraging the functionality of LangChain, you can write even more powerful workflows. This workflow shows how you can write LangChain code within n8n, including importing LangChain modules. The workflow itself produces a summary of a YouTube video, when given the video's ID. Note that to use this template, you need to be on n8n version 1.19.4 or later.
By David RobertsGet multiple attachments from Gmail and upload them to GDrive
This is a simple template to show how to extract multiple email attachments and return them as an iterable output. How it works: The Gmail Trigger node detects any new email that has attachments. The Code node will then extract them as binary files and attaches them to the item. They can then be uploaded via the Google Drive node. Setup steps: add your Gmail Credentials add your Google Drive Credentials Follow the official n8n Documentation for help Feedback & Questions If you have any questions or feedback about this workflow - Feel free to get in touch at ria@n8n.io
By RiaHigh-level service page SEO blueprint report generator
Introduction The "High-Level Service Page SEO Blueprint Report" workflow is a powerful, AI-driven solution designed to generate comprehensive SEO content strategies for service-based businesses. By analyzing competitor websites and user intent, this workflow creates a detailed blueprint that outlines the optimal structure, content, and conversion elements for a service page. The workflow leverages the JINA Reader API to extract content from competitor websites and uses Google Gemini AI to perform deep analysis across multiple dimensions: competitor content structure, user intent, strategic opportunities, and conversion optimization. The final output is a professionally formatted Markdown document that provides actionable guidance for creating a high-performing service page that satisfies both user needs and search engine requirements. This workflow eliminates the time-consuming process of manually analyzing competitors and developing content strategies, providing a data-driven foundation for service page creation that would typically require hours of expert analysis. Who is this for? This workflow is designed for digital marketers, SEO specialists, content strategists, and web developers who need to create or optimize service pages for businesses. It's particularly valuable for marketing agencies and freelancers who regularly develop content strategies for clients across various industries. Users should have a basic understanding of SEO concepts, content marketing, and website structure. While technical SEO knowledge is beneficial, the workflow is designed to provide comprehensive guidance even for those with intermediate-level expertise. The ideal user is someone who wants to streamline their content planning process and ensure their service pages are built on data-driven insights rather than guesswork. What problem is this workflow solving? Creating effective service pages that rank well in search engines while converting visitors is a complex challenge that typically requires extensive competitive research, content planning, and conversion optimization expertise. This workflow addresses several key pain points: Time-consuming competitor analysis: Manually analyzing multiple competitor websites to identify content patterns, heading structures, and meta tag strategies can take hours. Difficulty identifying content gaps: Determining what topics competitors are missing that could provide a competitive advantage requires deep analysis and industry knowledge. Balancing SEO and conversion elements: Creating content that satisfies both search engines and user needs while driving conversions is a delicate balance that many struggle to achieve. Lack of structured approach: Many content creators work without a comprehensive blueprint, leading to inconsistent results and missed opportunities. Difficulty translating analysis into actionable recommendations: Even when analysis is performed, turning those insights into a concrete content plan can be challenging. This workflow automates these processes, providing a structured, data-driven approach to service page creation that saves hours of research and planning time. What this workflow does Overview The workflow takes a list of competitor URLs and a target keyword as input, then performs a multi-stage analysis to generate a comprehensive service page blueprint. It extracts and analyzes competitor content, evaluates user intent, identifies strategic opportunities, and creates detailed recommendations for page structure, content, and conversion elements. The final output is a professionally formatted Markdown document that serves as a complete roadmap for creating an effective service page. Process Data Collection: The workflow begins with a form that collects essential information: competitor URLs, target keyword, services offered, brand name, and whether the page is a homepage. Competitor Content Extraction: The workflow processes each competitor URL, using the JINA Reader API to extract the HTML content from each site. Content Structure Analysis: For each competitor site, the workflow extracts and analyzes heading structures, meta tags, schema markup, and recurring phrases (n-grams). Competitor Analysis Report: The AI synthesizes the competitive data to identify patterns in meta titles/descriptions, common outline sections, key heading concepts, and structural elements. User Intent Analysis: The workflow analyzes the target keyword to determine primary and secondary user intents, user personas, and their position in the buyer's journey. Gap Analysis: The AI identifies content overlaps ("table stakes"), content gaps (opportunities), SEO keyword priorities, and potential UX/conversion advantages. Page Outline Generation: Based on the previous analyses, the workflow creates an optimal page structure with H1, H2s, H3s, and potentially H4s, with justifications for each section. UX & Conversion Recommendations: The workflow adds detailed recommendations for calls-to-action, trust signals, copywriting tone, visual elements, and risk reversal strategies. Final Blueprint Creation: All analyses and recommendations are compiled into a comprehensive, well-structured Markdown document that serves as a complete service page blueprint. Setup Download or import the "High-Level Service Page SEO Blueprint Report" workflow JSON file into your n8n instance. Create a JINA Reader API key by visiting https://jina.ai/api-dashboard/key-manager. You can claim a free API key that allows up to 1 million tokens. Set up Google Gemini (PaLM) credentials by following the guide at https://docs.n8n.io/integrations/builtin/credentials/googleai/using-geminipalm-api-key. Update the "Edit Fields" node with: Your JINA Reader API Key Adjust the "Waiting Time" to 20 seconds if using the free Google Gemini API tier (which limits to 5 requests per minute) Optionally change the Gemini model if needed Activate the workflow and start the form trigger. Complete the form with: Competitors (up to 5 direct competitor URLs) Target Keyword (the query related to your service) Services Offered (details of your complete service offerings) Brand Name (your company name) Whether the page is a homepage After processing, download the generated .txt file, which contains the blueprint in Markdown format. How to customize this workflow to your needs Adjust AI parameters: Modify the temperature settings in the Google Gemini Chat Model nodes to control creativity vs. precision in the AI outputs. Customize extraction logic: Edit the "Extract HTML Elements" code node to focus on specific HTML elements that are most relevant to your industry or content type. Modify analysis prompts: Customize the prompts in the various analysis nodes to focus on specific aspects of SEO or content strategy that are most important for your use case. Add industry-specific guidance: Enhance the prompts with industry-specific instructions or examples to make the output more relevant to particular sectors. Integrate with content management systems: Extend the workflow to automatically send the blueprint to content management systems, project management tools, or document storage platforms. Add competitor scoring: Implement a scoring system to evaluate and rank competitors based on specific criteria relevant to your strategy. Expand the analysis: Add additional analysis nodes to evaluate other aspects of competitor websites, such as page speed, mobile-friendliness, or backlink profiles.
By Custom Workflows AIExport SQL table into CSV file
This workflow demonstrates how easy it is to export SQL query to CSV automatically! Before running the workflow please make sure you have access to a local or remote MSSQL server with a sample AdventureWorks database. The detailed process is explained in the tutorial https://blog.n8n.io/sql-export-to-csv/
By EduardAI-powered lead research & personalized email generation with Groq & Google Sheets
Overall Description & Potential << What Does This Flow Do? >> Overall, this workflow is an intelligent sales outreach automation engine that transforms raw leads from a form or a list into highly personalized, ready-to-send introductory email drafts. The process is: it starts by fetching data, enriches it with in-depth AI research to uncover "pain points," and then uses those research findings to craft an email that is relevant to the solutions you offer. This system solves a key problem in sales: the lack of time to conduct in-depth research on every single lead. By automating the research and drafting stages, the sales team can focus on higher-value activities, like engaging with "warm" prospects and handling negotiations. Using Google Sheets as the main dashboard allows the team to monitor the entire process—from lead entry, research status, and email drafts, all the way to the send link—all within a single, familiar interface. << Potential Future Enhancements >> This workflow has a very strong foundation and can be further developed into an even more sophisticated system: Full Automation (Zero-Touch): Instead of generating a manual-click link, the output from the AI Agent can be directly piped into a Gmail or Microsoft 365 Email node to send emails automatically. A Wait node could be added to create a delay of a few minutes or hours after the draft is created, preventing instant sending. Automated Follow-up Sequences: The workflow can be extended to manage follow-up emails. By using a webhook to track email opens or replies, you could build logic like: "If the intro email is not replied to within 3 days, trigger the AI Agent again to generate follow-up email 1 based on a different template, and then send it." AI-Powered Lead Scoring: After the research stage, the AI could be given the additional task of scoring leads (e.g., 1-10 or High/Medium/Low Priority) based on how well the target company's profile matches your ideal customer profile (ICP). This helps the sales team prioritize the most promising leads. Full CRM Integration: Instead of Google Sheets, the workflow could connect directly to HubSpot, Salesforce, or Pipedrive. It would pull new leads from the CRM, perform the research, draft the email, and log all activities (research results, sent emails) back to the contact's timeline in the CRM automatically. Multi-Channel Outreach: Beyond email, the AI could be instructed to draft personalized LinkedIn Connection Request messages or WhatsApp messages. The workflow could then use the appropriate APIs to send these messages, expanding your outreach beyond just email.
By ainablerScale deal flow with a Pitch Deck AI vision, chatbot and QDrant vector store
Are you a popular tech startup accelerator (named after a particular higher order function) overwhelmed with 1000s of pitch decks on a daily basis? Wish you could filter through them quickly using AI but the decks are unparseable through conventional means? Then you're in luck! This n8n template uses Multimodal LLMs to parse and extract valuable data from even the most overly designed pitch decks in quick fashion. Not only that, it'll also create the foundations of a RAG chatbot at the end so you or your colleagues can drill down into the details if needed. With this template, you'll scale your capacity to find interesting companies you'd otherwise miss! Requires n8n v1.62.1+ How It Works Airtable is used as the pitch deck database and PDF decks are downloaded from it. An AI Vision model is used to transcribe each page of the pitch deck into markdown. An Information Extractor is used to generate a report from the transcribed markdown and update required information back into pitch deck database. The transcribed markdown is also uploaded to a vector store to build an AI chatbot which can be used to ask questions on the pitch deck. Check out the sample Airtable here: https://airtable.com/appCkqc2jc3MoVqDO/shrS21vGqlnqzzNUc How To Use This template depends on the availability of the Airtable - make a duplicate of the airtable (link) and its columns before running the workflow. When a new pitchdeck is received, enter the company name into the Name column and upload the pdf into the File column. Leave all other columns blank. If you have the Airtable trigger active, the execution should start immediately once the file is uploaded. Otherwise, click the manual test trigger to start the workflow. When manually triggered, all "new" pitch decks will be handled by the workflow as separate executions. Requirements OpenAI for LLM Airtable For Database and Interface Qdrant for Vector Store Customising This Workflow Extend this starter template by adding more AI agents to validate claims made in the pitch deck eg. Linkedin Profiles, Page visits, Reviews etc.
By JimleukAI sales agent: WhatsApp, FB, IG, OpenAI, Airtable, Supabase auto-booking
This workflow automates multi-channel AI-driven sales engagement for lead qualification, service information delivery, and consultation booking. It integrates WhatsApp, Facebook Messenger, Instagram DM, and an n8n chat interface with a backend CRM (Airtable), a knowledge base (Supabase), and conversational AI (OpenAI), all orchestrated by n8n. Tools & Services Used Messaging Platforms: WhatsApp, Facebook Messenger, Instagram DM, n8n Built-in Chat AI Core & Processing: OpenAI (GPT-4o for main agent logic, Whisper for audio transcription) CRM & Data Management: Airtable (for initial WhatsApp lead lookup, lead form submissions, and as the backend for the crmAgent sub-workflow operations) Knowledge Base: Supabase (Vector Store for technicalandsales_knowledge tool) Chat Memory: PostgreSQL (for the main AI Agent's conversation history) Orchestration & Automation: n8n (Self-hosted, utilizing Langchain community nodes) Calendar Service: Integrated via the calendarAgent sub-workflow CRM Service: Integrated via the crmAgent sub-workflow (interacting with Airtable) Workflow Overview This automation performs the following steps: Trigger: A new interaction is initiated through one of the following channels: A new message is received via the WhatsApp Trigger. A new message is received via the Facebook Trigger (Webhook). A new message is received via the Instagram Trigger (Webhook). A new message is received via the n8n Chat Trigger. Alternatively, a new lead is submitted via the Airtable Form Submitted Webhook. Channel-Specific Ingestion & Pre-processing: For WhatsApp: The system attempts to find an existing lead in Airtable using the sender's phone number. Incoming messages are routed by the Handle Message Types switch: Text messages are passed to the Edit Fields - chat1 node to prepare input for the AI Agent, including any found lead information. Audio messages are processed: the WhatsApp Business Cloud node gets the media URL, the HTTP Request node downloads the audio, OpenAI transcribes it to text, and Edit Fields - chat2 prepares this transcribed text and lead information for the AI Agent. Unsupported message types trigger the Reply To User1 node to send a notification that the message type cannot be processed. For Facebook Messenger: The system responds to webhook verification (Respond to Webhook - facebook get) and acknowledges new messages (Respond to Webhook - facebook post). The If is not echo - facebook node filters out messages sent by the page. The Sales Agent Demo - typing_on node sends a typing indicator. The Edit Fields - facebook node prepares the message text, sender ID, and Facebook-specific context for the AI Agent. For Instagram DM: The system responds to webhook verification (Respond to Webhook - instagram get) and acknowledges new messages (Respond to Webhook - instagram post). The If is not echo - instagram node filters out messages sent by the business account. The Edit Fields - instagram node prepares the message text, sender ID, and Instagram-specific context for the AI Agent. For n8n Chat: The Edit Fields - chat node prepares the user's input and session information for the AI Agent. Input Aggregation for AI Agent: Processed data from all active messaging channels (WhatsApp text/audio, Facebook, Instagram, n8n Chat) is funneled through the No Operation, do nothing node to the main AI Agent. AI Sales Conversation & Tool Utilization: The AI Agent (using OpenAI Chat Model - GPT-4o, and Postgres Chat Memory) engages the user according to its system prompt, aiming to qualify them for Paint Protection Film (PPF), Ceramic Coating, or Window Tint. The AI Agent uses the technicalandsales_knowledge tool (which queries the Demo Supabase vector store via Embeddings OpenAI and OpenAI Chat Model1) to provide service details and answer questions. The AI Agent uses the crmAgent tool (a sub-workflow) to log contact details (Name, Email, service interest) and update opportunity statuses in Airtable. The AI Agent uses the calendarAgent tool (a sub-workflow) to book consultation appointments once preferred dates/times are provided. This occurs after contact details are logged in the CRM. Response Delivery: The AI Agent's final textual response is passed to the Switch node. The Switch node routes the response to the appropriate node for delivery on the original channel: Reply To User for WhatsApp. Facebook Graph API - Sales Agent Demo for Facebook Messenger. Instagram Graph API - smb.sales.agent.demo for Instagram DM. Output - chat for the n8n Chat interface. Airtable Form Submission Processing (Separate Branch): When the Airtable Form Submitted webhook receives data, the Airtable node fetches the full record. The Create Contact node creates a new contact in the Airtable 'Contacts' table. The Edit Fields - form node prepares data for a notification. The WhatsApp Business Cloud2 node sends a templated WhatsApp message to the lead, confirming their form submission.
By Sam YassineRespond with file download to incoming HTTP request
This simple workflow demonstrates how to get an end user's browser to download a file. It makes use of the Content-Disposition header to set a filename and control the browser behaviour. A use case could be the download of a PDF file at the end of an application process or to export data from a database without replacing the current page content in the browser. With this approach, the current page remains open and the file is simply downloaded instead: The original idea was first present here by @dickhoning in the n8n community.
By TomAi data extraction with dynamic prompts and Airtable
This n8n template introduces the Dynamic Prompts Ai workflow pattern which are incredible for certain types of data extraction tasks where attributes are unknown or need to remain flexible. The general idea behind this pattern is that the prompts for requested attributes to be extracted live outside the template and so can be changed at any time - without needing to edit the template. This seriously cuts down on maintainance requirements and is reusable for any number of tables at little cost. Check out the video demo I did for n8n Studio here: https://www.youtube.com/watch?v=_fNAD1u8BZw Check out the example Airtable here: https://airtable.com/appAyH3GCBJ56cfXl/shrXzR1Tj99kuQbyL Looking for the Baserow Version? https://n8n.io/workflows/2780-ai-data-extraction-with-dynamic-prompts-and-baserow/ How it works Given we have an "input" field for context and a number of fields for the data we want to extract, this template will run in the background to react to any changes to either the "input" or fields and automatically update the rows accordingly. The key is that Airtable fields have a special property called the "field description". In this pattern, we use this property to allow the user to store a simple prompt describing the data that should exist in the column. Our n8n template reads these column descriptions aka "prompts" to use as instructions to perform tasks on the "input". In this template, the "input" is a PDF of a resume/CV and the columns are attributes a HR person would want to extract from it - such as full name, address, last position, years of experience etc. How to use First publish this template and ensure it's accessible via webhook URL. You then have to run the "create airtable webhooks" mini-flow to configure your Airtable to send change events to the n8n template. This mini-flow exists in the template but you'll have to update the IDs. Check the template for more instructions. Requirements Airtable for Tables/Database OpenAI for LLM and extraction. Feel free to choose another LLM if preferred. Customising this workflow If you're not using files, you can replace the "input" field with anything you like. For example, the "input" could be single line text.
By JimleukSync Jira issues with subsequent comments to Notion database
This workflow creates/updates/deletes a Notion database page when an issue is created/updated/deleted in Jira. Subsequent updates to the issue's title or status in Jira are updated in the Notion database. If you require more fields to send to Notion, this template is easily extendible which will be described in setup. The Notion database will require setup before the workflow can be used. Prerequisites Notion account and Notion credentials. Jira account and Jira credentials. How it works When a new issue is created in Jira, the workflow creates a new page in the Notion database will all the required fields. When the issue's title or status is updated in Jira, the workflow updates the specific Notion database page identified by the "Issue Key" field in Notion. If the status in Jira is set to "Done", the workflow will mark the Notion database page "Done" field as true. When the issue is deleted in Jira, the workflow archives the Notion database page. Setup This workflow requires that you set up a Notion database. To do so, follow the steps below: In Notion, create a new database. Add the following columns to the database: Done (with type "Checkbox") Title (renamed from "Name") Status (with the following options: "To Do", "In Progress", "Done") Link (with type "URL") Issue ID (with type "Number") Issue Key (with type "Text") Add any other fields you require to the database. Your database should look something like this Share the database to n8n. By default, the workflow will fill all the fields provided above, except for any other additional fields you add.
By n8n Team