Shun Nakayama
Founder of Human Beings Inc. | Automation Specialist Specializing in n8n workflows and AI integration to streamline business processes. I help companies save time and focus on what matters.
Templates by Shun Nakayama
Ai-driven Instagram reels creation and publishing with GPT, Creatomate and Slack
Automate your Instagram growth strategy by generating and posting viral Reels using AI and Creatomate. This workflow plans content topics based on trends, generates video assets, and handles the approval and posting process—all without manual video editing. How it works Schedule Trigger: Runs every day at 9:00 AM. Topic Planning: Checks past topics from Google Sheets to avoid duplicates, then uses OpenAI (GPT-4o) to generate a new quiz-style content plan. Video Generation: Uses Creatomate to generate a video based on a template, dynamically inserting the AI-generated text and images. Approval Loop: Sends the generated video to Slack for human review. Posting: Once approved in Slack, the workflow automatically uploads the Reel to Instagram. Logging: Saves the new topic to Google Sheets and notifies Slack upon successful publication. Setup steps Configure Credentials: OpenAI: For generating content plans. Creatomate: For video rendering. Google Sheets: For tracking past topics. Slack: For approval notifications. Facebook Graph API: For Instagram publishing. Google Sheets Setup: Create a Google Sheet with columns: Question, Answer, Title, Date. Update the Get Past Topics and Save New Topic nodes with your Sheet ID. Creatomate Setup: Create a template in Creatomate or use an existing one. Update the Generate Video node with your template_id in the JSON body. Slack Setup: Create a channel for approvals. Update the Slack Approval Request and Slack Notification nodes with your Channel ID. Activate: Turn on the workflow to start automating your content pipeline!
By Shun NakayamaConvert task ideas to implementation plans with GPT-4o, Slack & Google Sheets
🚀 Turn your random ideas into concrete automation specs This workflow acts as your interactive "n8n Consultant." Simply write down a rough automation idea in Google Tasks (e.g., "Send weather updates to Telegram"), and the AI will research, design, and send a detailed n8n implementation plan to your Slack. ✨ Why is this workflow special? Unlike simple notification workflows, this features a Human-in-the-Loop review process. You don't just get a message; you get control. Regenerate: Not satisfied with the AI's plan? Click a button in Slack to have the AI rewrite it instantly. Archive: Happy with the plan? Click "Approve" to automatically save the detailed specs to Google Sheets and mark the task as complete. How it works Fetch: The workflow periodically checks a specific Google Tasks list for new ideas. AI Design: The AI (OpenAI) analyzes your idea and generates a structured plan, including node configuration and potential pitfalls. Human Review: It sends the plan to Slack with interactive "Approve" and "Regenerate" buttons. The workflow waits for your input. If Regenerate: The AI re-analyzes the idea and creates a new variation. If Approve: The workflow proceeds to the next step. Archive: The approved plan (Title, Nodes, Challenges) is saved to a Google Sheet for future development. Close: The original Google Task is updated with a "Processed" flag. How to set up Google Tasks: Create a new list named "n8n Ideas". Google Sheets: Create a new sheet with the following headers in the first row (A to H): Date Added Idea Title Status Recommended Nodes Key Challenges Improvement Ideas Alternatives Source Task ID Credentials: Configure credentials for Google Tasks, Google Sheets, OpenAI, and Slack. Configure Nodes: [Step 1] Fetch New Ideas: Select your Task list. [Step 4] Slack — Review & Approve: Select your target channel. [Action] Archive to Sheets: Select your Spreadsheet and Sheet. [Close] Mark Task Done: Select your Task list again. Requirements Google Tasks account Google Sheets account OpenAI API Key Slack account
By Shun NakayamaAutomatically optimize AI prompts with OpenAI using OPRO & DSPy methodology
This workflow implements cutting-edge concepts from Google DeepMind's OPRO (Optimization by PROmpting) and Stanford's DSPy to automatically refine AI prompts. It iteratively generates, evaluates, and optimizes responses against a ground truth, allowing you to "compile" your prompts for maximum accuracy. Why this is powerful Instead of manually tweaking prompts (trial and error), this workflow treats prompt engineering as an optimization problem: OPRO-style Optimization: The "Optimizer" LLM analyzes past performance scores and reasons to mathematically deduce a better prompt. DSPy-style Logic: It separates the "Logic" (Workflow) from the "Parameters" (Prompts), allowing the system to self-correct until it matches the Ground Truth. How it works Define: Set your initial prompt and a test case with the expected answer (Ground Truth). Generate: The workflow generates a response using the current prompt. Evaluate: An AI Evaluator scores the response (0-100) based on accuracy and format. Optimize: If the score is low, the Optimizer AI analyzes the failure and rewrites the prompt. Loop: The process repeats until the score reaches 95/100 or the loop limit is hit. Setup steps Configure OpenAI: Ensure you have an OpenAI credential set up in the OpenAI Chat Model node. Customize: Open the Define Initial Prompt & Test Data node and set your initialprompt, testinput, and ground_truth. Run: Execute the workflow and check the Manage Loop & State node output for the optimized prompt.
By Shun NakayamaPodcast to X (Twitter) pipeline with OpenAI Whisper, GPT-4o & Slack approval
Turn your favorite podcast episodes into engaging social media content automatically. This workflow fetches new episodes from an RSS feed, transcribes the audio using OpenAI Whisper, generates a concise summary using GPT-4o, and drafts a tweet. It then sends the draft to Slack for your review before posting it to X (Twitter). Who is this for Content creators, social media managers, and podcast enthusiasts who want to share insights without manually listening to and typing out every episode. Key Features Large File Support: Includes a custom logic to download audio in chunks, ensuring stability even with long episodes (preventing timeouts). Human-in-the-Loop: Nothing gets posted without your approval. You can review the AI-generated draft in Slack before it goes live. High-Quality AI: Uses OpenAI's Whisper for accurate transcription and GPT-4o for intelligent summarization. How it works Monitor: Checks the Podcast RSS feed daily for new episodes. Process: Downloads the audio (handling large files via chunking) and transcribes it. Draft: AI summarizes the transcript into bullet points and formats it for X (Twitter). Approve: Sends the draft to a Slack channel. Publish: Once approved by you, it posts the tweet to your X account. Requirements OpenAI API Key Slack Account & App (Bot Token) X (Twitter) Developer Account (OAuth2) Setup instructions RSS Feed: The template defaults to "TED Talks Daily" for demonstration. Open the [Step 1] RSS node and replace the URL with your target podcast. Connect Credentials: Set up your credentials for OpenAI, Slack, and X (Twitter) in the respective nodes. Slack Channel: In the [Step 12] Slack node, select the Channel ID where you want to receive the approval request.
By Shun NakayamaOptimize Instagram hashtags with GPT-4o & real engagement data via Graph API
Instagram Hashtag Generator Workflow This workflow automatically generates optimal hashtags for your Instagram posts by analyzing captions and fetching real-time engagement data. Key Features 100% Official API & Free: Uses ONLY the official Instagram Graph API. No expensive third-party tools or risky scraping methods are required. Safe & Reliable: Relying on the official API ensures compliance and long-term stability. Smart Caching: Includes a Google Sheets caching mechanism to maximize the value of the official API's rate limits (30 searches/7 days). Workflow Overview Caption Input: Set your caption manually or via a workflow trigger. AI Suggestions: GPT-4o-mini analyzes the caption and suggests 10 relevant hashtags, balancing popular (big words) and niche keywords. Official API Search (Instagram Graph API): Fetches Hashtag IDs using the ighashtagsearch endpoint. Retrieves engagement metrics (Average Likes, Average Comments) using the ID. Selection & Sorting: Sorts candidates by engagement metrics. Selects the top 5 most effective hashtags that balance relevance and engagement. Output: Returns the final list of hashtags as text. Setup Steps Import to n8n: Copy the content of workflowhashtaggenerator.json and paste it into your n8n canvas, or import the file directly. Credentials: OpenAI account: Connect your OpenAI credentials. Facebook Graph account: Connect your Facebook Graph API credentials. Configuration: Instagram Business ID: Update the YOURINSTAGRAMBUSINESSACCOUNTID placeholder in the Get Hashtag Info and Get Hashtag Metrics nodes with your actual Business Account ID. Google Spreadsheet ID: Update the YOURSPREADSHEETID placeholder in the Fetch Cached Hashtags and Save to Cache nodes. Adjustments: Filter Logic: You can adjust the sorting or filtering logic in the Aggregate & Rank Candidates node's JavaScript code (e.g., exclude tags with fewer than 1000 posts) if needed. Important Notes on API Limits The official Instagram Hashtag Search API (ighashtagsearch) allows for 30 unique hashtag queries per rolling 7-day period. Why this is fine: This workflow caches results in Google Sheets. Once a tag is fetched, it doesn't need to be queried again for a while, allowing you to build up a large database of tags over time without hitting the limit. Recommendation: Use mock data during initial testing to save your API quota.
By Shun Nakayama