Skip to content
NEWMarketplace and the trig8n Agent: sell what you build, and get plans and changes that are tested before you see them. See what is new

Library / Content Writing & Generation

Content Writing & Generation

Generate Research Reports with OpenAI, Web Search and Telegram

When you run it or another workflow calls it, an OpenAI agent searches news, Wikipedia and the web, writes a report and shares it via Drive, Gmail and Telegram.

What it does

# 📋 Research Report Workflow 🧠💻 This workflow generates a professional PDF research report on a given topic, sends it via Telegram, and emails🚀 --- ## 🔍 Query Refiner - What it does: Refines the input topic for better readability. 🧹 - Input: Topic from the HTTP Request (e.g., "the best ai models 2025"). - Output: Formatted topic (e.g., "The Best AI Models 2025"). - ✨ Detail: Capitalizes words and ensures "AI" is uppercase. --- ## 📊 Aggregate Research Data - What it does: Collects research data for the topic. 📚 - Input: Refined topic. - Output: Research data (introduction, summary, key findings, etc.) with a timestamp. - ⏰ Note: The timestamp is used to date the report. --- ## 🔗 Merge Split Items - What it does: Combines and organizes research data into sections. 🗂️ - Input: Data from Aggregate Research Data. - Output: Structured JSON with sections like introduction, key_findings, sources. - 📑 Purpose: Prepares data for the PDF report. --- ## 📝 Generate PDF HTML - What it does: Creates an HTML template for the PDF report. 🖥️ - Input: Refined topic and research data. - Output: HTML content, file name (e.g., research-report-the-best-ai-models-2025-2025-04-09.pdf), and formatted date. - 🎨 Features: - Professional styling (Helvetica, Georgia fonts, deep blue accents). - Sections: Cover page, introduction, summary, key findings, etc. - Escapes special characters to prevent HTML errors. - ⏳ Timestamp Fix: Stores rawTimestamp and formattedDate (e.g., "April 9, 2025"). --- ## 📄 Convert HTML to PDF (PDFShift) - What it does: Converts the HTML to a PDF using the PDFShift API. 🖨️ - Input: HTML content from the previous node. - Output: JSON response with a URL to the generated PDF. - 🔑 Requirement: Needs a valid PDFShift API key. - ⚠️ Note: Outputs a URL, not the PDF binary data. --- ## ⬇️ Download PDF - What it does: Downloads the PDF from the URL provided by PDFShift. 📥 - Input: PDF URL from the Convert HTML to PDF node. - Output: Binary PDF data (MIME type: application/pdf, ~98 KB). - 📛 File Name: Uses the file name from the previous node (e.g., research-report-the-best-ai-models-2025-2025-04-09.pdf). --- ## 📱 Gmail/Telegram - What it does: Sends the PDF to a Gmail/Telegram chat. 💬 - Input: PDF binary data and metadata (topic, formatted date). - Output: Sends the PDF as a document to the spe

The steps

  1. OpenAI Chat Model
  2. Simple Memory
  3. Search News
  4. Wikipedia
  5. OpenAI Chat Model1
  6. Query Refiner
  7. Research AI Agent
  8. Google Search Web
  9. SerpApi
  10. Structured Output Parser
  11. Split Out
  12. Input Validation
  13. Parse Research Output
  14. Merge Split Items

85 steps in total.

Similar automations