Generate research proposals with GPT-4o, web search, and quality control agents
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: SerpApi (Google Search). 1 breaking item(s) found. Static check, last run 2026-10-19.
What to replace before upgrading
| Removed in 3.0 | Replace with |
|---|---|
| SerpApi (Google Search) Web Search Tool | No direct replacement: call the SerpApi REST API with an HTTP Request tool, or use a verified community node |
Nodes used (12)
- Manual Trigger
n8n-nodes-base.manualTrigger - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - AI Agent Tool
@n8n/n8n-nodes-langchain.agentTool - Http Request Tool
n8n-nodes-base.httpRequestTool - SerpApi (Google Search)
@n8n/n8n-nodes-langchain.toolSerpApi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - If
n8n-nodes-base.if - Edit Fields (Set)
n8n-nodes-base.set - Data table
n8n-nodes-base.dataTable - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Code
n8n-nodes-base.code
What it does
How It Works This workflow automates academic and professional research proposal generation using a multi-agent AI pipeline. It targets researchers, academics, grant writers, and R&D teams who need structured, high-quality proposals efficiently. The core problem it solves: manually drafting proposals is time-consuming, inconsistent, and prone to missing key elements like ethics, impact, and funding alignment. A Supervisor Agent orchestrates three specialist sub-agents, Research Content, Strategic Planning, and Ethics/Impact, each powered by dedicated AI models. A Funding Agency Research Tool and Web Search Tool supply real-time context. The generated proposal is parsed, then evaluated by a Quality Control Agent. Proposals meeting the quality threshold are formatted and stored; those falling short are flagged for human revision, ensuring only polished outputs reach storage. Setup Steps 1. Add OpenAI (or compatible) API credentials to all AI model nodes. 2. Configure Supervisor, Research Content, Strategic Planning, and QC Agent system prompts. 3. Set up Funding Agency Research Tool with target agency endpoints or search parameters. 4. Connect Web Search Tool credentials (e.g., SerpAPI or Tavily). 5. Configure storage node (Google Sheets/database) with target schema. 6. Set quality score threshold in the Check Quality Score node. Prerequisites - Web search API key (SerpAPI/Tavily) - Google Sheets or database credentials Use Cases - Grant proposal drafting for research institutions Customisation - Swap AI models per agent for cost/performance balance Benefits - Cuts proposal drafting time by 70–80%