Templates / Generate research proposals with GPT-4o, web search, and quality control agents

Generate research proposals with GPT-4o, web search, and quality control agents

Needs changes

by Cheng Siong Chin ✓ · 794 views · created 2026-03-04 · Content Creation, AI Summarization

Needs 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 this workflow does

This AI workflow has 21 nodes and runs manually, when you click “Execute workflow”. Along the way it connects OpenAI Chat Model, HTTP Request and SerpApi (Google Search).

How it runs

Trigger: Manually, when you click “Execute workflow”.

  1. Supervisor Agent (AI Agent): runs an AI agent, with model: Supervisor Model; 4 tools (Web Search Tool, Research Content Agent, Strategic Planning Agent, Funding Agency Research Tool); memory: Conversation Memory
  2. Parse Proposal Structure (Code): runs custom JavaScript code
  3. Quality Control Agent (AI Agent): runs an AI agent, with model: Quality Control Model; output parser: Quality Assessment Output
  4. Check Quality Score (If): checks a condition and branches into true / false
  5. Format Final Proposal (Edit Fields (Set)): sets 4 fields: status, proposal_title, quality_score…
  6. Flag for Revision (Edit Fields (Set)): sets 4 fields: status, quality_score, weaknesses…
  7. Prepare Storage Data (Edit Fields (Set)): sets 2 fields: timestamp, proposal_id
  8. Store Proposal Results (Data table): uses Data table

Services it uses

OpenAI Chat ModelHTTP RequestSerpApi (Google Search)

Before you upgrade to n8n 3.0

1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:

  • SerpApi (Google Search) in Web Search Tool: no direct replacement: call the SerpApi REST API with an HTTP Request tool, or use a verified community node.
Removed in 3.0Replace 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)

From the author

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…

Excerpt from Cheng Siong Chin's description on n8n.io.

View the original on n8n.io → Check your own copy

Get the weekly “what broke” email

New templates, newly broken ones, and n8n release changes. One short email a week.

Form not loading? Subscribe here.