Synthesize and compare multiple LLM responses with OpenRouter council
This template adapts Andrej Karpathy’s LLM Council concept for use in n8n, creating a workflow that collects, evaluates, and synthesizes multiple large language model (LLM) responses to reduce individual model bias and improve answer quality.
🎯 The gist
This LLM Council workflow acts as a moderation board for multiple LLM “opinions”:
- The same question is answered independently by several models.
- All answers are anonymized.
- Each model then evaluates and ranks all responses.
- A designated Council Chairman model synthesizes a final verdict based on these evaluations.
- The final output includes:
- The original query
- The Chairman’s verdict
- The ranking of each response by each model
- The original responses from all models
The goal is to reduce single‑model bias and arrive at more balanced, objective answers.
🧰 Use cases
This workflow enables several practical applications:
- Receiving more balanced answers by combining multiple model perspectives
- Benchmarking and comparing LLM responses
- Exploring diverse viewpoints on complex or controversial questions
⚙️ How it works
- The workflow leverages OpenRouter, allowing access to many LLMs through a single API credential.
- In the Initialization node, you define:
- Council member models: Models that answer the query and later evaluate all responses
- Chairman model: The model responsible for synthesizing the final verdict
- Any OpenRouter-supported model can be used: https://openrouter.ai/models
- For simplicity:
- Input is provided via a Chat Input trigger
- Output is sent via an email node with a structured summary of the council’s results
👷 How to use
- Select the LLMs to include in your council:
- Council member models: Models that independently answer and evaluate the query. The default template uses:
- openai/gpt-4o
- google/gemini-2.5-flash
- anthropic/claude-sonnet-4.5
- perplexity/sonar-pro-search
- Chairman model: Choose a model with a sufficiently large context window to process all evaluations and rankings.
- Council member models: Models that independently answer and evaluate the query. The default template uses:
- Start the Chat Input trigger.
- Observe the workflow execution and review the synthesized result in your chosen output channel.
⚠️ Avoid using too many models simultaneously. The total context size grows quickly (n responses + n² evaluations), which may exceed the Chairman model’s context window.
🚦 Requirements
- OpenRouter API access configured in n8n credentials
- SMTP credentials for sending the final council output by email (or replace with another output method)
🤡 Customizing this workflow
- Replace the Chat Input trigger with alternatives such as Telegram, email, or WhatsApp.
- Redirect output to other channels instead of email.
- Modify council member and chairman models directly in the Initialization node by updating their OpenRouter model names.
n8n Workflow: Basic Chat Trigger with Email and HTTP Request
This n8n workflow demonstrates a foundational setup for interacting with a chat system, processing messages, and then sending an email or making an HTTP request based on the chat input. It serves as a starting point for building more complex conversational AI applications or integrating chat interactions with other services.
What it does
This workflow outlines a basic structure for:
- Receiving Chat Messages: It starts by listening for incoming chat messages.
- Processing Chat Data: It includes nodes to manipulate and transform the incoming chat message data.
- Conditional Actions: It provides placeholders for taking actions like sending an email or making an HTTP request, which can be triggered based on the content of the chat message (though the specific logic for this is not fully defined in the provided JSON).
Prerequisites/Requirements
- n8n Instance: An active n8n instance to host and run the workflow.
- Chat Service Integration: A chat service configured to send messages to the "Chat Trigger" node (e.g., a custom chat application, a messaging platform with a webhook integration).
- Email Account (for Send Email node): An SMTP server configured as an n8n credential for sending emails.
- API Endpoint (for HTTP Request node): An external API or webhook endpoint if you intend to use the HTTP Request node.
Setup/Usage
-
Import the Workflow:
- Copy the provided JSON code.
- In your n8n instance, click "New" to create a new workflow.
- Go to the "Workflow" menu (three dots in the top right) and select "Import from JSON".
- Paste the JSON code and click "Import".
-
Configure the Chat Trigger:
- Locate the "When chat message received" (Chat Trigger) node.
- You will need to configure this node to connect to your specific chat service. This typically involves setting up a webhook URL in your chat service that points to the n8n webhook provided by this node.
-
Configure Credentials (if using Send Email or HTTP Request):
- Send Email: Click on the "Send Email" node. You will need to select or create an SMTP credential. Provide your SMTP server details (host, port, user, password, etc.).
- HTTP Request: Click on the "HTTP Request" node. Configure the URL, method (GET, POST, etc.), headers, and body as required by the API you intend to call. If the API requires authentication, you will need to set up appropriate credentials (e.g., API Key, OAuth2) within n8n.
-
Customize Data Transformation:
- The "Edit Fields" (Set), "Code", "Aggregate", and "Split Out" nodes are included for data manipulation. You will need to configure these nodes based on how you want to process the incoming chat message data and prepare it for subsequent actions.
- Edit Fields (Set): Use this to add, modify, or remove fields from the incoming data.
- Code: For advanced JavaScript logic to transform or analyze the chat message.
- Aggregate / Split Out: Useful for handling lists of items or structuring data for batch processing.
- The "Edit Fields" (Set), "Code", "Aggregate", and "Split Out" nodes are included for data manipulation. You will need to configure these nodes based on how you want to process the incoming chat message data and prepare it for subsequent actions.
-
Define Conditional Logic:
- Currently, the "Send Email" and "HTTP Request" nodes are not directly connected in a conditional flow. You would typically add a "Switch" node or "IF" node after the data processing steps to route the workflow based on the content of the chat message (e.g., if the message contains "email", send an email; if it contains "request", make an HTTP call).
-
Activate the Workflow:
- Once configured, save the workflow and activate it by toggling the "Active" switch in the top right corner of the n8n editor.
Related Templates
Track competitor SEO keywords with Decodo + GPT-4.1-mini + Google Sheets
This workflow automates competitor keyword research using OpenAI LLM and Decodo for intelligent web scraping. Who this is for SEO specialists, content strategists, and growth marketers who want to automate keyword research and competitive intelligence. Marketing analysts managing multiple clients or websites who need consistent SEO tracking without manual data pulls. Agencies or automation engineers using Google Sheets as an SEO data dashboard for keyword monitoring and reporting. What problem this workflow solves Tracking competitor keywords manually is slow and inconsistent. Most SEO tools provide limited API access or lack contextual keyword analysis. This workflow solves that by: Automatically scraping any competitor’s webpage with Decodo. Using OpenAI GPT-4.1-mini to interpret keyword intent, density, and semantic focus. Storing structured keyword insights directly in Google Sheets for ongoing tracking and trend analysis. What this workflow does Trigger — Manually start the workflow or schedule it to run periodically. Input Setup — Define the website URL and target country (e.g., https://dev.to, france). Data Scraping (Decodo) — Fetch competitor web content and metadata. Keyword Analysis (OpenAI GPT-4.1-mini) Extract primary and secondary keywords. Identify focus topics and semantic entities. Generate a keyword density summary and SEO strength score. Recommend optimization and internal linking opportunities. Data Structuring — Clean and convert GPT output into JSON format. Data Storage (Google Sheets) — Append structured keyword data to a Google Sheet for long-term tracking. Setup Prerequisites If you are new to Decode, please signup on this link visit.decodo.com n8n account with workflow editor access Decodo API credentials OpenAI API key Google Sheets account connected via OAuth2 Make sure to install the Decodo Community node. Create a Google Sheet Add columns for: primarykeywords, seostrengthscore, keyworddensity_summary, etc. Share with your n8n Google account. Connect Credentials Add credentials for: Decodo API credentials - You need to register, login and obtain the Basic Authentication Token via Decodo Dashboard OpenAI API (for GPT-4o-mini) Google Sheets OAuth2 Configure Input Fields Edit the “Set Input Fields” node to set your target site and region. Run the Workflow Click Execute Workflow in n8n. View structured results in your connected Google Sheet. How to customize this workflow Track Multiple Competitors → Use a Google Sheet or CSV list of URLs; loop through them using the Split In Batches node. Add Language Detection → Add a Gemini or GPT node before keyword analysis to detect content language and adjust prompts. Enhance the SEO Report → Expand the GPT prompt to include backlink insights, metadata optimization, or readability checks. Integrate Visualization → Connect your Google Sheet to Looker Studio for SEO performance dashboards. Schedule Auto-Runs → Use the Cron Node to run weekly or monthly for competitor keyword refreshes. Summary This workflow automates competitor keyword research using: Decodo for intelligent web scraping OpenAI GPT-4.1-mini for keyword and SEO analysis Google Sheets for live tracking and reporting It’s a complete AI-powered SEO intelligence pipeline ideal for teams that want actionable insights on keyword gaps, optimization opportunities, and content focus trends, without relying on expensive SEO SaaS tools.
Generate song lyrics and music from text prompts using OpenAI and Fal.ai Minimax
Spark your creativity instantly in any chat—turn a simple prompt like "heartbreak ballad" into original, full-length lyrics and a professional AI-generated music track, all without leaving your conversation. 📋 What This Template Does This chat-triggered workflow harnesses AI to generate detailed, genre-matched song lyrics (at least 600 characters) from user messages, then queues them for music synthesis via Fal.ai's minimax-music model. It polls asynchronously until the track is ready, delivering lyrics and audio URL back in chat. Crafts original, structured lyrics with verses, choruses, and bridges using OpenAI Submits to Fal.ai for melody, instrumentation, and vocals aligned to the style Handles long-running generations with smart looping and status checks Returns complete song package (lyrics + audio link) for seamless sharing 🔧 Prerequisites n8n account (self-hosted or cloud with chat integration enabled) OpenAI account with API access for GPT models Fal.ai account for AI music generation 🔑 Required Credentials OpenAI API Setup Go to platform.openai.com → API keys (sidebar) Click "Create new secret key" → Name it (e.g., "n8n Songwriter") Copy the key and add to n8n as "OpenAI API" credential type Test by sending a simple chat completion request Fal.ai HTTP Header Auth Setup Sign up at fal.ai → Dashboard → API Keys Generate a new API key → Copy it In n8n, create "HTTP Header Auth" credential: Name="Fal.ai", Header Name="Authorization", Header Value="Key [Your API Key]" Test with a simple GET to their queue endpoint (e.g., /status) ⚙️ Configuration Steps Import the workflow JSON into your n8n instance Assign OpenAI API credentials to the "OpenAI Chat Model" node Assign Fal.ai HTTP Header Auth to the "Generate Music Track", "Check Generation Status", and "Fetch Final Result" nodes Activate the workflow—chat trigger will appear in your n8n chat interface Test by messaging: "Create an upbeat pop song about road trips" 🎯 Use Cases Content Creators: YouTubers generating custom jingles for videos on the fly, streamlining production from idea to audio export Educators: Music teachers using chat prompts to create era-specific folk tunes for classroom discussions, fostering interactive learning Gift Personalization: Friends crafting anniversary R&B tracks from shared memories via quick chats, delivering emotional audio surprises Artist Brainstorming: Songwriters prototyping hip-hop beats in real-time during sessions, accelerating collaboration and iteration ⚠️ Troubleshooting Invalid JSON from AI Agent: Ensure the system prompt stresses valid JSON; test the agent standalone with a sample query Music Generation Fails (401/403): Verify Fal.ai API key has minimax-music access; check usage quotas in dashboard Status Polling Loops Indefinitely: Bump wait time to 45-60s for complex tracks; inspect fal.ai queue logs for bottlenecks Lyrics Under 600 Characters: Tweak agent prompt to enforce fuller structures like [V1][C][V2][B][C]; verify output length in executions
Automate invoice processing with OCR, GPT-4 & Salesforce opportunity creation
PDF Invoice Extractor (AI) End-to-end pipeline: Watch Drive ➜ Download PDF ➜ OCR text ➜ AI normalize to JSON ➜ Upsert Buyer (Account) ➜ Create Opportunity ➜ Map Products ➜ Create OLI via Composite API ➜ Archive to OneDrive. --- Node by node (what it does & key setup) 1) Google Drive Trigger Purpose: Fire when a new file appears in a specific Google Drive folder. Key settings: Event: fileCreated Folder ID: google drive folder id Polling: everyMinute Creds: googleDriveOAuth2Api Output: Metadata { id, name, ... } for the new file. --- 2) Download File From Google Purpose: Get the file binary for processing and archiving. Key settings: Operation: download File ID: ={{ $json.id }} Creds: googleDriveOAuth2Api Output: Binary (default key: data) and original metadata. --- 3) Extract from File Purpose: Extract text from PDF (OCR as needed) for AI parsing. Key settings: Operation: pdf OCR: enable for scanned PDFs (in options) Output: JSON with OCR text at {{ $json.text }}. --- 4) Message a model (AI JSON Extractor) Purpose: Convert OCR text into strict normalized JSON array (invoice schema). Key settings: Node: @n8n/n8n-nodes-langchain.openAi Model: gpt-4.1 (or gpt-4.1-mini) Message role: system (the strict prompt; references {{ $json.text }}) jsonOutput: true Creds: openAiApi Output (per item): $.message.content → the parsed JSON (ensure it’s an array). --- 5) Create or update an account (Salesforce) Purpose: Upsert Buyer as Account using an external ID. Key settings: Resource: account Operation: upsert External Id Field: taxid_c External Id Value: ={{ $json.message.content.buyer.tax_id }} Name: ={{ $json.message.content.buyer.name }} Creds: salesforceOAuth2Api Output: Account record (captures Id) for downstream Opportunity. --- 6) Create an opportunity (Salesforce) Purpose: Create Opportunity linked to the Buyer (Account). Key settings: Resource: opportunity Name: ={{ $('Message a model').item.json.message.content.invoice.code }} Close Date: ={{ $('Message a model').item.json.message.content.invoice.issue_date }} Stage: Closed Won Amount: ={{ $('Message a model').item.json.message.content.summary.grand_total }} AccountId: ={{ $json.id }} (from Upsert Account output) Creds: salesforceOAuth2Api Output: Opportunity Id for OLI creation. --- 7) Build SOQL (Code / JS) Purpose: Collect unique product codes from AI JSON and build a SOQL query for PricebookEntry by Pricebook2Id. Key settings: pricebook2Id (hardcoded in script): e.g., 01sxxxxxxxxxxxxxxx Source lines: $('Message a model').first().json.message.content.products Output: { soql, codes } --- 8) Query PricebookEntries (Salesforce) Purpose: Fetch PricebookEntry.Id for each Product2.ProductCode. Key settings: Resource: search Query: ={{ $json.soql }} Creds: salesforceOAuth2Api Output: Items with Id, Product2.ProductCode (used for mapping). --- 9) Code in JavaScript (Build OLI payloads) Purpose: Join lines with PBE results and Opportunity Id ➜ build OpportunityLineItem payloads. Inputs: OpportunityId: ={{ $('Create an opportunity').first().json.id }} Lines: ={{ $('Message a model').first().json.message.content.products }} PBE rows: from previous node items Output: { body: { allOrNone:false, records:[{ OpportunityLineItem... }] } } Notes: Converts discount_total ➜ per-unit if needed (currently commented for standard pricing). Throws on missing PBE mapping or empty lines. --- 10) Create Opportunity Line Items (HTTP Request) Purpose: Bulk create OLIs via Salesforce Composite API. Key settings: Method: POST URL: https://<your-instance>.my.salesforce.com/services/data/v65.0/composite/sobjects Auth: salesforceOAuth2Api (predefined credential) Body (JSON): ={{ $json.body }} Output: Composite API results (per-record statuses). --- 11) Update File to One Drive Purpose: Archive the original PDF in OneDrive. Key settings: Operation: upload File Name: ={{ $json.name }} Parent Folder ID: onedrive folder id Binary Data: true (from the Download node) Creds: microsoftOneDriveOAuth2Api Output: Uploaded file metadata. --- Data flow (wiring) Google Drive Trigger → Download File From Google Download File From Google → Extract from File → Update File to One Drive Extract from File → Message a model Message a model → Create or update an account Create or update an account → Create an opportunity Create an opportunity → Build SOQL Build SOQL → Query PricebookEntries Query PricebookEntries → Code in JavaScript Code in JavaScript → Create Opportunity Line Items --- Quick setup checklist 🔐 Credentials: Connect Google Drive, OneDrive, Salesforce, OpenAI. 📂 IDs: Drive Folder ID (watch) OneDrive Parent Folder ID (archive) Salesforce Pricebook2Id (in the JS SOQL builder) 🧠 AI Prompt: Use the strict system prompt; jsonOutput = true. 🧾 Field mappings: Buyer tax id/name → Account upsert fields Invoice code/date/amount → Opportunity fields Product name must equal your Product2.ProductCode in SF. ✅ Test: Drop a sample PDF → verify: AI returns array JSON only Account/Opportunity created OLI records created PDF archived to OneDrive --- Notes & best practices If PDFs are scans, enable OCR in Extract from File. If AI returns non-JSON, keep “Return only a JSON array” as the last line of the prompt and keep jsonOutput enabled. Consider adding validation on parsing.warnings to gate Salesforce writes. For discounts/taxes in OLI: Standard OLI fields don’t support per-line discount amounts directly; model them in UnitPrice or custom fields. Replace the Composite API URL with your org’s domain or use the Salesforce node’s Bulk Upsert for simplicity.