Detect hallucinations using specialised Ollama model bespoke-minicheck
Fact-Checking Workflow Documentation Overview This workflow is designed for automated fact-checking of texts. It uses AI models to compare a given text with a list of facts and identify potential discrepancies or hallucinations. Components Input The workflow can be initiated in two ways: a) Manually via the "When clicking 'Test workflow'" trigger b) By calling from another workflow via the "When Executed by Another Workflow" trigger Required inputs: facts: A list of verified facts text: The text to be checked Text Preparation The "Code" node splits the input text into individual sentences Takes into account date specifications and list elements Fact Checking Each sentence is individually compared with the given facts Uses the "bespoke-minicheck" Ollama model for verification The model responds with "Yes" or "No" for each sentence Filtering and Aggregation Sentences marked as "No" (not fact-based) are filtered The filtered results are aggregated Summary A larger language model (Qwen2.5) creates a summary of the results The summary contains: Number of incorrect factual statements List of incorrect statements Final assessment of the article's accuracy Usage Ensure the "bespoke-minicheck" model is installed in Ollama (ollama pull bespoke-minicheck) Prepare a list of verified facts Enter the text to be checked Start the workflow The results are output as a structured summary Notes The workflow ignores small talk and focuses on verifiable factual statements Accuracy depends on the quality of the provided facts and the performance of the AI models Customization Options The summarization function can be adjusted or removed to return only the raw data of the issues found The AI models used can be exchanged if needed This workflow provides an efficient method for automated fact-checking and can be easily integrated into larger systems or editorial workflows.
By Guido ZockollExtract website intelligence & classify ecommerce URLs with Gemini & Firecrawl to Google Sheets
Description This n8n template automates website analysis and ecommerce URL classification using AI. It scrapes a website, extracts business intelligence, maps all internal pages, and categorises them into products, categories, or non-commerce pages. All outputs are saved in Google Sheets for easy access. --- Use cases Lead enrichment for sales and marketing teams Ecommerce product & category discovery Competitor website analysis Website audits and content mapping Market and industry research --- How it works A user submits a website URL via an n8n form. The homepage is scraped and cleaned. AI extracts company insights (value proposition, industry, audience, B2B/B2C). Firecrawl maps all internal URLs. URLs are enriched with metadata. AI classifies each URL as product, category, or other. Results are written into structured Google Sheets tabs. --- How to use Import the workflow into n8n. Connect Google Sheets, Firecrawl, and AI credentials. Update the Google Sheets document links. Open the form URL and submit a website. Let the workflow run and review the results in Sheets. --- Requirements n8n (self-hosted or cloud) Firecrawl API key Google Gemini or compatible LLM credentials Google Sheets account --- Customising this workflow Change AI prompts to match your niche (SaaS, ecommerce, services). Add filters to exclude unwanted URLs (blogs, legal pages, etc.). Extend Sheets with scoring, tagging, or lead qualification logic. Replace the LLM with another supported model if needed. --- What this template demonstrates End-to-end website intelligence extraction Safe, rule-based AI classification (no hallucinations) Scalable URL processing with batching Clean data pipelines into Google Sheets Practical AI usage for real business workflows This template is designed to work out-of-the-box for website intelligence, ecommerce mapping, and lead research. Feel free to reach out for custom implementation or enhancements: 📧 Email: @dinakars2003@gmail.com
By Dinakar Selvakumar