🤝 Top Collaborators
.png&w=640&q=75)
🤓 Latest Submissions
FlowForge: Natural Language to n8n Workflow JSON
FlowForge is an open source tool that converts natural language descriptions into importable n8n workflow JSON using a fine tuned Gemma model trained entirely on AMD hardware. The problem is simple. Building n8n automations by hand takes time and requires knowing the platform's node structure by heart. General purpose language models are surprisingly bad at this task since n8n workflow JSON has a strict schema with node types connections and parameters that must all line up correctly. We built a full pipeline from scratch. Two thousand seven hundred eleven real n8n templates were collected cleaned to eighteen hundred and enriched three times using an LLM to produce natural language prompts for each workflow giving us fifty four hundred training examples split into forty five hundred ninety training rows and eight hundred ten held out rows for evaluation. Training ran on a single AMD Radeon PRO W7900 with forty eight gigabytes of VRAM using LoRA rank sixteen on Gemma 3 4B with plain PyTorch and PEFT since Unsloth segfaults on this RDNA3 card and Gemma 4 currently cannot be LoRA trained at all because PEFT does not support its custom linear layers. This alone took real debugging and is documented in the README as a known issue others can avoid. We measured results honestly using a three gate evaluation harness checking whether output is valid JSON whether it matches the n8n schema and whether it actually imports into a live n8n instance. The base Gemma 3 4B model produces zero valid workflows on held out prompts. Our fine tuned model produces valid schema compliant workflows twenty percent of the time and critically whenever it produces valid JSON that JSON is always schema correct meaning the remaining failure mode is simply cutting off on the longest workflows rather than generating the wrong structure. The full stack includes a FastAPI backend anyone can clone the repository run the training pipeline on their own AMD hardware and build on top of what we made.
12 Jul 2026
IntelScout AI — Live GTM Intelligence
IntelScout AI solves a critical problem for enterprise go-to-market teams: competitive intelligence that is fast, live, and immediately actionable.Traditional tools rely on static databases that are outdated the moment they are published. IntelScout AI takes a fundamentally different approach. When a user submits a research request, the platform triggers a live Bright Data SERP API crawl bypassing georestrictions, CAPTCHAs, and IP blocks that defeat ordinary scrapers. Depending on the selected depth, the system pulls 2, 10, or 30 pages of real-time web results scoped to the exact company, market, and focus areas the user specified.This raw data flows into an n8n workflow where it is passed to a Gemini AI agent with a structured prompt. The AI analyzes pricing signals, product launches, partnershipannouncements, hiring patterns, funding activity, and regional expansion moves then returns a fully structured JSON containing a sentiment score, categorized opportunities, risk signals, and a complete narrative report.A JavaScript processing node normalizes and validates this output before it is delivered back to the frontend via webhook response. The result renders as a visual dashboard: a Chart.js sentiment graph, color-coded metric cards, opportunity and risk insight panels, and a full intelligence report with section headers and sourced bullet points.The platform includes persistent user profiles, full research history stored locally, and a clean multi-page interface covering research, history, about, and contact all served from a single HTML file with no backend dependency beyond the n8n workflow.IntelScout AI was built as a working SaaS prototype demonstrating that Bright Data's live data infrastructure, combined with AI reasoning and n8n's workflow automation, can replace expensive static intelligence subscriptions with a system that is faster, more accurate, and fully auditable.
31 May 2026
