How BeGlobal automated commercial offer creation with n8n and PromptGorillas
BeGlobal, a Dutch branded corporate gifts company, worked with the agency PromptGorillas to automate its proposal process. An n8n-orchestrated pipeline now turns a chat intake into a finished Google Slides offer, which removed the main bottleneck on how many offers the team could send.
The problem
BeGlobal could only create and send about 50 offers a year because each proposal was built by hand. Sales reps searched a catalog of roughly 100,000 products, then assembled a presentation with images and descriptions matched to the occasion. Past offers and CRM data for existing clients were not reused.
How they did it
- A custom frontend (built with Cursor) hosts a chat agent that collects product type, budget per unit, occasion, client name and domain, and whether the client is new or existing, then confirms the inputs with the user.
- An n8n workflow checks whether the client already exists and, if so, pulls CRM data and historical offers.
- An AI agent (GPT) node and code nodes build precise queries against Supabase, which stores the roughly 100,000 products. Results go back to the frontend via a webhook.
- n8n sends the selected product images through Nano Banana to generate themed, occasion-specific visuals.
- n8n duplicates slides from a Google Slides template in Google Drive, one per selected product, and fills in details, prices and the generated images.
Results
- As reported by n8n, offers sent per year rose roughly tenfold, from ~50 to almost 500.
- As reported by n8n, creating one offer went from a few hours manually to <1 min of workflow execution.
- As reported by n8n, the end-to-end workflow takes around 52 seconds to produce a full presentation.
- Long-term revenue metrics are still being collected, but the team can serve a larger pipeline with the same or less effort.
As reported by the source (n8n customer case study); AgentGid did not measure these figures.
This suits a team with a structured product catalog, someone comfortable with n8n, Supabase and API wiring, and a reusable slide template; the advanced difficulty rating is fair. The roughly tenfold and 52-second figures are reported by n8n, not independently measured, and the case gives no revenue results yet. If you want a free open-source orchestrator, Dify (Free) is the closest alternative.
The agents used here
A workflow automation platform with a visual editor, several hundred integrations and native AI agent nodes. It can be self-hosted or used as a cloud…
- Price
- Free
- Gid Score
- 75 #1 in Automation
AI coding editor and agent platform with a desktop app, a CLI, web and mobile agents, and cloud agents that run tasks in remote environments. It offe…
- Price
- Free + $20/mo
- Gid Score
- 72 #1 in IDEs
Similar use cases
Triage support tickets with an n8n AI Agent and confidence-based routing
An n8n workflow cleans and validates incoming tickets with plain code nodes, uses an AI Agent only to classify urgency and type, and routes each ticket based on how confident the …
The suggested routing: above 0.85 processes autonomously, 0.6-0.85 is processed but flagged for review, and below 0.6 goes to a human.
Run nanoMuse, an open-source personal agent, across phone, desktop and web
The nanoMuse project is an open-source personal agent that runs on Android, iOS, Windows, macOS, Linux and the browser under one account. It can operate apps through their screens…
The article gives no performance metrics; it is a project README.
How Healthie automated sales call coaching and churn alerts with Zapier Agents
Healthcare software company Healthie built Zapier Agents that review sales calls, draft follow-ups and flag churn risks across its systems. Zapier reports large weekly time saving…
Zapier reports 60+ hours saved per week across Sales and CS.
Guides
AI Agent vs Chatbot vs Agentic AI: What Is the Difference?
Plain-language definitions of AI agents, chatbots, agentic AI, LLMs, workflows and skills, how they relate, and how to tell which one you are looking at, with real examples.
Best AI Agents in 2026: Live Rankings by Category
The leading AI agents for coding, design, research, data, marketing, sales, support, HR, finance, legal, DevOps and security, ranked by public usage data that refreshes daily, with prices and free options.
How to Build an AI Agent: No-Code Builders, Frameworks and SDKs
A practical guide to building your first AI agent: choosing between no-code builders, open-source frameworks and model vendors' SDKs, the core agent loop, tools, guardrails and testing, with live usage data for each option.
What Is an AI Agent? A Practical Explanation With Real Examples
What makes software an AI agent, how agents differ from chatbots and plain language models, the main types in use today and how to judge one.