Most website chatbots do two things exceptionally well:
They answer like a broken FAQ widget, hallucinate when someone asks a real question, and when a prospect is actually ready to talk, they still fail to capture the lead properly.
So we built something better.
A real AI Sales Agent that:
We built it using:
And yes, it’s live and working on growthhub.io.
This guide is an exhaustive walkthrough of how we built it from scratch, including the architecture, prompts, workflows, pitfalls, cost breakdown, and how you can deploy the same system.
Imagine this:
A prospect lands on your site and asks:
“Do you do paid campaigns, and what’s your SEO methodology?”
Charlotte instantly answers with specific details from your website, not generic AI filler.
Then the prospect says:
“Cool. I’m interested. My name is Alex Smith, company TechCorp, email alex@techcorp.com, phone +1-555-123-4567.”
Charlotte confirms and instantly saves the lead into HubSpot. No human involved. No copy-paste. No lead lost.
This is not a chatbot.
This is a sales agent with knowledge, process, and actions.
A plain LLM chatbot is trained on general internet data. It does not automatically know your website content, pricing rules, processes, or case studies.
So when a visitor asks a question that’s not in its memory, it does what LLMs do best:
It guesses.
That’s how you get confident nonsense like:
RAG (Retrieval-Augmented Generation) fixes that.
RAG is the shift from AI being a “guessing engine” to a “knowledge-driven assistant.” It retrieves verified content from your knowledge base at the moment the question is asked, then generates an answer using that content.
RAG combines:
That’s why our agent can answer:
… without making anything up.
Let’s talk economics, because this is where most “AI agent” solutions quietly become expensive.
If you self-host n8n, your automation engine is basically yours forever. No per-seat platform tax, no feature gating, and no “pay more to unlock basic automation” nonsense.
Your ongoing costs become mainly:
In other words: once it’s set up, your agent can run 24/7 for the cost of a coffee or two per month, depending on traffic.
HubSpot’s AI features use credits, a flexible currency consumed by AI actions such as:
Most plans include monthly credits, but if you exceed them, you add more capacity using credit packs (commonly sold in 1,000-credit packs for around $10/month) or pay overages. Admins can set caps to control spend.
This model is fine, but it means your true cost is not “the subscription.”
It’s subscription + usage.
A single conversion (meaning: a real conversation + qualification + lead capture) is rarely one action. It may involve multiple AI responses, follow-up questions, enrichment, and routing logic.
So while HubSpot is a great platform, total cost per captured lead can quickly approach a few dollars per lead, depending on usage and the number of AI actions triggered.
Our agent is built to be lean:
So instead of paying per seat and per AI action, you mostly pay for:
That’s the cost model you want if you care about ROI.
If you want this live on your site without spending your weekend wrestling with workflows, chunking issues, and HubSpot property mapping, we’ve got you.
Included:
Result: A 24/7 sales agent that answers intelligently, qualifies leads, and books calls.
Want it? Book a call and we’ll show you a demo on your own site.
L
et’s be blunt: not everyone needs an AI agent.
But if your business lives or dies by speed, accuracy, and lead follow-up, then a RAG-powered agent is not a “nice-to-have.” It’s a competitive advantage.
In Mastering RAG for AI Agents, Jason Brener frames RAG as the shift from an AI that guesses to an AI that becomes a knowledge-driven assistant, because it retrieves relevant information from external sources at the moment a question is asked. In plain English: it stops making things up and starts behaving like an expert with access to your actual documentation.
That’s why RAG is useful far beyond chatbots. It’s the foundation of AI agents that can operate safely in real-world business environments: customer support, finance, legal, healthcare, operations, and of course, sales.
RAG is worth the effort when any of these are true:
If being wrong costs you money, trust, or legal problems, use RAG.
Here’s the exhaustive matrix of where RAG-powered agents shine, why they matter, and what they replace.
| Use Case | What the Agent Does | Why RAG Matters | Typical ROI |
|---|---|---|---|
| Sales Agent (B2B services, agencies) | Answers complex service questions, qualifies leads, captures details, books calls. | Without RAG it guesses. With RAG it retrieves your site content, making answers accurate and trustworthy. | More qualified calls, fewer lost leads, faster response time (24/7). |
| Customer Support Agent | Resolves tickets, answers FAQs, guides troubleshooting, escalates when needed. | Support knowledge changes constantly. RAG retrieves the right help article and prevents hallucinations. | Ticket deflection, lower support load, faster resolution times. |
| Compliance / Legal / Insurance Agent | Retrieves policies, clauses, regulations, explains them, generates grounded responses. | These domains require traceable sources. RAG enables citations and safe reasoning. | Reduced risk, faster internal answers, fewer escalations to legal teams. |
| Healthcare Research Agent | Retrieves studies/guidelines, summarizes evidence, supports research workflows. | Recency and accuracy are critical. RAG pulls current sources instead of relying on model memory. | Faster research, better evidence summaries, improved consistency. |
| Finance / Market Intelligence Agent | Retrieves reports, filings, market updates, answers research questions with citations. | Finance data becomes outdated quickly. RAG fixes recency and improves credibility. | Analyst speed, better insights, less manual research work. |
| Internal Company Knowledge Agent | Answers questions from SOPs, onboarding docs, wikis, runbooks, policies. | Internal docs drift constantly. RAG lets you update knowledge without retraining a model. | Less time wasted searching docs, faster onboarding, fewer internal interruptions. |
| Engineering / Manufacturing Agent | Retrieves specs, manuals, incident reports, supports technicians & engineers. | Procedural accuracy matters. RAG grounds answers in approved documentation. | Reduced errors, faster troubleshooting, lower downtime. |
| Ecommerce Assistant (Product Recommendations) | Recommends products, compares items, answers shipping/spec questions, suggests bundles and upsells. | Without RAG it hallucinates features. With RAG it retrieves specs, FAQs, policies, and content from your catalog and HubDB. | Higher conversion rate, higher AOV, fewer returns, fewer support tickets. |
If you’re wondering whether this applies to your business, here’s a deeper breakdown of who benefits most and why.
If you sell services, your website visitors always ask the same things:
A static site can’t respond. A typical chatbot guesses. And a human sales team replies too late.
A RAG sales agent fixes that by:
Bottom line: you stop losing leads because your website becomes interactive and sales-ready 24/7.
Support is where “hallucinations” become expensive.
RAG-powered support agents excel because they can retrieve exact troubleshooting steps from your documentation and respond with accuracy. They can also safely say “I can’t find that” instead of improvising.
ROI: fewer tickets, faster resolutions, happier customers, and less burnout for the team.
These domains are high-stakes: wrong answers can trigger regulatory issues or legal exposure.
RAG matters here because it can ground answers in retrieved policies, contract clauses, and regulations. This is where citations and transparency become critical.
ROI: faster internal answers, reduced compliance risk, fewer escalations.
Healthcare and clinical research require up-to-date evidence, not “whatever the model remembers.” RAG enables retrieval of relevant papers and guidelines before summarizing.
ROI: faster research workflows and more consistent summaries.
Finance is merciless about outdated data. Generic LLM answers can be wrong just because the world changed last week.
RAG agents retrieve recent filings, reports, and summaries before responding.
ROI: faster analysis, more grounded insight, less manual research.
If your company has:
… then you already have the knowledge base. Employees just can’t find it when they need it.
A RAG agent becomes an internal “expert helpdesk” that retrieves exactly the right section instantly.
ROI: faster onboarding, fewer interruptions, reduced “tribal knowledge” dependency.
Ecommerce is one of the most profitable RAG use cases because shoppers don’t ask polite, structured questions. They ask messy, human ones:
Traditional site search and filter menus are great… if your visitor already knows what they want. Most don’t.
A RAG-powered ecommerce agent can:
If your assistant uses only a generic LLM, it will hallucinate product features and make recommendations that sound good but aren’t true. That’s a refund magnet.
With RAG, the assistant retrieves product data from your catalog, your FAQs, and your policies, then generates recommendations grounded in real information.
If your store content is built on HubSpot CMS, you can store structured product data in HubDB (prices, SKUs, specs, categories, inventory status, links).
That enables a “best of both worlds” approach:
In practice, the agent can retrieve from both:
Result: a shopping assistant that feels like a real salesperson, but never lies about your products.
ROI: higher conversion rate, higher AOV, fewer support tickets, fewer returns.
If you’re reading this and thinking “ok, cool… but is this really worth doing?” here’s the honest answer:
If you sell anything complex, and you lose leads because people don’t get answers fast enough, yes.
Because the winning advantage isn’t “AI.” It’s:
And if you self-host n8n, your ongoing costs stay low because you mostly pay for usage (OpenAI calls + vector retrieval), not a platform subscription and credit overages.
One-time setup fee. Limited availability.
We’ll implement your AI sales agent end-to-end:
Result: A 24/7 sales assistant that answers like a pro, qualifies leads, and pushes them into HubSpot automatically.
If you want this live on your site, book a call now. We’ll show you a demo using your own content and tell you exactly what it would take to deploy.
Note: The €999 setup offer is limited-time and may be withdrawn once we hit capacity.
Alright, enough theory. If you want to build this yourself, here’s the exact blueprint we used, from a blank n8n canvas to a production-ready AI sales agent that retrieves answers from your website and saves leads into HubSpot.
You don’t need a full dev team, but you do need to follow the steps properly, because small mistakes (like indexing menus) turn “AI sales agent” into “expensive hallucination machine.” Let’s build it.
We start with a blank n8n canvas. This is where your AI agent lives.
Add the Chatbot Trigger node. This becomes the entry point for your website chat widget.
Add an AI Agent node to your canvas and connect the Chatbot trigger to it.
This is where most chatbots die. A system prompt is not copy, it’s policy. Here’s the version we used:
You are NAME OF YOUR AGENT, the COMPANY Sales Assistant.
Human, sharp, slightly witty, never cringe. Like a great agency rep.
### CORE KNOWLEDGE (ALWAYS TRUE - DO NOT SEARCH FOR THIS):
- Services: Paid Campaigns (Google Ads & Meta Ads), SEO, Web Design.
- Founders: NAME FOUNDERS (15+ years experience, Strategy & Growth).
- Manifesto: The AI-First Manifesto.
- Pricing: No fixed packages; custom scope, usually starts at €4k/month.
### INSTRUCTIONS:
- If the user asks about the above topics, answer directly from this Core Knowledge.
- When a user expresses interest in a project or booking a call, you MUST politely ask for their First Name, Email, Company Name, and Phone Number.
- Do NOT use the 'save_lead_to_hubspot' tool until you have collected ALL four pieces of information.
- Once you have ALL required lead details, use the 'save_lead_to_hubspot' tool to save their information.
- ONLY use the 'search_website' tool if the user asks for specific details NOT listed above.Add an OpenAI Chat Model node and connect it to the agent. Choose gpt-4o for quality or a lighter model for cost savings.
Add a Simple Memory node so the agent can retain context across turns.
Add a Respond to Webhook node that outputs the agent response in JSON back to the widget.
This is where your agent stops guessing and starts quoting your website.
Add an OpenAI Embeddings node using text-embedding-3-small.
Add a Pinecone Vector Store node set to Retrieve Documents (As Tool for AI Agent). Set:
Create a separate workflow named Scraper - Website Index.
Workflow outline:
Important: clean HTML properly, otherwise you’ll embed menus and your agent will answer with “Home | About | Contact”.
We’ll be honest: we didn’t start with a perfect, neatly organized knowledge base.
Like most businesses, our “knowledge” lived across a website, a few scattered documents, and whatever was in someone’s head. So we did the practical thing: we used our public website as the source of truth and built a scraper workflow to turn it into a searchable knowledge base.
That’s the beauty of RAG. You don’t need a formal knowledge base to start. You just need one reliable source of truth, and a way to extract, chunk, embed, and index it.
For most service businesses, the website already contains:
So scraping is the quickest way to ship a RAG-powered sales agent that answers accurately and stays up to date as your site evolves.
Once the pipeline is working, you can ingest content from almost anywhere. The pattern stays the same:
Here are common sources we build RAG pipelines from:
The website is great for sales. But the moment you add internal documents, you unlock much stronger use cases:
And because the knowledge lives outside the model, you can update it at any time without retraining anything. You simply re-run the ingestion workflow and your agent immediately has the latest knowledge.
If you want your agent to behave well, don’t mix everything into one messy index.
We recommend using Pinecone namespaces such as:
This lets the agent retrieve from the right source depending on the user intent, and prevents “internal” answers from leaking into public conversations.
Bottom line: scraping your website is the fastest way to start. But the real power comes when you plug in the rest of your business knowledge and let the agent answer like it’s been working with you for years.
This is where the agent becomes a system, not a toy.
Create a workflow named Tool - Add HubSpot Lead with an Execute Workflow Trigger.
Inputs:
Add a HubSpot node to create/update a contact using a HubSpot Private App token with the correct scopes.
Back in the main chatbot workflow, add a Call n8n Workflow Tool node and name it:
save_lead_to_hubspot
Description should enforce:
You can try our sales agent right here by clicking on the chat bottom right corner.
Test with a realistic flow:
A standard chatbot is a guessing machine.
This is different. With RAG, your AI agent retrieves verified content from your website and responds with grounded answers. It qualifies leads, captures details, and routes them straight into HubSpot, automatically.
And if you self-host n8n, your ongoing costs are mostly usage-based: OpenAI calls, Pinecone retrieval, and a HubSpot API write. That’s why this setup stays cheap, even as it scales.
If you want this running on your site without wasting weeks on trial and error, we’ll build it for you.
We’ll implement the full system, connect it to HubSpot, index your website, and deploy a production-ready AI sales agent on your site.
Want it? Book a call. We’ll show you a demo using your own website content.