How does the knowledge base ingestion work?

Upload PDFs or paste URLs into an admin page (Webtwizz scaffolds the form). The AI scaffolds a route that fetches/parses the content, chunks it into ~500-token segments with overlap, and stores embeddings in pgvector (Postgres extension via Supabase). Re-ingestion is incremental - only changed docs re-embed.

How accurate is RAG vs fine-tuning?

RAG is right for almost everyone. Fine-tuning is expensive, slow, and brittle when your docs update. RAG retrieves fresh context per query, which is why the answer can include "this changed last week" without retraining. Keep prompt engineering tight: instruct the model to refuse if retrieval is empty.

Can users see which document an answer came from?

Yes. The AI scaffolds citations inline - each answer ends with a "Sources:" block listing the doc titles and URLs the model pulled from. Clicking a citation deep-links to the source. Trust signal users actually look at.

How much does it cost to run per conversation?

Roughly $0.01-$0.05 per conversation on Claude Haiku or GPT-4o-mini for typical Q&A length. Embeddings are ~$0.0001 per chunk, one-time at ingestion. So a 100-page doc set costs cents to embed; 1,000 user conversations a month costs $10-$50 in API spend. Compare to $990 per 1,000 resolutions on Intercom Fin.

Can it be embedded in another site (widget on a blog, in-app help)?

Yes. Webtwizz scaffolds an embed snippet (a script tag + iframe) that renders the chat in any website. Auth is optional - anonymous users get a session ID; logged-in users get history attached to their account.

Build an AI Chatbot with Knowledge Base

Upload your docs. The AI answers questions grounded in your content, with citations. Skip Intercom Fin's $0.99 per resolution.

Webtwizz AI Full-Stack Builder Interface Preview

Saved per 1,000 chats vs Intercom Fin

Chat UI + RAG + ingestion wired

Citations on every answer

Vendor model lock-in (swap providers)

01 / What you get

AI Chatbot with Knowledge Base, generated.

Click Generate from the box above. Real Next.js code, real database, real integrations - not a sandbox. Each piece below ships in the first prompt.

Streaming chat UI with markdown rendering and code-block syntax highlighting

Knowledge base ingestion: upload PDFs, paste text, crawl URLs - all chunked and embedded

RAG retrieval: every answer cites the source documents it pulled from

OpenAI or Anthropic backend, swap models without changing the UI

Conversation history per user, searchable, exportable

Token usage tracking per conversation so you can audit cost per user

The same shape becomes

4 variants you can ship.

Customer support bot

Docs-grounded, ticket creation if it can't answer, multi-language, escalation rules.

Sales assistant

Catalog and pricing-aware, lead capture mid-conversation, demo-booking handoff.

Internal HR / IT bot

Employee Q&A on policies, IT troubleshooting, SSO-aware so it's on the right account.

In-product docs assistant

Embedded in your app, context-aware of which page the user is on.

Pixel-perfect control over every detail

Fine-tune typography, colors, spacing, and layouts with precision. See changes instantly as you design.

Built-in content and data

Manage your content directly in the builder, or connect a database for dynamic data like products, blog posts, and user accounts. No technical setup needed.

AI that actually builds

Describe what you want and watch it come to life. The AI creates pages, adds features, fixes issues, and refines your app through natural conversation.

Layers panel

See your entire page structure at a glance. Select, reorder, and nest elements with drag and drop precision.

Custom components

Build once, reuse everywhere. Create your own components and drop them into any page instantly.

Pages panel

Manage all your pages in one place. Add, duplicate, and organize your site structure effortlessly.

For people who hate $99-per-seat tools.

→Support teams replacing tier-1 with a bot trained on their docs

→SaaS companies building "ask the docs" search inside their product

→Agencies offering chatbot setups to clients as a service

→Founders who need a docs assistant before they have a support team

Powerful integrations

Payments, database, AI, email, analytics. Wired up the moment you click connect.

Stripe

Payments

Supabase

Database & Auth

OpenAI

AI · GPT

Anthropic

AI · Claude

Resend

PostHog

Analytics

Sentry

Errors

Suggest an integration

Why generate it instead of buying it.

“

Intercom Fin charges $0.99 per resolution. At 1,000 questions a month that's $12,000 a year and you don't own the conversations or the model choice.

“

You pick the model (Claude, GPT, open-weight via Ollama later), the embeddings (OpenAI, Cohere, local), and the vector store (pgvector, Pinecone). When prices drop or a better model ships, you swap one line.

Head-to-heads: vs Lovable · vs Bolt · vs v0 · vs Replit

Frequently Asked Questions

More ai chatbots you can ship.

SaaS with Subscription Billing

Login, Stripe Checkout, plan limits, customer portal - the four pieces every paid SaaS needs, generated and wired up. Skip the boilerplate, ship the actual product.