Blog — Lumen Chat - Lumen Chat

How Vector Search Actually Finds the Right Answer

A plain explanation of similarity search — how an AI chatbot finds the right chunk of your docs to answer from, and why it works by meaning, not keywords.

August 31, 20263 min read

security

Prompt Injection and Why Source-Grounded Bots Are Safer

What prompt injection is, why it's a real risk for AI chatbots, and how grounding answers in scoped, trusted content reduces the attack surface.

August 28, 20263 min read

embeddings

Chunking and Embeddings 101: How Your Docs Become Searchable

A plain explanation of chunking and embeddings — the two steps that turn a document into something an AI chatbot can search and answer from.

August 26, 20263 min read

ai chatbot

Grounded vs. Hallucinated Answers: How to Tell the Difference

What separates an AI answer that's actually grounded in your documentation from one that's confidently made up — and why the distinction matters for support.

August 24, 20263 min read

ai chatbot

Anatomy of One Chatbot Conversation

A single, realistic support conversation annotated turn by turn — what's actually happening behind each reply, from retrieval to escalation.

August 22, 20263 min read

ai chatbot

Why "Just Add ChatGPT" Doesn't Work for Customer Support

A general-purpose AI model dropped into a support widget doesn't know your product. Here's why grounding it in your own docs is the part that actually matters.

August 22, 20262 min read

ai chatbot

5 Things Everyone Gets Wrong About AI Chatbots for Support

Common assumptions about AI chatbots for customer support — more data, a human tone, model choice — and why they don't hold up in practice.

August 20, 20263 min read

ai chatbot

Tokens and Context Windows, Explained Without the Jargon

What a token actually is, why AI pricing is measured in them, and why a chatbot can seem to 'forget' things you said earlier in a conversation.

August 20, 20263 min read

case study

We Pointed Lumen Chat at Our Own Docs. Here's What It Couldn't Answer.

We ran our own help docs and blog through Lumen Chat and published the real list of questions it fell back on — and what we fixed because of it.

August 20, 20263 min read

security

We Spent a Week Trying to Jailbreak Our Own Chatbot. Here's What Actually Worked.

A week of real attempts to break Lumen Chat's guardrails — what worked, what didn't, and what we changed because of it.

August 20, 20264 min read

ai chatbot

What Does It Actually Cost to Run an AI Chatbot?

A plain-English breakdown of what actually drives AI chatbot costs — tokens, embeddings, storage — and how to think about build-it-yourself versus buying.

August 20, 20263 min read

rag

What Is RAG (Retrieval-Augmented Generation), Explained for Non-Engineers

A plain-language explanation of retrieval-augmented generation — the technique behind AI chatbots that answer from your own documentation instead of guessing.

August 20, 20263 min read

best practices

Seasonal Traffic Prep: Getting Your Chatbot Ready for a Launch or Sale

A pre-spike checklist for AI chatbots — content gaps, source freshness, and escalation limits — before a product launch, sale, or seasonal surge.

August 19, 20263 min read

dashboard

A Tour of the Lumen Chat Dashboard for New Teams

A walkthrough of the Lumen Chat dashboard — overview stats, document sources, widget settings, and conversations — for teams getting started.

August 19, 20262 min read

documentation

Writing Docs That AI Chatbots Actually Answer Well From

Practical formatting and structure tips that make your existing documentation easier for an AI chatbot to retrieve and answer from accurately.

August 18, 20262 min read

document sources

Setting Up Auto-Sync So Your Chatbot Never Goes Stale

How auto-sync works for Notion, Google Drive, and website sources in Lumen Chat, and how to choose the right sync interval.

August 17, 20262 min read

widget

Embedding the Chat Widget on Your Site in 5 Minutes

How to add the Lumen Chat widget to any website — React, plain HTML, or otherwise — with a single script tag, and how to keep the embed key secure.

August 15, 20262 min read

widget

Customizing Your Chat Widget to Match Your Brand

A walkthrough of every widget setting in Lumen Chat — title, colors, avatar, starter questions, and fallback behavior — so it looks like it belongs on your site.

August 13, 20262 min read

pdf

Uploading PDFs and Files as a Chatbot Source

How to add PDFs, Word docs, Markdown, and plain text directly to Lumen Chat when your content doesn't live in a connected platform.

August 12, 20262 min read

website crawling

Turning Your Website Into a Chatbot Source (No Docs Platform Needed)

How to point Lumen Chat at your public site, crawl your help center or marketing pages, and use them as chatbot knowledge without touching Notion or Drive.

August 10, 20262 min read

google drive