Content
Website pages
URLs and sitemaps
Documents
PDF, Word, Excel
Videos
YouTube and transcripts
Why grounded answers hold up
RAG Chatbot on Your Content in Minutes
Connect your docs, files, and URLs so answers stay grounded in the source material your customers already trust.
7-day free trial · No charge during trial
Social proof
Keep answers grounded from day one
100%
Cited answers from your content
7+
Knowledge source formats
95+
Languages supported
Owned
Content sources supported
The Problem
RAG Chatbot breaks down when answers drift away from the docs, pages, and files people actually trust.
The Solution
Ground RAG chatbot in your real source material so answers stay tied to the content you already maintain instead of floating on model memory.
See it in action
See it go live
Watch a file turn into a trained website assistant that answers with your own content.
7-day free trial • No charge during trial • Live in minutes
Whole product
Everything in one place
Chat, files, tools, and deployment live together here.
Brand
Logo and colors
Match your website
Assistant tone
Brand-safe answers
Custom domain
assistant.yourbrand.com
Launch
Website widget
Bubble and iframe
Full-page assistant
Shareable destination
Lead capture
Forms and inbox
Learn
Top questions
Visitor intent
Content gaps
Missing answers
Source usage
Most-used content
Product scope
The product behind the free trial
Start with the builder flow, then keep model access, knowledge, deployment, and multimodal work connected as usage grows.
Content
Train on owned content
Import owned content, keep sources organized, refresh them as the site changes, and ground answers in approved material.
- Sitemap and URL import
- Documents and PDFs
- Grounded answers
Start here when the content library keeps growing but discovery is not getting easier.
Brand
Launch under your brand
Use InsertChat as the white-label layer for a customer-facing assistant that looks, sounds, and behaves like your own website experience.
- White-label controls
- Suggested prompts
- Custom domain
Use this when the assistant must feel client-ready, brand-safe, and publishable.
Learn
Learn what visitors need
Analytics show the questions visitors ask, where the assistant needs better sources, and which conversations indicate lead or support intent.
- Top questions
- Content gaps
- High-intent chats
Use this when marketing, digital, and content leaders need better visitor intent data.
Capabilities
What you get
See the main things you can do without extra tools.
PDFs, URLs & Docs
Upload PDFs, Word documents, paste URLs, connect sitemaps. Your AI indexes it all.
YouTube & Audio
Import YouTube videos and audio files. Your AI transcribes and learns from multimedia content.
Catalogs & Q&A Pairs
Upload product catalogs or structured Q&A pairs for precise, predictable answers.
Auto-Sync
Schedule re-crawls daily or weekly. Your AI always has the latest information.
Process
How it works
See the simple path from setup to live use.
1
Connect the sources that should drive answers
Use PDFs, URLs, videos, and synced docs so the assistant starts from your real material.
2
Set the grounding behavior
Control prompts, retrieval rules, and escalation paths before it starts answering real questions.
3
Refresh and review from live usage
Keep the answers aligned as content changes and new questions show up in live traffic.
Test it on your content
Connect the real documents, review the grounded answers, and confirm the source coverage before you rely on it for live traffic.
7-day free trial · No charge during trial
Comparison
Key differences
See the main differences side by side.
| Criteria | InsertChat | Others |
|---|---|---|
| Answers from your data | Yes — every answer cites your sources | No — generic internet knowledge |
| Accuracy | Restricted mode prevents off-topic answers | Hallucinations frequent |
| Setup time | Minutes — upload docs and go | Instant but inaccurate for your use case |
| Data freshness | Auto-sync keeps answers current | Knowledge frozen at training cutoff |
| Data privacy | Your data stays yours, zero training | Data may be used for model training |
| Cost | From $98/mo, content-trained assistants included | $20/mo for 1 model, no knowledge base |
Verified reviews
RAG Chatbot proof from real customers
Verified first-party reviews show 98% customer satisfaction. Teams use InsertChat to consolidate AI subscriptions, launch agents faster, and keep answers grounded in their own content.
"We had ChatGPT, Claude, and a couple of random tools floating around. InsertChat pulled the assistant workflow into one place, and now every source stays connected."
Whitney S.
Growth & Marketing Leader, Software marketplace
"I set up the customer agent without pulling in engineering. By the next day it was answering onboarding questions, handling billing basics, and cutting repeat tickets every morning."
Patrick B.
Head of Engineering, Customer onboarding platform
"We use InsertChat as the assistant hub for our site now. Need a doc answer, a branded response, or a quick content check? It is just there, instead of another tab someone has to remember."
Rebecca L.
Customer Experience Manager, Commerce platform
"The knowledge base was the part that surprised me. We connected our docs and FAQs, and the agent started giving useful answers without us rebuilding everything into some perfect format first."
Priya M.
Product Manager, B2B SaaS company
"I white-labeled a client agent in the first week and it looked like something we had built ourselves. That changed the conversation from "can we offer AI?" to "how many clients want this?""
Julien P.
Agency Founder, Client services agency
"We had ChatGPT, Claude, and a couple of random tools floating around. InsertChat pulled the assistant workflow into one place, and now every source stays connected."
Whitney S.
Growth & Marketing Leader, Software marketplace
"I set up the customer agent without pulling in engineering. By the next day it was answering onboarding questions, handling billing basics, and cutting repeat tickets every morning."
Patrick B.
Head of Engineering, Customer onboarding platform
"We use InsertChat as the assistant hub for our site now. Need a doc answer, a branded response, or a quick content check? It is just there, instead of another tab someone has to remember."
Rebecca L.
Customer Experience Manager, Commerce platform
"The knowledge base was the part that surprised me. We connected our docs and FAQs, and the agent started giving useful answers without us rebuilding everything into some perfect format first."
Priya M.
Product Manager, B2B SaaS company
"I white-labeled a client agent in the first week and it looked like something we had built ourselves. That changed the conversation from "can we offer AI?" to "how many clients want this?""
Julien P.
Agency Founder, Client services agency
"Our shoppers ask the same sizing and shipping questions all day. The agent answers those in our brand voice, and store staff only step in when someone actually needs a person."
Maya R.
Ecommerce Director, B2C apparel brand
"We use it before sales calls now. The agent pulls account notes, writes a first-pass brief, and saves me from opening six tabs just to remember what a prospect asked last time."
Elliot C.
Revenue Operations Lead, B2B analytics platform
"Parents message us at night about classes, pricing, and makeups. InsertChat handles the simple stuff right away, so my front desk is not waking up to a pile of repeats."
Nina A.
Studio Owner, B2C fitness studio
"The useful part was how fast people adopted it. Support uses it for answers, marketing uses it for drafts, and nobody had to learn some big new system first."
Grant M.
Operations Manager, B2B logistics company
"We connected our product guides and return policy, then put the agent on the store. It started giving clean answers the same afternoon, which is usually not how software setup goes."
Leah T.
Founder, B2C skincare shop
"Our shoppers ask the same sizing and shipping questions all day. The agent answers those in our brand voice, and store staff only step in when someone actually needs a person."
Maya R.
Ecommerce Director, B2C apparel brand
"We use it before sales calls now. The agent pulls account notes, writes a first-pass brief, and saves me from opening six tabs just to remember what a prospect asked last time."
Elliot C.
Revenue Operations Lead, B2B analytics platform
"Parents message us at night about classes, pricing, and makeups. InsertChat handles the simple stuff right away, so my front desk is not waking up to a pile of repeats."
Nina A.
Studio Owner, B2C fitness studio
"The useful part was how fast people adopted it. Support uses it for answers, marketing uses it for drafts, and nobody had to learn some big new system first."
Grant M.
Operations Manager, B2B logistics company
"We connected our product guides and return policy, then put the agent on the store. It started giving clean answers the same afternoon, which is usually not how software setup goes."
Leah T.
Founder, B2C skincare shop
Outcomes
What you get
See what changes once it is live.
- Answers stay tied to the documents and pages people already trust.
- Updating source material is faster than rebuilding the assistant.
- Weak spots show up quickly from live usage.
- The same grounded setup can support multiple channels.
- Citations and source control stay easier to manage.
- Review and improvement stay tied to the same approved sources.
Document Classification
Data Protection
Security Briefing
Declassified
Public Release Authorized
REF: IC-SEC-2026-001DATE: 12 MAY 2026PAGES: 1/1
Executive Summary
Your data is stored on European servers. Never used for AI training. Deletable at any time. GDPR compliant with DPA available on request.
SEC-001DECLASSIFIED
Data Residency
Primary infrastructure in Frankfurt and Amsterdam. Your data never leaves the EU unless you explicitly choose a non-EU region.
Status: ACTIVE
SEC-002DECLASSIFIED
GDPR Compliance Status
Full compliance with General Data Protection Regulation (EU) 2016/679. Annual audits conducted by independent authorities.
Status: VERIFIED
SEC-003DECLASSIFIED
Zero Data Training Policy
InsertChat maintains a strict policy of never using customer data for AI model training. All data remains property of the customer.
Status: ENFORCED
SEC-004DECLASSIFIED
Enterprise-Grade Security
AES-256 encryption at rest. TLS 1.3 in transit. 24/7 monitoring. Regular penetration testing by independent auditors.
Status: ACTIVE
Authorized By
InsertChat Security
This document has been approved for public release
Start with Starter for your first branded assistant, move to Pro when you need more assistants and sources, or choose Business for team access, white-label controls, and deeper reporting.
StarterProBusiness
FAQ
Commonquestions
Answers about setup, pricing, handoff, and what happens after the live version starts handling real traffic. This FAQ is framed for rag chatbot searches.
InsertChat
Product FAQ
Hey! 👋 Browsing Product questions. Tap any to get instant answers.
0 of 21 questions explored Instant replies
Product FAQ
What is InsertChat?
InsertChat is a white-label AI assistant platform for content-rich websites. Train an assistant on owned content, brand it, publish it on your website, and learn from visitor questions.
What's the difference between an agent and an InsertChat agent?
A basic chatbot is prompt-only. InsertChat assistants are grounded in your approved sources, configurable per use case, brandable for your website, and able to use scoped tools when follow-up is needed.
How do agents stay accurate and avoid hallucinations?
Ground your agent in approved owned content and keep it fresh. Use analytics to find gaps and improve coverage over time.
What can I connect as knowledge?
URLs, sitemaps, documents (PDF and office files), media like YouTube and audio, and structured data. The goal is a clear source of truth for answers.
Do sources stay up to date?
Yes. Refresh sources on demand or set up scheduled refresh depending on the source type.
Can I control how the agent behaves?
Yes. Control prompts, model choice, tool access, and the branded assistant experience so behavior stays consistent.
Which AI models can I use?
InsertChat supports multiple model providers. Choose the model behind each assistant for quality, speed, and cost, or use BYOK to manage provider access yourself.
Can I pick different models for different workflows?
Yes. Use a faster model for common questions and a stronger model for complex reasoning. InsertChat supports that balance per conversation.
Where can I deploy an agent?
Website widget, embedded window, full-page assistant, custom domain, in-app embed, or API. Keep one assistant setup and reuse it where visitors need it.
Do I need coding skills?
No. Build and deploy AI agents using our visual builder. The embed code is one line of JavaScript.
Can I customize the branding and UI?
Yes. Customize the assistant name, logo, colors, welcome message, suggested prompts, tone, domain, and white-label presentation.
Can I use my own domain?
Yes. Custom domains are supported, typically via enterprise options.
Does InsertChat support voice?
Yes. Voice dictation and text-to-speech let users speak instead of type.
Does InsertChat support vision?
Yes. Enable vision for agents when images help clarify a request or context.
What tools and integrations are supported?
Zendesk, HubSpot, Shopify, WooCommerce, calendar booking, web search, Perplexity, and webhooks for your own systems.
Can I control which tools the agent is allowed to use?
Yes. Tool access is controlled per agent so you enable only what you need.
Can the agent hand off to a human?
Yes. Configure human handoff so the agent escalates when needed. Full conversation history is passed along.
Do you provide analytics?
Yes. Track chats, leads, feedback, top questions, unanswered questions, most-used sources, and content gaps.
Is it mobile friendly?
Yes. The widget and embeds work well on desktop and mobile with no separate experience needed.
What's the fastest path to a successful deployment?
Start with one agent and a small set of high-value sources. Iterate using real questions from analytics.
What is the fastest way to get started?
Create an account, connect one high-value content source, ask a test question, brand the assistant, then publish it on a controlled website page.
Pricing FAQ
What do I pay for with InsertChat?
Pricing is based on how many agents you run, what knowledge sources you connect, and how much conversation usage you drive. Check the pricing page for current tiers.
How much does InsertChat cost?
Plans start at $98/month. Verify the latest pricing and included limits on the pricing page.
Is pricing per seat?
Pricing is oriented around assistants, content sources, usage, white-label needs, seats, and client-site complexity.
Can I start small and upgrade later?
Yes. Start with self-serve, validate your use case, then scale up as needed.
Can I cancel anytime?
Yes. Cancel anytime with no long-term contract. Your data remains available for 30 days after cancellation.
Do you offer enterprise pricing?
Yes. Enterprise plans cover larger orgs, advanced requirements, and custom deployment needs.
Do you support annual billing?
Yes. Toggle to annual billing on the pricing page and save 20%. For invoicing or procurement workflows, contact us.
What happens if we hit limits?
You will get a notification before you hit a limit. Upgrade your plan anytime with one click, or reduce usage. Nothing stops working without warning.
What counts as a source?
A source is any connected item your agent learns from: a URL, document, YouTube link, or other knowledge input. Your plan determines how many you can connect.
Is there a max file size for uploads?
Yes. Plans enforce a max file size per upload. Check your plan details on the pricing page.
What are credits?
Credits budget your usage across conversations, sources, and tools. They keep costs predictable as you scale.
Do you charge for all messages, even unresolved ones?
Ground answers in your knowledge and enable tools only when needed to control cost. Check the pricing page for how usage is measured.
Can I control which models we use so costs do not spike?
Yes. Choose the model per chat to balance quality, speed, and budget for different workflows.
Do I need to buy separate subscriptions for each model?
No. Keep assistant setup in one place and choose supported models behind the branded experience without separate visitor-facing tools.
What is BYOK?
Bring Your Own Key. Use your own provider API key for model access to consolidate billing or apply your own setup.
If I use BYOK, do I still pay InsertChat?
Yes. InsertChat still provides the agent product: knowledge, deployments, tools, analytics, and governance. Model provider usage is billed separately.
Can I use my own logo and domain?
Yes. Public plans include white-label access. Check the pricing page for current logo, domain, and assistant limits.
Does InsertChat replace support staff?
No. Deploy agents for common questions and use handoff to humans for edge cases and high-stakes requests.
What's the ROI case for pricing?
Buyers see value when assistants improve content discovery, handle repeat questions, capture leads, and reveal content gaps. Best ROI comes from grounding on your sources and iterating with analytics.
Can I test before I commit?
Start self-serve to validate your workflow. For guided proof-of-concept or enterprise requirements, contact us.
Do you have discounts for startups or nonprofits?
If pricing is a blocker, contact us with your context.
What's included in enterprise that self-serve might not cover?
Higher source volume, more assistants, custom domains, BYOK, S3-compatible source sync, role-based access controls, advanced integrations, and security review support.
Can I use InsertChat on multiple websites or products?
Yes. Deploy agents across website, in-app embed, and API. See pricing details for how that maps to your plan.
If I stop paying, do I lose my data?
Retention depends on your plan terms. Contact us for specific export or retention guarantees before purchase.
What if InsertChat isn't a fit after we try it?
Share what didn't work and we'll help you decide whether to tune the setup or move on.
How do I start?
Start a 7-day free trial with full access. A credit card is required to begin, but you are not charged during the trial.
Security FAQ
Where is my data stored?
European servers. GDPR compliant, never used for training, and deletable at any time.
What is InsertChat, from a privacy standpoint?
A branded AI assistant platform that connects to your approved sources and uses model providers to generate responses. Privacy depends on what you ingest, what tools you enable, and who can access the assistant.
What gets sent to AI model providers?
Your prompt and relevant context excerpts from connected sources are sent to the selected model provider to generate an answer.
Do you use our data to train models?
No. InsertChat never uses your data to train models.
Is my data isolated from other customers?
Yes. Data is scoped to your account and agents. Sources and conversations remain isolated.
Can I delete data?
Yes. Delete sources, conversation history, leads, and feedback at any time.
What data does InsertChat store?
Agent configuration, connected knowledge sources, and conversation data needed for the experience and analytics.
Can I keep an agent private?
Yes. Choose public or private agents depending on whether anyone or only authenticated users can access the embed.
Do you have role-based access controls?
Yes. Control who can manage agents and data with role-based access.
What is BYOK from a privacy standpoint?
You provide your own API key for model access. Prompts and context are still sent to the provider, so review their policies for your compliance needs.
Can I restrict what the agent can do?
Yes. Control tool enablement per agent to limit actions to only what is necessary.
Can we limit exposure of sensitive data in the agent?
Yes. Scope sources to what should be answerable and limit tool enablement to only what is required.
Can I export or audit what users asked?
Yes. Analytics show what people ask. Contact us for exports for audits or internal reporting.
Do you support GDPR?
Yes. Full GDPR compliance with Data Processing Addendum (DPA) available on request.
Can you provide a DPA?
Yes. Our DPA covers processing obligations, subprocessors, and deletion/return terms. Contact us to request it.
Do you list subprocessors?
Yes. Subprocessors are documented in the DPA. Request it or contact us for details.
How do you handle security questionnaires?
Contact us and we provide the right documentation for your security review process.
Is InsertChat safe to embed on a public website?
Yes, when configured correctly. Ground answers in approved sources and keep tool access controlled.
What if we need a private deployment or special requirements?
Enterprise plans cover custom deployment, advanced controls, and procurement constraints. Contact us to discuss.
How do privacy requests work (access, deletion)?
Submit privacy requests through the contact page. We route them to the right process.
Where can I request security documentation?
Submit security inquiries through the contact page.
Do you support self-hosting?
Yes. Enterprise plans include self-hosting and bring-your-own-LLM options.
How do I evaluate InsertChat?
Start a free trial with non-sensitive data. When ready, request our security questionnaire and DPA.
Ground it on your content today
Connect the docs, files, and URLs first so the answers stay tied to the source material your customers already trust.
7-day free trial · No charge during trial