Skip to content
01 · PRODUCT

A chat, an inbox, a knowledge base, an MCP server —
one grounded pipeline.

Every answer the widget streams, every draft your inbox suggests, every article the gap-finder writes, every tool an external LLM calls — all routed through the same retrieval, the same citations, the same audit trail.

01 · MESSENGER

A messenger, not a bubble.

Home space with grounded suggestion chips pulled from your own content. Chat space with phased typing, inline [n] citations, and a resume card for returning visitors.

  • Home → Conversation, not a cold thread
  • Suggestion chips auto-generated from ingested content
  • “Pick up where you left off” card with a Gemini-written summary
  • Unread badge on the launcher when the assistant posts
  • InlineAsk block for any page — greeting + chips that open the chat
  • Visible human handoff with named agent + reply ETA
Hi there. 👋
How can we help?
Ask a questionAI
02 · GROUNDED ANSWERS

Every claim linked. Every source visible.

URL, sitemap, or PDF/DOCX/MD upload → HTML-aware chunking with section breadcrumbs → Gemini embeddings → Qdrant retrieval → BGE reranker → Gemini 2.5 Flash streaming generation. When the KB doesn't cover a question, we admit it and tag miss_reason — which feeds the gap-finder below.

Refunds depend on whether the order has shipped.
Unshipped orders can be refunded in full from Orders → Cancel & refund. Shipped orders become returns and take 3–5 business days after we receive them.
03 · KNOWLEDGE

It learns what you haven't answered yet —
and drafts the missing article.

Ingest URLs, whole sitemaps, or upload PDF/DOCX/MD. Every hour the gap-finder clusters visitor questions your KB couldn't answer and drafts a markdown article for each topic — ready for one-click publish.

Ingest anything

URL, sitemap.xml bulk-crawl, PDF/DOCX/MD up to 20 MB. Originals stored privately in our object store.

Section-aware chunks

HTML h1/h2/h3 breadcrumbs survive into every chunk so retrieval ranks by topic, not paragraph soup.

Gap-finder

Hourly clusterer turns unanswered questions into draft articles. Review, edit, publish — then the next visitor gets an answer.

04 · INBOX

Your team replies.
Chatified drafts.

Open a conversation. Click Suggest draft. The same grounded RAG pipeline that answers visitors produces a reply-ready draft with citation chips. Edit or send as-is — the reply lands as an assistant message tagged authored_by: "agent" and fires your webhook the same way a RAG-generated answer does.

Full transcript

Every message, every citation, every miss-reason tag — visible to your team.

Grounded draft

One click. Same retrieval. Attribution shown next to each reply.

Clean handoff

Escalation fires a conversation.escalated webhook so your helpdesk stays single-source-of-truth.

05 · MCP · BOTH DIRECTIONS

Tools, not just docs.

Chatified speaks Model Context Protocol on both sides:

  • As a client: point the widget at your merchant MCP server (HTTP, JSON-RPC 2.0) — orders, CRM, whatever. We introspect your tools, you enable per-tool, we audit every call.
  • As a server: npx @chatified/mcp drops Chatified into Claude Desktop, Cursor, or Zed. Your LLM can search your KB, ingest URLs, read conversations.
Add to Claude Desktop
"mcpServers": {
  "chatified": {
    "command": "npx",
    "args": ["-y", "@chatified/mcp"],
    "env": { "CHATIFIED_API_TOKEN": "ct_live_…" }
  }
}
Bring your own MCP server: paste the endpoint URL + optional auth header in the portal. We introspect via tools/list, you pick which to enable, we audit every tools/call.
06 · ANALYTICS

See the gaps. Close them.

Six panels under /app/analytics: funnel, miss-reasons, traffic sources, top-pages-driving-chats, new-vs-returning, daily volume. First-touch UTMs captured by the widget on page one, joined straight to conversation counts.

Funnel
page_view → widget_opened → started → answered → escalated
Miss-reasons
retrieval_empty vs model_hedged vs answered — what to ingest next
Traffic sources
Paid / organic / social / email / referral / direct, joined to chats
Top pages driving chats
Where on your site are people asking from?
Returning vs new
Cohort split on session count
Daily conversations
Time-series volume with per-stage conversion %
07 · POSTURE

Honest about what's shipped today.

Things we do today — not certifications we're angling for. The list below is what's running in production right now.

Per-tenant Qdrant — no cross-tenant vectors
Public keys SHA-256 hashed; soft-revoke
Signed HMAC webhooks + outbox retry
MCP calls audited with args-hash + result preview
Consent-aware (TCF v2.2 + Consent Mode v2)
Per-org retention cron (30 / 90 / custom)
Private-ACL object storage for uploads
Migrations fail-loud on drift

Ready to
ship it?

Install a script tag, point it at your docs. You'll have grounded answers before your coffee goes cold.

Start 7-day trial See pricing