The Questionnaire Death March

Trust pages are stale PDFs that were wrong the day they shipped. A living trust center answers compliance questions from real, cited evidence, and gates the proof behind Zero Trust.

The pain

Enterprise deals stall for weeks on security questionnaires and a trust page that's already stale.

The fix

A living assistant answers from your real docs with citations, and refuses when it can't ground it.

So what

Cut weeks off security review and hand auditors cited answers instead of questionnaire ping-pong.

See it in context

Visit Northwind Health's trust center, the fix living inside a real-looking company site.

Try it

Ask Northwind Health's trust assistant

A fictional company with a real compliance corpus. The assistant answers from that evidence with citations. When the answer is not in the documents, it declines instead of inventing one.

Answerable from the evidence

Try one it should refuse

Answers take ~2-8 seconds (grounded retrieval + a 70B model). Citations show the exact evidence used.

How it works

Point AI Search at your docs; it answers with citations, or refuses when the answer is not there.

💬
Question
from a user
query
Worker
aiSearch()
retrieve + generate
📚
AI Search
corpus + LLM
Grounded answer + citations
Not in docs → refuses

Add it to your site

dashboard setup + ~15 lines
Dashboard: create an AI Search instance
AI → AI Search → New
Data source: your R2 bucket or uploaded docs
Cloudflare chunks, embeds, and indexes them for you.
Worker: one call
const res = await env.AI.autorag('your-instance').aiSearch({
  query: question,
});

return Response.json({ answer: res.response, citations: res.data });
01
Create an AI Search instance pointed at your docs
02
Call aiSearch() from a Worker
03
Render the answer + citations; refusals come from your system prompt
Works with:Workers AIAI Search (AutoRAG)R2