Verified knowledge before your AI uses it.

Rasepi verifies every source before your AI uses it. Up-to-date? Verified? Approved for this purpose? Only what passes verification gets through. Outdated and unapproved content is blocked. No proxy, no migration.

Made in Germany·Open Source at its core·Trust API & MCP
QUELLEN KI Antwort 2 Quellen · geprüft Provenance Ledger Entscheidung #4812 · 7 erlaubt · 5 blockiert

Your documents are lying to your team. And your AI is spreading the word.

A human sometimes notices that a page looks outdated. An AI never does. It reads the text, takes it as true, and responds with full conviction. The better the answer sounds, the greater the damage.

💬

The support bot quotes the old price list

The source was semantically perfect. Unfortunately, it’s been wrong since January. The customer receives a confident response with outdated figures.

The agent acts according to a dead runbook

Autonomous agents don’t just read—they act. An agent that changes configurations based on outdated instructions is no longer a documentation issue. It’s an incident.

📋

No one can prove what a response was based on

The audit asks: Which sources did the AI use, and were they approved? “Probably the right ones” is not an answer.

Don’t just check the answer. Check the knowledge it’s based on.

This is how the Trust Gate decides

Your AI searches as before. Before the answer is generated, Rasepi checks every source found and makes a clear decision. With a rationale, not just a number.

ALLOW Allowed: Current, verified, and approved for this purpose. The source reaches the AI.
WARN With Conditions: Usable, but requires a citation or a note. Review expires soon.
BLOCK Blocked: Expired, modified after approval, or never approved. Does not appear in the prompt.

The same document. Four answers.

Trust is not a fixed property of a document. It is a contextual decision: Who is asking, for what purpose, and through which channel?

OAuth Migration Guide
Engineering · Review overdue for 12 days · linked API reference recently changed
👤 Employee reading internally
WARN
Review overdue, but the responsible owner is active.
🤖 Internal AI assistant
WARN
Allowed for internal AI, with mandatory attribution.
💬 Customer support bot
BLOCK
Linked API reference changed since last approval. Customer responses require a new approval.
Autonomous Agent
BLOCK
Document is not approved for active agents.

Keep your systems. Add trust.

The Trust Gate does not require migration. Rasepi connects to the systems where your knowledge resides today, catalogs the content, and calculates trust based on it. It doesn’t matter which systems these are.

  • Every source is cataloged: wikis, documentation platforms, Git repositories, ticket systems
  • Catalog broadly, verify deeply only where necessary
  • Trust status visible where work is done, via API and badges
  • No lock-in: Your knowledge stays where it is
Connected Knowledge4 Source Systems
Company Wiki
2,418 pages cataloged
61
142 reviews overdue38 sources modified
Developer documentation
312 pages cataloged
88
Webhooks active Reviews up to date
Team notes
876 pages cataloged
34
No owner for 61%Blocked for AI

Every decision leaves a record.

Which sources were reviewed? Which were approved, which were blocked, and why? Which version was valid at the time of the response? The Provenance Ledger answers the question that arises after every incident and in every audit.

“Who or what relied on what knowledge, and why was that permitted?” Review requests are automatically sent to owners from blocked sources.
app.rasepi.com / ledger / 4812
Decision No. 4812support-bot · answer_customer
June 12, 2026 9:30 AM
7 sources approved—current, verified, approvedALLOW
⚠️2 sources with conditionsCitation required setWARN
🚫3 sources blockedSource changed / not approvedBLOCK
Fully traceableExport →

Built for developers

The Trust Gate speaks a simple HTTP API: sources in, decisions out. A single call after retrieval is all it takes. Works with any RAG pipeline, any chatbot, any agent, and natively in your AI assistant via MCP.

Where Rasepi makes a difference

From support bots to compliance audits: The Trust Gate solves the same problem everywhere, just in the respective context.

Our other products

Trust Gate is the heart of the system. Those who want to feed their knowledge directly into Rasepi get two additional products built on the same foundation.

Feed your AI only knowledge
you would trust yourself.

In a short demo, we’ll show you the Trust Gate using examples from your stack. Ready to go in 20 minutes.

Request a demo
🇩🇪 Made in Germany 🔧 Open source at its core 🔐 Trust API & MCP No proxy, no migration