Public previewRAGSuite is open-source, self-hosted and EU-ready — and we build it in the open.See it live

Platform Platform overviewSee it in actionAI SearchAI AssistantAI Connectors & MCPIntegrationsQuality LoopAdministration & SecurityMobile app
Solutions IT & Platform teamsCompliance & Data ProtectionDevelopersAgencies & Partners
Sovereignty
References
Pricing
Resources Trust CenterEU AI ActSecurity & disclosureFree toolsOpen source & open coreDocumentation ↗API reference ↗GitHub ↗ReferencesBlogChangelog
Company AboutPartnersContact
Search See it live Book a demo
Platform · The quality loop

Measure answer quality. Prove it improved.

Compare models side by side, trace every query end to end, and read the analytics — with a citation on every answer. The loop that turns a demo into something you can trust in production.

See pricing
your-domain.de / compare modelsEE
Anthropictop

Cap = prior 12 months’ fees; excludes gross negligence.

0.94
Local · Ollama

Liability limited to fees paid; carve-out for intent.

0.89
Across the loop

What ships in each edition.

Citations & feedback

A citation on every answer and a feedback page (thumbs, stars, reason tags, comments).

Community

Compare Models

One query across saved configs, scored on quality, tokens and response time.

Enterprise

Deep query tracing

Retrieval, reranking, LLM and streaming timings, parameters and confidence — CSV/JSON export.

Enterprise

Advanced analytics

Cohorts, trends and cost breakdowns on top of the basic dashboard.

Enterprise

See the quality loop in the live product · take the tour →

Deep query tracing

Trace timings, parameters and confidence.

Every query broken down — retrieval, reranking, LLM and streaming — with runtime parameters and a confidence badge, exportable to CSV and JSON.

Enterprise Edition
your-domain.de / query traceEE
retrieve 120ms
rerank 60ms
generate 340ms
cite 20ms
confidence 0.94 · 2 citations · model: local · Ollama
Analytics

Queries, latency, satisfaction, cost.

A dashboard of how much it’s used, how fast it answers, how happy people are and what it costs (queries, p95 latency, thumbs-up rate, tokens), with charts and export. Advanced analytics — cohorts, trends and cost breakdowns — are Enterprise.

your-domain.de / analytics · 7 days
Queries · 7d
12,480
p95 latency
840 ms
Thumbs-up
94%
Tokens
8.2M
Reference
“RAGSuite gave our industrial clients a sovereign AI they actually own — citation-backed, self-hosted, and defensible to their auditors.”
Stephan Neudecker · Tech-Lead, Fischer and Friends
Read the case study
−74%
lookup time
9
sources unified
Local
LLMs
Measured
answer quality

All references

Compare Models, deep tracing and feedback — one quality loop, on your own infrastructure.
The quality loop
FAQ

The quality loop, answered

What’s in the Community Edition?

A basic dashboard, a citation on every answer and feedback collection. Compare Models, deep tracing and advanced analytics are Enterprise.

How does Compare Models work?

Run one query across your saved model configs and compare score, token use and response time side by side. CE shows a locked teaser.

What does a trace show?

A timing breakdown — retrieval, reranking, LLM, streaming — plus runtime parameters and a confidence badge, exportable to CSV or JSON.

Can we export the data?

Yes — traces and analytics export to CSV/JSON in the Enterprise Edition.

Mihaela Angelova, Delivery & Onboarding
Mihaela Angelova
Delivery & Onboarding

Measure answer quality — don’t assume it.

Compare Models, trace every query, and close the feedback loop. We’ll set it up against your own content.

Founding-customer programme open now — own your AI, on your own infrastructure.
See AI Search