RAG pipelines
AI answers from your documents, with sources and your permissions. Confluence, SharePoint, OneDrive, Nextcloud, codebases and more.
Inquire about RAGAI from Seibert Group
Self-hosted. On your terms.
From your own RAG pipeline, decision models and meeting transcription to autonomous agents: building blocks that work without a US cloud and that you can run yourself. With Weldall, you decide what your agents are allowed to access.
- No data shared with third parties
- On your infrastructure or exclusively on ours
- Built GDPR-compliant together with you
Custom-built for you
Either run GDPR-compliant by us, with a DPA and NDA, or built by us in your infrastructure. Either way, with the best open models and tools.
Chatbots
Chatbots for employees or customers, with your knowledge, tone and rules. Internal, on your website or in Teams and Slack.
Choose a channel for the example
Inquire about a chatbotCan I still change my order?
Yes, until it ships. Give me your order number and I'll update it.
DecisionsNew
Decision models
Small, fast models for the many yes/no and multiple-choice decisions in your workflows: routing tickets, classifying documents, assessing risks, checking agent actions. They return a choice with a confidence score instead of text, and your software decides when to act on its own and when a human takes a look.
Choose an example
Inquire about a decision model- Input
- “Login hasn't worked since the update”
- Question
- Which team?
- Answer
- IT support
Assign automaticallyConfidence 0.94
Above the threshold: the software acts on its own.
SpeechNew
Speech recognition & meetings
Meetings, calls and dictations become text, with speakers, timestamps and a summary.
Inquire about speech recognitionReady-made building blocks
Autonomous agents
Taskmate
Agents handle your routine tasks, just like a person would. Managed or self-hosted, including an LLM from the EU.
Go to Taskmate (opens in a new tab)Access & permissions for agents
Weldall
Agents can only do what you can: through your SSO, with no visible tokens. Code on GitHub, self-hostable.
The foundation
Language model
The SeibertGPT API, a GPU cluster exclusively for you or an LLM you run yourself.
For companiesTwo ways, same building blocks
On your infrastructure
Runs entirely in your infrastructure, no data shared with third parties, no US cloud. We build, hand over and provide support if you want.
On ours, exclusively for you
We run your solution on dedicated infrastructure. Operated in the EU with a DPA.
What do you want to build?
A few details are enough. We'll get back to you by email, with no obligation and no login.
Prefer to reach out directly? Write to gpt@seibert.group.