The concept of spaces
What a space is and how to create one: a workspace with its own knowledge, its own chats and its own members.
Tutorials
Get to know skai in short videos. Each tutorial first explains the concept and then shows the exact steps in the application, in one to two minutes. The videos are narrated in German.
From the foundations to administration
41 tutorials · around 53 minutes · 4 areas
The starting point: what spaces are and how to run your first chat.
Your first chat
Start a chat, attach a space as knowledge and get a grounded answer with source references.
The chat input
Every function of the input line: attach files, dictate questions, reference knowledge, web search and model selection.
The navigation
A tour of the interface: the sidebar from top to bottom, from chats and experts through spaces and knowledge to your profile.
Building on that: bring in your own knowledge and work with experts.
Your own knowledge as a source
Create your own source, add content and get answers in chat that build on it.
Your own AI experts
Configure a reusable expert: role, instructions and knowledge, set up once for the whole team.
Starting an expert round
Several experts and invited people answer a question together in one round.
A chatbot for your website
Create a chatbot, connect it to space knowledge, test it in the preview and embed it into your website with a script tag.
Your first automation
Create a workflow: pick a trigger, connect and configure an AI node, run it and check the result.
Meeting notes
Upload a meeting recording, create the diarised transcript and generate a structured protocol from it.
The prompt library
Store proven prompts with placeholders centrally, share them in categories and insert them into a chat with one click.
Email workflows with Outlook
Building on your first automation: connect a workflow to an Outlook mailbox so incoming emails trigger it and the AI prepares a reply as a draft.
The glossary
The two glossaries: the personal glossary for your meeting notes and the glossary in a space that teaches the AI your terms and abbreviations when it answers.
For administrators: configure the organisation and keep an eye on usage.
Organisation settings
Master data, configuration and AI models: what administrators define centrally for the whole organisation.
Chat administration
Chat start widgets per view mode, central experts and shared prompts: the chat area of the administration.
Statistics
Credits, usage, messages and consumption: see how your organisation uses skai, narrowed down with from and to.
The focus mode
Full view or focus mode: set the organisation default, control the permission and switch the view in your user profile.
Users & groups
Invite or create members directly, edit and deactivate them, manage permissions via user groups – and what applies with Entra synchronisation.
The foundations: what AI is, how it works, where its limits are and how to use it safely.
What is AI?
What sets artificial intelligence apart: recognising patterns from examples instead of fixed rules.
AI, ML and LLM
The map of terms: AI as the umbrella, machine learning as the usual method and the language model as one kind of it.
How an AI learns
How a model learns from large amounts of data in training – parameters instead of programming, and training versus use.
Language models
What a language model is: it predicts the next word, and from that apparent understanding emerges.
Model and tool
The difference between an AI model and an AI tool (GPT versus ChatGPT): the model is the engine, the tool builds interface, memory and rules around it.
The prompt
The input is the instruction: how a clear, precise question leads to a better answer.
Tokens and context window
How an AI reads text in chunks (tokens) and why its memory per request is limited (the context window).
Hallucinations
Why an AI can be convincingly wrong – and why you should not blindly trust answers but check the sources.
Prompt injection and guardrails
How hidden instructions can be smuggled in (even via documents or websites) and how safeguards contain them.
Grounding and RAG
Answers based on real company knowledge instead of guessing: the AI looks things up first and then backs every statement (retrieval augmented generation).
Semantic search
How an AI finds by meaning rather than just by keyword – the basis for finding the right knowledge for a question.
AI and your data
What happens to your input: where the model runs, who has access and whether data is used for training.
Regulation and jurisdiction
The GDPR as the framework – and why it matters not only where the data sits but which law the provider is subject to.
Running an LLM
What running large and small models costs – memory, hardware and the trade-off between performance, cost and control.
Using AI responsibly
What AI is and is not good for – and why the human stays in control and checks the results.
AI agents and automation
AI that does not just answer but breaks a goal into steps, uses tools and works autonomously.
Multimodal AI
A model that understands not only text but also images, speech and documents.
Reasoning AI
Reasoning models take time for intermediate steps before answering – better on tricky tasks, but slower and more expensive.
Adapting AI to your knowledge
Prompting, RAG or fine-tuning: the three ways to teach an AI your knowledge – and when each one fits.
Open source or proprietary
A ready vendor service versus open weights: convenient and strong versus control and independence.
Bias and fairness
Why an AI picks up skews from its training data and is not neutral by default – and how to contain that.
The EU AI Act
The EU AI law in brief: regulation by risk and what matters for companies (not legal advice).
Introducing AI in your company
From idea to use: a clear use case, taking people along, clear rules and starting small.