dAI Pro turns what you already have into an assistant that answers: your website, your PDFs, your knowledge base, your ticket system.

This chapter walks through the whole path once: create a collection, set up the website as a data source, index, process, ask in the test chat, embed.

All pages of dAI Pro follow the same patterns.

The settings of the collection determine which language model answers, how it answers, what visitors may do and which paths lead out of the chat.

Data sources bring the knowledge into the collection.

The collection view is the workbench for your content: here you see what is indexed, start runs, process, deactivate and clean up.

The quality of the answers decides whether visitors trust the chat. dAI Pro uses the knowledge rule to make sure that no answer is invented.

The chat of your collection should go on your website.

The chat answers questions. The search shows where the answers are: a result list across the entire indexed content of the collection, with title, address and a short description per result.

One collection, several faces: an assistant is a profile within the collection with its own name, its own greeting, its own starter questions, its own goal and, if desired, a narrowed knowledge scope.

With the voice chat, visitors talk to the assistant instead of typing: press the microphone, speak the question, hear and read the answer.

A chat that cannot help must not leave the visitor on their own.

On public pages, the chat is anonymous. In a customer portal, behind a login, your website knows who is asking. dAI Pro can use this knowledge: the chat addresses the visitor by name, and tools may use bound details such as the customer nu…

More and more of the questions put to your website come not from people but from AI assistants: ChatGPT, Claude, Perplexity, the assistants in browsers and operating systems.

Agents work on a schedule with the collection's knowledge: they check the website for changes and keep the index up to date, find outdated details and contradictions, analyse the real questions visitors ask, make FAQ suggestions, test answer quality and write reports.

Whether the chat is good is not decided in testing but in the real conversations. dAI Pro logs every question with its answer, sources, rating and outcome and turns them into metrics, topics and concrete work lists.

The inbox is where requests arrive that no chat resolves: handovers from the chat, emails from a support mailbox, cases from the ticket system, form submissions.

The Copilot writes drafts for the editorial team from the knowledge of the collection, in the style of the website: page texts, meta descriptions, summaries, posts for social media, alt texts for images.

Every call to a language model costs money, usually fractions of a cent, but noticeable in total. dAI Pro logs every call per collection, purpose and model and converts it into costs using the stored list prices.

Where a question is processed is no minor matter for many companies: privacy policy, data processing agreements, promises to customers. dAI Pro makes the processing region a setting of the collection, checks it against all services involve…

The chat sets no cookies, and a question in the chat is a deliberate act by the visitor.

Since 2025 the German Accessibility Improvement Act (BFSG) requires many websites to make their services usable by everyone.

dAI Pro talks to several providers of language models.

The configurator generates the embed code; anyone who writes it by hand, builds it into templates or connects it to their own JavaScript will find all attributes, variables, events and endpoints here.