Training the AI: how dot learns your business

How do you train an AI on your own business data?

In stipt the AI assistant is called dot. Training here does not mean building or tuning a model yourself: you fill a knowledge base with your own sources, and dot searches it the moment a question or email comes in. Everything lives in Studio, in the What dot knows group: Knowledge, About your company and Feedback. Studio is available to admins and to users with the Studio right.

Every item in the knowledge base is a source. There are four kinds: a text, an FAQ, a URL (your website) and a file (PDF). Internal sources stay internal; only sources you mark as customer sources may be shown to customers. You organise sources into groups, and for each loop you choose which groups it may read. That way the customer‑facing WhatsApp bot can read different knowledge than the loops for your own team.

Besides the knowledge base you give dot business context via About your company: a short text about what you do, what you offer and what dot should keep in mind. That text is used by every loop. If you first want to know what AI can and cannot do well for small businesses, read the guide on AI for small businesses.

How do you have the AI read your website?

In the knowledge base, choose a URL source, paste your website address and click Fetch. You immediately see a preview of the first page, so you know the site is readable. After saving, dot reads the site in the background and keeps that knowledge up to date by itself. Update your website and the changes flow in by themselves.

Every source shows a status: Queued, Indexing, Indexed or Error. That way you can see whether a source is ready for use.

If your website is very large, dot does not read all of it in one go. You then see how many pages are still missing and add the rest as a new source with one click.

What documents can you add?

You upload PDFs as a file source: drag, drop, done. dot reads the text including photos and scans, so a scanned brochure or a datasheet full of tables comes through as well. Very large files have a limit; if dot cannot read a PDF, or not all of it, the source shows that, with the reason.

For knowledge that is not written down anywhere, use a text source. Put a clear heading above each topic, so dot can find what it needs per topic. For loose question‑and‑answer pairs, such as frequently asked customer questions, there is the FAQ source.

How do product datasheets end up in the knowledge base?

Attach a datasheet PDF to a product and it automatically lands in the knowledge base, in the fixed group Product datasheets. You manage datasheets on the product itself, not in the knowledge base; which loops may read them is controlled through groups, just like other sources.

Your product knowledge stays in sync with your catalog, with nothing to maintain twice. Remove a datasheet from a product and the knowledge base updates itself. How the product catalog itself works is covered in the product catalog guide.

Where does the AI use that knowledge?

In three places, mainly. In the inbox, dot drafts a reply to an email using real customer data and knowledge from the knowledge base: on request, or prepared in advance when you switch on the Inbox helper loop. The draft always comes to you for review first; no email ever goes out automatically.

In chat, dot answers questions from your team: about a customer, about how you work, or simply something from the knowledge base. Answers come with clickable source references; a click opens the source used, so you can check where something came from.

On WhatsApp, dot can answer on its own. The internal bot is for your own staff, the customer bot answers customer questions from the customer‑safe knowledge you connect. Both are off by default; no bot ever answers a real customer until you deliberately switch it on. With its first answer in a conversation, the customer bot also tells the customer they are chatting with an AI assistant.

How do you steer the AI with feedback?

You can give feedback wherever dot answers. In chat you use the thumbs down, and on WhatsApp you can also tell the internal bot that an answer is wrong.

All feedback comes together in Studio under Feedback. Admins see who gave the feedback, on which answer, with a click‑through to the source used. With Answer questions you clear open questions dot had no source for in bulk: you write an answer per question, each answer is saved as a knowledge base item and the feedback is marked resolved. That way the knowledge base grows exactly where it fell short.

How do you keep the AI away from certain topics?

You set boundaries per loop. You pick from standard boundaries: never promise prices or discounts, no legal or medical advice, do not discuss competitors, and complaints always go to a human. You can add your own as well. On top of that you give each loop instructions in plain language, for example keep it short or always mention the delivery time, and for customer‑facing loops you choose a tone of voice and whether the AI addresses customers formally or informally.

The customer WhatsApp bot has extra guardrails. It only answers from the connected knowledge base and makes no hard promises. You name the topics that go straight to a colleague yourself, such as complaints or cancellations. And when the bot is unsure about its answer, it hands the conversation to a human instead of sending a shaky answer.

The internal bot sticks to fixed rules too: sensitive topics such as prices and legal advice only come from your own knowledge base or retrieved data, never from general knowledge.

How do you test whether the AI is trained well?

Every loop has Try it at the bottom: you try it on an example or a recent real case and see the result, with no customer involved. The WhatsApp bots have a built‑in test chat where you talk the way a customer or colleague would; it never touches a real WhatsApp.

How things stand shows on dot's start page in Studio: cards with the number of sources and pieces of knowledge, how many loops are on and how much feedback is still open. The dot log also shows every AI run with its status, the knowledge used, the credits and the linked record. For the customer bot there is a performance panel: how many conversations were resolved and how often a human took over.