Adding an AI Assistant to Your Website: Time, Cost and Risks
Business

Adding an AI Assistant to Your Website: Time, Cost and Risks

A ready-made widget can go live in days, but an assistant that answers from your own data needs clean sources, a handover to people and a KVKK notice. Here is how to choose and launch it.

Short answer

To add an AI chatbot to your website, either embed a ready-made widget or build a RAG assistant that answers from your own documents with sources. A widget suits questions already answered on your site; your own data is needed for prices, contracts or technical documents. Before launch, make the assistant say 'I don't know' when it finds no source, offer a human handover, and check your KVKK information notice.

What does adding an AI chatbot to your website involve?

Adding an AI assistant to your website means placing a chat box that takes a visitor's question in plain language and answers it from your own business information. There are two routes: you embed a ready-made chatbot widget with a snippet of code, or you build an assistant that searches your own documents and answers with sources. The first can go live within days; the second depends on how ready your data is and usually takes weeks.

Older rule-based chatbots worked from pre-written menus. An AI assistant is built on a language model and understands free-form questions. On its own, though, the model does not know your campaign terms, your returns policy or your opening hours. A good assistant therefore finds the relevant passages in your content at the moment a question arrives and bases its answer only on those. This method is called RAG (retrieval-augmented generation).

Three decisions matter before any technology choice: which questions the assistant will answer, which source it will answer from, and who the visitor is handed to when it cannot answer. If those are clear, choosing a tool is easy. If they are not, even the most expensive widget becomes a shop window that gives wrong answers.

Should you use a ready-made widget or an assistant built on your own data?

The options do not rank above one another; each fits a different need. The table below is enough for a first screening.

OptionWhen it fitsWhat to watch
Menu-based chatbotFew, fixed questionsGets stuck on unexpected questions
Ready-made AI widgetGeneral questions, quick startWhere data is processed, retention period
Hosted platform with your contentYour site pages hold the answersCitations and permissions may be limited
RAG assistant on your own dataNeeds products, contracts, stock dataData preparation and testing effort
Model on your own serversData must not leave your networkHardware and operating responsibility

The rule is simple: if the answers are already written on your site, a ready-made tool may be enough. If they depend on information that is not on the site, such as price lists, technical documents, order status or contracts, you need an assistant connected to your own data. We cover the cost items separately in our article on the cost of an enterprise AI assistant.

How do you manage the risk of wrong answers (hallucinations)?

Language models can produce answers that look right but are invented. OWASP's misinformation risk page explains a main cause: the model fills gaps in its training data with statistical patterns. The same page says that retrieving information from trusted sources reduces the risk, while critical topics still call for human oversight and verification. It also cites a case where an airline lost a legal dispute after its chatbot gave travellers wrong information. In a visitor's eyes, what your assistant says is what you said.

In practice, put these safeguards in place:

  • Answer only from sources: if the retrieved passages do not contain the answer, the assistant should say "I don't know" and direct the visitor onwards.
  • Show sources: display the page each answer came from. See our article on verifying sources in RAG answers for details.
  • Narrow the scope: on prices, discounts, legal commitments and health, the assistant should not make binding promises but hand over to a person.
  • Provide a human handover: a phrase such as "I want to speak to someone" must always work and open contact details or a request form.
  • Allow for hostile input: OWASP's prompt injection page describes an attacker trying to make a customer support chatbot ignore its earlier rules, and notes that RAG does not fully close this gap. Give the assistant no authority to act, and let it read only public content.

What should you check for KVKK and information notices?

If a visitor types a name, phone number, order number or health detail into the chat box, you are processing personal data. Article 10 of Law No. 6698 (KVKK) requires the data controller to tell people who it is, why the data is processed, to whom it may be transferred, how it is collected and on what legal basis, and what other rights the person has. Consider placing a short link to that information next to the chat box, and check whether your notice covers chat data.

Article 12 of the same law requires the controller to ensure an appropriate level of security; where another person processes personal data on your behalf, you share responsibility with them. If a widget provider processes data for you, the contract should state this clearly. The KVKK Authority's guide on generative AI and personal data says that personal data processing in these systems is assessed under Law No. 6698 and aims to guide data controllers. If the provider processes data abroad, the transfer conditions in Article 9 should also be assessed. For an overview, read our article on the KVKK generative AI guide.

Ask the provider these questions: in which country is the data processed, how long are chat logs kept, is the data used to train models, and how are deletion requests handled? Get the answers in writing. Tell visitors plainly that they are talking to an AI, and remind them not to type unnecessary personal details.

Which steps should you follow before going live?

  1. List the questions: collect the 50 to 100 most frequent questions from support emails, phone notes and your site search logs.
  2. Prepare the knowledge source: remove outdated, contradictory and confidential documents. The assistant will know only what is written there.
  3. Write the scope and limits: decide what it answers and what it hands to a person.
  4. Build a golden question set: write the expected answer and source for each question. This set is your acceptance test. For measures, see our article on RAG evaluation metrics.
  5. Complete the notice and contract: put an information link in the chat box and settle data processing terms with the provider.
  6. Start with a small audience: launch on one page or a small share of traffic, and read the logs every week.
  7. Measure and correct: add unanswered and wrongly answered questions back into the knowledge source.

How do you measure the share of questions resolved?

The most useful indicator is the share of chats the visitor resolved without needing a person. Place each chat in one of three groups: the assistant answered correctly, the assistant said "I don't know" and handed over, or the assistant answered wrongly or incompletely. Reading and classifying 30 to 50 chats by hand each week teaches you more in the first months than automated metrics.

For example, suppose you receive 400 chats a month. Of 50 chats you review by hand, 31 were resolved correctly, 12 were handed to a person and 7 were answered wrongly or incompletely. In this hypothetical case the resolution rate is 62%, the handover rate 24% and the error rate 14%. Aim to cut the error rate first and raise the resolution rate second, because a wrong answer costs more than no answer. After you add the failed questions to the knowledge source, re-run the same set and you will see the improvement in numbers.

The cost items are: preparing the knowledge source, development and integration, language model usage fees, hosting, monitoring and regular content upkeep. The total varies with the number of sources, the languages and the integrations you need, so quoting a general figure would be misleading.

What are the common mistakes?

  • Launching the assistant before cleaning the knowledge source; an old campaign or price page turns into a wrong answer.
  • Letting the assistant make up an answer on topics it does not know; being able to say "I don't know" is a feature.
  • Offering human handover only in office hours and hiding it.
  • Leaving out the information notice link and not knowing how long chat logs are kept.
  • Not reading the logs after launch; the assistant does not improve by itself and the content has to be kept current.
  • Giving the assistant freedom to answer on binding topics such as prices, contracts and refunds.

How Hatson Tech helps

Hatson Tech builds assistants that answer from your documents and internal data with sources, as part of our RAG and semantic search solutions. Where needed, we can run the model on your own servers. The first meeting and discovery are free; we do not publish fixed prices, and we agree the scope with you before quoting.

To go deeper, see our articles on AI hallucination and RAG permission filters.

Key takeaways

  • Decide which questions the assistant answers, from which source, and who takes over when it cannot answer, before choosing a tool.
  • A ready-made widget suits answers already on your site; an assistant on your own data suits prices, contracts and technical documents.
  • Make the assistant answer only from retrieved sources, show the source and say 'I don't know' when nothing is found.
  • Check the information notice and the provider's data processing terms under Law No. 6698 before launch.
  • Start small, review chats by hand each week and track resolved, handed-over and wrongly answered shares.

Frequently asked questions

How long does it take to add an AI chatbot to a website?

A ready-made widget can be embedded in days because it needs only a code snippet and some settings. An assistant built on your own documents usually takes weeks, because the knowledge source has to be cleaned, tested with real questions and checked for permissions and data protection.

How much does a website AI assistant cost?

The cost depends on the number of sources, languages and integrations, so there is no honest general figure. The items are preparing the knowledge source, development, language model usage, hosting, monitoring and ongoing content upkeep. Hatson Tech does not publish fixed prices and agrees the scope after a free discovery meeting.

Can an AI chatbot give customers wrong information?

Yes. Language models can produce confident but invented answers, and OWASP lists this under misinformation risks. Limit answers to retrieved sources, show the source, narrow the scope on prices and legal topics, and always offer a human handover.

Is a website chatbot subject to KVKK?

If visitors type personal data such as names, phone numbers or order details, yes, you are processing personal data under Law No. 6698. Article 10 requires an information notice, and the security duty in Article 12 should be reflected in your contract with the provider. If the provider processes data abroad, Article 9 should also be assessed.

Do we need RAG, or is a ready-made chatbot widget enough?

If the answers are already written on your public pages, a ready-made widget may be enough. If answers depend on documents that are not on the site, such as price lists, contracts or technical manuals, RAG lets the assistant retrieve them and cite the source.

How do we know if the chatbot is working?

Review 30 to 50 chats by hand each week and sort them into correctly resolved, handed over and wrongly answered. Also keep a golden question set with expected answers and re-run it after every content change.

All articles