Back to Blog

AI Chatbot for Swiss SMEs — Strategy, Privacy and Limits

Why standard plugins often fail for SMEs, how Hybrid Mode works and which public prices apply.

Editorial review:

Editorial review: 7 September 2026. Updated technical distinctions and sources, with added practical checks. The original publication date and complete topic structure remain traceable.

TL;DR: Key Takeaways

FAQ, plugin or dedicated RAG: the right choice depends on the task, data flows and operation. A controlled pilot makes quality and effort comparable.

  • Compare options against the task.
  • Test sources, permissions and human handover.
  • Record cost and rework in the pilot.

Customers expect fast answers. A chatbot can help. Whether it helps depends on data flow, goals and operations — not on the plugin alone.

Chapter 1: what to check when selecting a plugin

Many plugins send questions to external services. Without contract, logging and a data-flow review, that is a risk for SMEs. Whether the EU AI Act applies depends on role, use case, system category, market placement and other facts; a concrete case must be assessed and may require legal review [1].

Privacy (FADP)

The revised Swiss Data Protection Act (FADP) has been in force since 1 September 2023 [2]. It requires proportionality, transparency and security, among other things. A plugin without a documented data flow does not automatically meet that.

Hallucinations and trust

Language models can produce false statements. For SMEs that is a reputation issue. Answers must come from approved sources, not from model memory.

Chapter 2: Hybrid Mode — architecture, not a promise

Hybrid Mode separates sensitive content from external inference. Whether it works depends on rules, tests and operations.

Data abstraction (DAL)

  • A local pre-check can mark or remove PII — only if that module is active.

  • Placeholders replace identifiers; originals stay in a project-defined store.

  • Only approved context is sent to the external model.

  • Answers are reassembled locally.

What a chatbot can do — and what it cannot

FAQ and knowledge

A chatbot can answer from approved content. It does not replace binding advice.

Appointment and contact requests

A chatbot can capture and structure requests. It does not replace human confirmation.

Handover to people

For complex cases, escalation to people is sensible. The chatbot is a tool, not a substitute for responsibility.

Chapter 3: Public prices

Public prices are fixed and limited: Short Check, SOURCE/01 Full and mandate. RAG has no public numeric price.

Short Check

First alignment, one domain, limited scope. CHF 0.

SOURCE/01 Full

Separately bookable in-depth audit with a documentation package. CHF 2'450 one-time.

Mandate

Ongoing visibility work after the appropriate audit or baseline. From CHF 1'500 / month.

RAG / Hybrid Chat

Internal company knowledge, FADP-aware, project-specific. No public figure — scope and price are set in an introductory call.

Chapter 4: Define goals — without borrowed KPIs

Define goals from your own baseline and measure them during a controlled pilot. A chatbot is not an end in itself.

  • Which requests come in today?

  • Which of them are repetitive and approved?

  • Which answers may be automated?

  • How is handover to people handled?

Visible FAQ, plugin or a dedicated RAG system?

Choose the technical form for the task. A small, rarely changing set of approved answers may be clearer directly on the website. A plugin can fit when data flows, maintenance and answer limits are documented. A dedicated RAG system becomes relevant for multiple sources, differentiated permissions or integrations. No option is superior merely because of its category.

OptionSuitable starting caseCheck before use
Visible FAQA few recurring questions with stable answersSpecialist approval and contact path.
Chat pluginBounded task with a documented service chainRecipients, retention, cost and fallback.
Dedicated RAGDistributed knowledge and role-based answersSource permissions, evaluation questions and operation.

Fictional pilot: a team selects 20 common support questions, including five without an approved answer. It measures source accuracy, correct escalation and handling time. This sample is a project template, not a universal quality standard. Comparison with the existing workflow shows whether the additional operational work is justified.

Conclusion

A chatbot can help when data flow, goals and operations are right. GlasBox reviews that project by project.

Kacper Ruta · owner of Ruta Group · GLASBOX Studio

Sources

The next step

Review the chatbot setup?

We review data flow, goals and operations. No prices beyond the public list.

Request Consultation