AI Agent ROI Calculator
Free training: Chatbot crash course
Whitepaper: The acceptance of chatbots
Wizard of Oz Experiment
--> Go to BOTwiki
In the field of human-computer interaction, the "Wizard of Oz" method refers to a research experiment in which participants interact with a computer system that they perceive as autonomous, but which is in fact operated or partially controlled by an unseen person.
Chatbots and Wizard of Oz
Chatbots are enormously suitable for the Wizard of Oz experiment. In this way, a use case can already be examined for its"chatbot suitability" before implementation. The findings can then be used to iteratively expand existing flows and define new communication strands. In addition, the collected data, such as utterances, can be used directly for the Chatbot Training be used. A mature human handover tool is even able to automatically convert the tested data into a chatbot.
Recommended procedure
- Define different chatbot flows
- Integration of a live chat or an empty chatbot that only triggers a human handover.
- Manual response to user queries
- Derive chatbot flows
- Answering the queries based on the chatbot flows
- Iterative revision and expansion of the chatbot flows
- Manual or automated transfer of the flows into a chatbot builder
> Back to BOTwiki
The Wizard of Oz experiment is a UX research method in which users interact with an apparently autonomous system whose responses are formulated by an unseen human. In the context of conversational AI, the method is used to realistically test the dialogues of a planned AI agent before the system goes live. This allows use cases to be validated and real user data to be collected without the NLU model having to be trained yet.
A WoZ test is particularly worthwhile when a new use case for an AI agent is being planned and the requirements for dialogue management or tone are still unclear. The method also helps identify risks early on in sensitive channels such as voice hotlines, where there is little room for error. It is also useful when there is internal disagreement about whether a topic can be automated at all.
The experiment yields both qualitative and quantitative data: typical user comments, response patterns, escalation rates, common misunderstandings, and knowledge gaps. This information is incorporated into intent models, dialogue flows, and Knowledge AI content. As a result, the experiment serves as a direct precursor to the productive training of an AI agent.
While a traditional prototype test evaluates a system that has already been implemented, the Wizard of Oz experiment examines a use case whose logic does not yet exist in technical form. The Wizard replaces the model and provides flexible responses, enabling dialogues that are much more realistic. This yields insights that can be addressed during the early conceptual phase, rather than only becoming apparent after technical implementation.
RCS - Rich Communication Services
--> Go to BOTwiki
Rich Communication Services (RCS) is a mobile communication protocol standardized by the GSMA and is considered the technical successor to SMS and MMS. Unlike traditional text messages, RCS supports multimedia content, interactive buttons, carousels, and verified sender identities directly within the device’s pre-installed messaging app.
This provides companies with their own channel that doesn't require downloading an app and integrates seamlessly into an AI agent platform . RCS is thus a key component for conversational AI in the messaging environment and complements established channels such as voice and web chat.
How Rich Communication Services Works Technically
RCS runs over the mobile data network or Wi-Fi and uses the RCS profile provided by the mobile carrier. On Android, the system is integrated under the name RBM (Rich Business Messaging); Apple has also incorporated the standard into the Messages app with iOS 18. Businesses do not communicate directly with the end device, but rather through an RCS aggregator that establishes the connection to the carrier networks.
The sender's identity is verified through a verified brand listing that includes a logo, name, and a blue checkmark. This helps reduce phishing attempts and allows recipients to immediately recognize that they are communicating with a verified company.
What types of content does RCS support?
Compared to SMS, RCS offers a much wider range of interactive features. Recipients can view preview images, reply directly, or use buttons to enter a structured conversation. Typical features include:
- Rich Cards with a title, image, description, and multiple action buttons.
- Carousels that display multiple products or dates to choose from.
- Quick replies for predefined options such as Yes, No, or "Please call me back."
- Share locations, files, and maps directly from the chat.
- Read receipts and typing indicators for a conversational experience.
These elements replace unstructured free-form text with clearly structured dialogues, making them a good fit for intent-based intentarchitectures.
Implications for voice, chat, and email
RCS provides a useful addition to the voice channel: a voicebot on the service hotline can send longer selection lists or confirmation links directly to the caller via RCS, rather than simply reading them out over the phone. This transforms the traditional IVR from a “body without a brain” into an AI-native voice solution that routes calls to the appropriate channel in real time.
In a chat context, RCS complements existing web chat and messaging channels without requiring users to install an additional app. For asynchronous communications—such as appointment confirmations, shipping details, or contract documents—which are typically handled via email today, RCS can offer a faster and more measurable alternative because read receipts and response times are transparent.
Frequently Asked Questions (FAQ)
RCS is a messaging protocol standardized by the GSMA for mobile network operators that technically replaces SMS and MMS. It allows for multimedia content, buttons, carousels, and verified sender profiles to be displayed directly within the smartphone’s pre-installed messaging app, without requiring users to install an additional app.
SMS is limited to plain text and very short messages and does not offer any interactive features. RCS, on the other hand, supports rich media, read receipts, and verified brand identities. Unlike WhatsApp, RCS is delivered directly through the mobile carrier and the system messaging app, so no third-party app is required.
RCS is particularly well-suited for structured service interactions such as scheduling appointments, tracking shipments, booking confirmations, self-service inquiries, and transactional notifications. When combined with a voicebot, the channel can also be used to send longer selection lists or confirmations from a phone call directly to a smartphone.
It makes sense to integrate these features via a central AI agent platform, where intents, knowledge AI, and AI workflows are defined once and used across all channels. RCS is then integrated as an additional output channel, running in parallel with voice, web chat, and email. Well-designed multi-agent orchestration is essential to ensure that dialogues remain consistent and that users can switch channels without losing context.
> Back to BOTwiki