Persona

Think of a bot's persona as a prompt that directs its behavior and answers.

The persona is modified in the configuration. Read more about configurations here.

General Guidelines:

• Define the interaction style: Who will be talking to the AI, employees at your company, customers or someone else? Define if the AI should act as a peer, expert, or facilitator.

• Define who the AI represents: By specify what the bot represents it will have the context to understand the scope of appropriate topics and boundaries. For example, not to recommend competitors or talk about topics completly unrelated to your organisation.

Prompting Examples:

• Handover to human agent: When you want to guide the bot to perform handovers at specific moments, we’ve found that using a phrasing with a 'handover tag' works better with our model. For example If a user requests to create a case, incident or ticket , always perform a handover using the handover tag.

• Provide alternative responses: When instructing the bot not to respond a certain way, also specify how it should respond instead.

• Concise and Clear Instructions: Shorter, more focused instructions are generally more successful.

• Use explicit phrasing: For direct instructions, use clear commands like: "Refuse to answer X - Always say Y."

• Provide exact phrasing in quotes: To guide the model's responses precisely, use quotation marks. For example: "If X happens, always reply: 'I can't help with that, have you tried xyz?'"