Configure Instructions to create consistent and accurate responses to ensure the Freddy AI Agent follows your business processes and communication guidelines.
This article contains |
Benefits of Instructions
This feature helps you:
- Align the bot's communication style with your company’s standards.
- Define specific scenarios where the bot should or shouldn’t respond.
- Provide guidance on the tone and content of responses to enhance customer interactions.
Add and Manage Instructions
- As an Admin, navigate to Freddy AI Agent > Configure > Instructions.
- Find the text box with default instructions along with Writing Tips for guidance.
- You can edit, delete, or add more instructions that reflect your brand identity and business logic.
- Click Save.
Note: All instructions combined should not exceed the 1000-character limit.
Write Effective Instructions
To help you create clear and effective instructions for the bot, we provide a Writing Tips section.
Examples of Good Instructions
Use the following examples as a reference to craft clear, brand-aligned, and compliant instructions for your Freddy AI Agent:
- Style & Formatting Guidance
These instructions help ensure consistency in tone and response length.- Keep responses concise and relevant, ideally under 300 words.
Example: “Respond with short and direct answers; avoid unnecessary elaboration.” - Acknowledge customer concerns before presenting solutions.
Example: “Start responses by acknowledging the customer’s issue in a polite and professional tone.” - Use a formal and respectful tone for all customer interactions.
Example: “Maintain a professional tone across all responses; avoid slang or overly casual language.”
- Keep responses concise and relevant, ideally under 300 words.
- Terminology & Brand Language
Define how business-specific terms or roles should be referenced.- Use internal terms familiar to your customers.
Example: “Refer to delivery personnel as ‘Captains’ instead of ‘agents’ or ‘executives’.” - Treat synonymous terms interchangeably based on your business vocabulary.
Example: “Use ‘recipient’ and ‘customer’ interchangeably—they both refer to the end user.”
- Use internal terms familiar to your customers.
- Topic-Specific Boundaries
Clearly state what the bot should not engage with or respond to.- Avoid competitor-related discussions.
Example: “Do not respond to queries comparing our services with competitors or mentioning other brands.” - Exclude medical or clinical advice.
Example: “Do not provide medical or clinical recommendations. If asked, indicate that this is outside the bot’s scope.” - Do not comment on financial or legal matters.
Example: “Refrain from answering questions that involve legal disclaimers or financial advice.”
- Avoid competitor-related discussions.
What Not to Include in Instructions
- Do not include complete responses
Instructions should not contain actual reply content, links, or customer-facing actions.
Avoid instructions like: “If a customer wants to cancel their account, share the cancellation form link: https://example.com/form”
Such responses are considered critical and should be added in the QnA section, not in the Instructions. Including them here can overcomplicate your instructions and reduce the effectiveness of the AI agent. - Avoid using Instructions for Business Hours Handling
Instead of including time-based instructions like: “Outside these hours, ask the customer to leave their email address.”
Use the Business Hours feature to configure after-hours behavior. - Do not define Agent Handoff Behavior depending on user properties
Instructions such as: “If the customer’s plan is not “Premium” then don’t transfer chat to humans”.
If you need customized agent handoff rules, please contact the Support Team to explore implementation options.
Do not define Agent Handoff Behavior on Negative feedback or Fallback
Instructions for handling fallback or feedback as: “Before triggering agent handoff due to fallback take confirmation from the user if they would like to speak with an Agent before transferring the chat.” These settings can be configured in Preset Messages.