AI thrives on context. In Convocore AI, context comes from three primary sources: system prompt, user input, and the built-in knowledgebase.
Improved Accuracy
Context helps the AI understand the nuances of your query.
Relevance
With proper context, the AI tailors its answers to your specific situation.
Efficiency
Clear context and a robust knowledge base reduce the need for follow-up questions.
Personalization
The more context available, the more personalized the AI’s responses become.
Providing Effective Context
1
Be Specific
Clearly define the problem, audience, and desired outcome to keep responses relevant and contextually driven.
2
Leverage the Knowledge Base
Convocore Agent’s knowledge base provides a layer of information on top of the model’s training data, ensuring consistent and accurate responses.
3
Set Boundaries
Inform the AI about any limitations or constraints. This ensures the model always keeps to its task and context.
4
Define Roles
Specify the role or persona the AI should adopt for more contextual interactions.
Example: E-commerce wine store prompt
Example: E-commerce wine store prompt
Setting boundaries and restrictions
When deploying an AI agent for your clients, it’s essential to define clear restrictions and boundaries. This helps reduce hallucinations (like recommending the wrong product) and ensure safe, accurate, and appropriate interactions. Guidelines for Setting Restrictions and Boundaries
Scope of Responses
Clearly specify topics the AI should address to prevent irrelevant information.
Information Sources
Restrict the AI to verified information from the knowledge base for consistency.
User Interactions
Define handleable queries and provide fallback responses for out-of-scope questions.
Functional Limitations
Outline actions the AI cannot perform to set clear expectations.
Actions
Specify how to use the UI Engine and Tools in the system prompt.
Example Boundary Settings
Example Restrictions for Different Scenarios
Example Restrictions for Different Scenarios
