Step 1: Access the Playground #
- Go to the “playground” section in your AI platform.
Step 2: Set System Instructions #
- Instead of referring to any documents, select the option to write “system instructions”.
- Write detailed instructions such as:
- Your agent’s name.
- Desired language style (e.g., reply in soft language, reply precisely).
- Specify that the agent should reply to greetings with a greeting and a follow-up question.
- For example: “User will send you a greeting. Reply back with a greeting and a question about support, sales, etc.”.
Step 3: Test Greeting Responses #
- Send a greeting message (such as “hi”) in the playground to see how your AI agent replies.
- Modify the instructions as needed to adjust the tone and content of the greeting response.
Step 4: Create Conversation-End Responses #
- Write instructions for ending conversations, such as replying to “thanks” or “bye”.
- For example, instruct the agent to say “You’re welcome,” or “Goodbye, see you later” when the user sends thank you or farewell messages.
Step 5: Experiment and Refine #
- Try various messages and refine the instructions for both greeting and conversation-end scenarios to achieve the desired behavior.
- You can play with the instruction details to customize for different use cases and personalities.