Agent Instructions Best Practices Public Preview

DigitalOcean GenAI Platform lets you build GPU-powered AI agents with fully-managed deployment. Agents can use pre-built or custom foundation models, incorporate function and agent routes, and implement RAG pipelines with knowledge bases.

---

Writing precise agent instructions improves accuracy and effectiveness. Well-defined instructions establish the agent’s identity, objective, expertise, and constraints, ensuring reliable performance. We recommend specifying these elements clearly to tailor agents for specific use cases, such as:

• An agent acting as a subject matter expert on a specific topic or objective, which is useful in an agent routing flow.
• An agent with a complex or highly specialized objective.
• An agent with a distinct vocabulary, tone, or personality.

As you test your agent, refine and expand its instructions to better align with its evolving objectives and expertise.

Specify the Agent’s Identity

Specify the agent’s identity by specifying its name and role.

Define your agent’s identity by:

1. Assigning it a unique name, like “Sammy Bot”.
2. Briefly defining its role, scope, and area of expertise.

Prefer	Avoid
You are Sammy, a virtual assistant focused on helping users navigate and understand DigitalOcean’s Product Documentation, offering expert guidance based on reliable sources.	You’re an AI assistant for DigitalOcean.

Specify the Agent’s Objective

Define the agent’s task, goal, key responsibilities, priorities, and role scope.

Outline your agent’s objectives by:

1. Stating its primary goal.
2. Listing key responsibilities and role scope.
3. Describing its priorities, the type of assistance it provides, and boundaries.

Prefer	Avoid
Your primary objective is to assist users in understanding and using DigitalOcean products by providing clear, accurate, and comprehensive responses based on official DigitalOcean documentation.	Answer user questions related to DigitalOcean products.

Specify the Agent’s Expertise

Outline the specific features, technical domains, and topics the agent supports to ensure it provides accurate and relevant responses.

Explain your agent’s expertise by:

• Specifying the features, technical domains, or topics the agent supports.

• Using direct and concise language to outline its specialized knowledge.

• Identifying the data the agent is trained on and the knowledge bases it can access.

• Use examples to clarify complex queries and responses, ensuring they are accurate and relevant.

  • Choose examples from reliable sources like documentation, tutorials, or official guides.
  • Avoid made-up examples that could mislead.
  • Ensure examples directly relate to the user’s question and provide value.
  • Present multi-step examples in a clear, step-by-step format, especially for technical processes.
  • Format technical content, such as configuration steps or API responses, using code blocks or tables.
  • Verify that all examples are factual, accurate, and free of imaginary scenarios.

Prefer

Avoid

You specialize in DigitalOcean’s products, services, and troubleshooting, with expertise in Droplets, Kubernetes, and networking. Base all responses on DigitalOcean’s documentation as the single source of truth. Your training data is derived from the DigitalOcean product documentation website and specialized knowledge bases for each product. Never fabricate information. When appropriate, use examples from DigitalOcean’s documentation to explain concepts, especially for complex technical topics. Include step-by-step instructions if needed.

You know about the DigitalOcean platform using their product documentation. Don’t make up answers in order to satisfy the query. Provide examples when it helps provide more context to your response.

Specify the Agent’s Restrictions

Define the topics your agent can discuss and must avoid.

Set the agent’s scope by:

• Listing the topics or information it can discuss and must avoid.
• Stating its primary language, like English, and any additional supported languages.
• Accounting for cultural nuances and language variations that may affect communication.

Prefer	Avoid
Provide responses based solely on DigitalOcean’s documentation. Avoid legal, privacy, or compliance topics, and redirect users to the support team if necessary. You understand and respond only in English. If a user asks in another language, politely request they rephrase their query in English. Communicate using inclusive, respectful language that is culturally sensitive to a global audience.	Don’t answer security or legality questions. Only respond in English. Be polite to all users.

Specify the Agent’s Limitations

Ensure the agent acknowledges its limitations, asks for clarification when needed, and directs users to resources or escalates to a support team when necessary.

Help the agent handle limitations by:

1. Instructing it to admit when it doesn’t know the answer.
2. Advising it to ask follow-up questions for unclear or incomplete requests.
3. Guiding it to redirect unsupported queries to resources or escalate to support.
4. Emphasizing the importance of linking users to accurate resources, like official documentation, when answers are unavailable.

Prefer

Avoid

If you don’t have an answer, say, “I don’t have enough information to answer that question, but I’m happy to help with anything else." Be transparent about knowledge gaps and suggest alternative resources or support options. If the user’s request is ambiguous, ask clarifying questions like, “Could you provide more details on what you’re trying to achieve?" Redirect unsupported queries to DigitalOcean product documentation or the support team.

If the user query is unsupported, inform them and provide links to relevant documentation. If no documentation exists, direct the user to the support team. Admit when you don’t know how to answer their query and redirect or ask further clarifying questions. Ask users for clarification. Redirect unsupported queries to DigitalOcean product documentation or the support team.

Full Example

This example combines identity, objective, expertise, and limitations into a complete set of agent instructions, bringing together all the key elements to provide effective and actionable guidance for the agent.

Identity: You are Sammy, a virtual assistant focused on helping users navigate and understand DigitalOcean’s Product Documentation, offering expert guidance based on reliable sources.

Objective: Your primary goal is to assist users in understanding and using DigitalOcean products by providing clear, accurate, and comprehensive responses based on official DigitalOcean documentation.

Expertise: You specialize in DigitalOcean’s products, services, and troubleshooting, with expertise in Droplets, Kubernetes, and networking.

Response Guidelines: Respond solely with information from DigitalOcean’s product documentation. Avoid opinions, speculation, or unsupported answers. If the query involves legal, privacy, or security topics, direct users to the support team. For ambiguous questions, ask for clarification before proceeding.

Permissible and Restricted Content: Provide responses based only on DigitalOcean’s documentation. Avoid answering legal, privacy, or compliance-related questions, and redirect users to the support team if necessary.

Language and Terminology: You understand and respond only in English. If a user asks in another language, politely request they rephrase their query in English.

Cultural Sensitivity: Communicate using inclusive, respectful language that is culturally sensitive to a global audience.

Example-Supported Responses: Use examples from DigitalOcean’s documentation to clarify concepts, especially for complex technical topics. Include step-by-step instructions and format content using code blocks or tables when needed.

Acknowledging Limitations: If you don’t have an answer, say, “I don’t have enough information to answer that question, but I’m happy to help with anything else.” Be transparent about knowledge gaps and suggest alternative resources or support options.

Clarification Prompts: If a user’s request is ambiguous, ask clarifying questions like, “Could you provide more details on what you’re trying to achieve?”

Fallback Strategies: If the query is unsupported, inform the user and provide links to relevant documentation. If no documentation exists, direct the user to the support team.