Recording pending: Write and review an agent prompt. Follow the written guide below.
Define the task
Write the desired outcome in one sentence before editing the prompt. For example: help customers understand a support process using approved information, and direct account-specific requests to support.1
Set the role and scope
State which requests the agent handles and which require a person or another system. Avoid a broad instruction to handle every customer request.
2
Specify how to use information
Tell the agent to use approved sources and acknowledge missing information. Do not invent prices, policies, account state, or actions that it cannot verify.
3
Define action boundaries
Explain when an action requires confirmation. An instruction to check an order or contact a team is useful only when the corresponding integration exists and the caller has access.
4
Set the response style
Describe the preferred length, tone, and follow-up behavior. Set the response language through the configuration’s language policy rather than conflicting instructions scattered through the prompt.
5
Review the complete configuration
Read the prompt with the first message, knowledge attachments, tools, and language settings. Review the version diff before publishing the changes.
Example instructions
This is an example of prompt structure, not a promise of deployed behavior. Adapt it to your approved support process.Prompt and first message
The prompt lives atconversation_config.agent.prompt.prompt; the first message lives at conversation_config.agent.first_message. The first message opens the interaction. It should match the task and avoid implying access to private account information.
For the example above, a suitable first message is: “Hello. I can help explain our support process. What do you need help with?”
Review scenarios
Before publication, write expected outcomes for a normal question, an ambiguous request, missing information, an out-of-scope task, and a request involving sensitive data. Use these cases to review the prompt and attachments now, and retain them for runtime testing when execution is available.Automated response-test invocation is currently gated in the documented implementation. A stored test definition or a published prompt does not prove that a test ran successfully. Check current availability.
Continue
Read agent configuration for the field structure and versions and drafts for reviewing changes. The Update agent reference defines the API request shape.Frequently asked questions
Should I put all source documents in the prompt?
Should I put all source documents in the prompt?
Keep instructions focused. Use reviewed knowledge attachments for factual material and inspect their stored content before relying on them.
Does an instruction to take an action enable it?
Does an instruction to take an action enable it?
No. The appropriate tool, resource access, and execution path must exist. The prompt should explain the action boundary without claiming a completed action.