Configuring Engineering Assistant agent

Edit online

You can configure the Engineering Assistant agent to customize the AI model and the quick starter prompts used for natural language interactions with requirements.

About this task

You can configure the Engineering Assistant agent to control how it processes natural language queries and how quick starter prompts are presented to users. The agent supports the following configuration options:

  • AI model settings: Specify or update the AI model that the agent uses to interpret natural language input.
  • Default quick starter prompts: Modify the built‑in prompt, that is Summarize requirements, to align with your organization’s terminology and workflow.
  • Custom quick starter prompts: Create new quick starter prompts by defining a title and description. Custom prompts appear alongside the default ones in the user interface.
  • Quick starter enablement: Enable or disable individual quick starter prompts. You can enable up to five quick starters at a time.

Procedure

  1. From the Agent management page, click the Settings icon in the Actions column for the Engineering Assistant agent.
    TheEngineering Assistant configuration page opens.
  2. Optional: Turn on Show default value to view default settings.
    This toggle displays the default values for all configuration fields, helping you understand the default settings before making changes.
  3. In the Model ID field, review or update the AI model identifier.
    The default model is mistralai/mistral-small-3-1-24b-instruct-2503. For more information, see Model configuration.
    Note: The model ID format depends on your configured LLM provider:
    • For IBM WatsonX, use WatsonX model names (for example, mistralai/mistral-small-3-1-24b-instruct-2503 or meta-llama/llama-4-maverick-17b-128e-instruct-fp8)
    • For AWS Bedrock, use AWS Bedrock model names or cross-region inference profile IDs (for example, mistral.mistral-small-2402-v1:0 or us.meta.llama4-maverick-17b-instruct-v1:0)

    For more information about configuring your LLM provider, see Setting up LLM providers.

  4. In the Quick Starters section, manage the quick starter prompts.

    Quick starters provide predefined prompts that users can select for common tasks. The section displays the number of enabled tiles (for example, 1/5 tiles enabled).

    Note: You can enable a maximum of 5 quick starters at any time.

    You can perform the following actions on quick starter prompts:

    Action Description
    Edit a prompt Click the edit icon next to the prompt to customize the prompt text and description to match your organization's requirements workflow.
    Enable or disable a prompt Use this toggle to display the quick starter in the agent interface. When enabled, the icon shows green and will be displayed in the interface.
    Add a prompt ClickAdd, then enter the prompt title and description for the new quick starter.
    Remove a prompt Click the delete icon next to the prompt to permanently remove it from the configuration.
  5. Optional: Click Restore default for any section to reset values to their original settings.
  6. Click Save to apply your configuration changes.
    The agent configuration is updated and the changes take effect immediately.

Results

The Engineering Assistant agent now uses your customized settings and quick starter prompts when processing natural language queries.