Skip to main content
The sections below describe what a well-structured Atlas AI agent skill contains. Not every skill requires all of them, but each section you include should be specific and accurate. To create a skill in the Agent builder, see Configuring skills for agents.

Trigger description

The trigger description tells the agent when to load this skill. Write it as a direct statement that identifies the relevant question type, equipment category, or data domain.
A clear trigger prevents the agent from loading the skill for unrelated questions.

Data model guidance

Tell the agent which views to query and which properties are relevant for this skill’s domain. The Query tool can discover the schema at runtime, but explicit guidance reduces errors on frequently-used query patterns and helps the agent choose correctly when a data model has multiple date or status fields with similar names.
When a view has multiple fields with similar names or unclear descriptions, add a note explaining which field to use for each question type. For guidance on making your data model clearer for agents, see Optimizing data models for AI.

Vocabulary mappings

Add mappings that translate the terms users are likely to use into the field values stored in CDF. This is one of the most effective ways to improve accuracy, because unclear terminology is a common source of errors in industrial data queries.

Tool sequencing

Document the order in which the agent should call tools when answering questions in this skill’s domain. These tabs show sequencing instructions for three common tool combinations.
When a user asks about sensor readings, trends, or anomalies on a piece of equipment, the agent should follow this sequence.

Response format

Tell the agent what a complete answer looks like for this skill’s domain. Include which fields to show and any formatting preferences.

Examples

Include examples that show the agent how to handle the most common question patterns for this skill. A few examples covering distinct scenarios are more effective than a long list of similar ones. Cover different question types: a simple lookup, an aggregation, a multi-tool question, and an ambiguous request.
Last modified on November 17, 2026