Semanticus
Documentation

Data Agent

Configure Fabric data agents scoped to the open model: generate an agent's configuration from your model, edit its instructions and example queries, preview every change as a dry-run, and publish explicitly. Available in the Studio and over MCP.

Review before every write

Reading and editing the schema does not publish it. Create, update, publish and delete actions show the exact request first. A write happens only after explicit confirmation, and Data Agent writes require Pro.

In the Studio

The Data Agent tab lists the data agents in a workspace and lets you open one to see its draft (and published, if any) configuration: the AI instructions, each data source, and the example queries. You can generate a fresh configuration from the open model, edit the schema, instructions and examples, then publish. A persisted auth-mode picker and tenant field sit in the header, so the tab can target the right Entra tenant when your signed-in identity differs from the model's connection.

The Data Agent tab in the Semanticus Studio: a workspace's data agents with their draft configuration, AI instructions and data sources.

Over MCP

Reads are free. Generating, editing and publishing are Pro, and every write previews first.

list_data_agents                       # the agents in a workspace (live read, free)
get_data_agent <id>                    # one agent's decoded draft + published config (free)
generate_data_agent_config             # build a semantic_model datasource from the open model (Pro)
create_data_agent                      # Pro; dry-run by default, commit=true creates
update_data_agent                      # Pro; replaces only the parts you pass (read-modify-write)
publish_data_agent                     # Pro; copy draft to published (dry-run by default)
delete_data_agent                      # Pro; dry-run by default, commit=true deletes

Generate config from the open model

generate_data_agent_config builds a complete semantic-model datasource configuration from the open model in one shot: an element tree of every table, column and measure, carrying the model's descriptions, with each element's selection honoring hidden objects and your Prep-for-AI AI-data-schema exclusions, and the AI instructions seeded from the model's linguistic-schema instructions. It returns the JSON for you to review and writes nothing; feed it to update_data_agent to apply. Workspace and artifact ids come back as placeholders, so you resolve the real Fabric ids before applying rather than guessing them.

Dry-run, then publish

create_data_agent, update_data_agent, publish_data_agent and delete_data_agent are all dry-run by default: with commit=false each returns the exact request it would send and changes nothing, and commit=true executes it. update_data_agent is a read-modify-write that re-emits every existing part plus your changes, so it never drops parts it did not author, and AI instructions are capped at 15,000 characters. publish_data_agent copies the draft parts to published and records a publish description.

The distinction from Prep-for-AI

Data-agent configuration (agent instructions and example queries on a Fabric data-agent item) is distinct from a model's own Prep-for-AI settings (Q&A, synonyms, AI instructions on the semantic model). The model-side settings are on the AI-Readiness tab.

Free reads; Pro writes

Listing and reading agents is free. Generating a config from the open model and every write (create, update, publish, delete) are Pro, and every write previews as a dry-run before you commit. See Pro.