Skip to navigation
Tools

get_ada_configuration

Fetches AI Agent configuration: playbooks (summary), tools, custom instructions, and company description. Use this to understand what the Agent is currently configured with.

Example prompts

  • “Summarize our current AI Agent configuration.”
  • “What playbooks do we have configured?”
  • “Show me our custom instructions.”

Parameters

ParameterTypeRequiredDescription
cursorstringNoOpaque cursor returned as next_cursor by the previous call. Omit it to fetch the first page.

Pagination

Results are paged by size. If the response has a non-null next_cursor, pass it back as cursor to fetch the next page. Repeat until next_cursor is null before you answer a question about the whole configuration.

The tool rejects the cursor if a playbook, tool, or custom instruction is added or removed between calls, including a tool being enabled or disabled. It also rejects the cursor if the company description changes. Call again without cursor to start from the first page. Other edits, such as a change to the text of a custom instruction, do not reject the cursor. The pages are not a fixed snapshot of the configuration.

An item too large for one page arrives with its longest text cut and a truncated_fields list that names the cut fields. The full text of those fields is not available through this tool.

Response

Each page returns items, total_count and next_cursor. The first page also returns AI_agent_name, the configured display name for the Agent.

Each item has an entity_type:

  • company_description: the persona and company context configured for the Agent. A long description arrives as several items with chunk and chunk_count. Join their text in chunk order to get the full description.
  • playbook: a playbook summary with ID, name, description, version, and active status. For full playbook details including steps, use list_entities with entity_type='playbooks' and provide the playbook ID.
  • tool: an enabled tool the Agent can invoke, with ID, name, type (api, code, or mcp), description, inputs, and outputs. An mcp tool also includes its provider. A disabled tool, or a tool on a disabled MCP connection, is not listed.
  • custom_instruction: an active instruction that guides Agent behavior, with ID, title, and text.

This tool does not return coaching or knowledge articles. Use search_coaching and search_knowledge to find those.