UMT

Get Defaults

Returns the site-level default settings: default brand, default target groups, default visual style, and primary/secondary brand colors. Call this at the start of a session to pre-load defaults — use the returned IDs to load the full brand and target group profiles via get_brand and get_target_group.

Get All Brands

Returns a list of all available brands with their IDs and titles. Use this to let the user choose a brand, then call get_brand to load the full brand profile.

Get Brand

Returns the full brand profile including brand language instruction, brand personality, USPs, positioning, values, promises, messages, and keywords. Always load a brand before generating any text — the brand_language_instruction field is the primary style constraint for all outputs.

Get All Target Groups

Returns a list of all available target groups with their IDs and titles. Use this to let the user choose a target group, then call get_target_group to load the full profile.

Get Target Group

Returns a target group profile with persona type, communication style, and a detailed instruction. Apply the instruction field to adjust language, tone, and framing of all generated text toward this audience.

Get All Contexts

Returns a list of all available thematic contexts with their IDs and titles. Call this automatically before generating any text content to check whether relevant contexts exist. Present matching contexts to the user for confirmation, then load confirmed ones with get_context.

Get Context

Returns a thematic context with a detailed instruction field containing background information, facts, and topical framing. Use as an additional content layer when the context is directly relevant to the text being generated.

Get All Styles

Returns a list of all available visual image styles with their IDs and titles. Use this to let the user choose a style, then call get_style to load the full style definition.

Get Style

Returns a visual image style definition with: concept (short description of the style), instruction (characteristic style attributes grouped by aspect, e.g. composition, light, color, texture), theme_world (allowed subjects and scenes that fit the style), and exclusions (elements that must not appear in the image). Use these fields to compose image generation prompts that follow the defined visual style.

Get All Text Formats

Returns a list of all available text format templates with their IDs and titles. Use this to let the user choose a format, then call get_text_format to load the full template.

Get Text Format

Returns a text format template with: description (one-sentence summary of the format), text_structure (structural outline defining heading levels and content blocks), custom_instructions (format-specific style rules that override general brand language), and sample_text (a reference example). Apply text_structure as a strict structural constraint and custom_instructions as binding style rules — they take precedence over the general brand language instruction.

Get All Visual References

Returns a list of all available visual references with their IDs and titles. Use this to let the user choose a reference, then call get_visual_reference. Only relevant for image generation tasks.

Get Visual Reference

Returns a visual reference for image generation with: category (e.g. person, product, place), topic (factual short description), and reference_image_urls (array of image URLs). Use when generating images that must depict a specific known subject — pass the reference_image_urls as visual input to the image model to ensure likeness or object consistency.

Get All Grounding Pages

GEO TASKS ONLY. Do NOT use for regular content production — use get_all_contexts and get_context instead. Only call this when the user explicitly asks for Generative Engine Optimization (GEO) work: checking how AI systems understand an entity, monitoring AI search presence, or generating entity-specific grounding content.

Get Grounding Page

GEO TASKS ONLY. Do NOT use for regular content production — use get_context instead. Only call this for explicit GEO work. Returns a machine-readable fact page for an entity with: main_content (structured factual body), main_content_jsonld (JSON-LD structured data), grounding_verification_questions (branded questions to verify correct AI understanding), and intent_simulation_questions (non-branded questions to test AI search presence).