Skip to main content
Once you’ve set up a Brand Kit, it becomes a creative constraint in Studio. The agent doesn’t just know your guidelines exist — it uses them as the frame for every generation.

​
@mentioning a Brand Kit

In the Studio chat, type @ followed by your brand kit name. The agent loads your brand context:
“@Acme Brand — create a hero image for our spring campaign”
Mentions appear as styled chips with thumbnails in your message. The agent confirms what it loaded before generating.

​
What the agent sees

When you @mention a brand kit, the agent gets:
  • Your uploaded logo files and reference images (as visual context)
  • Your defined color palette
  • Your typography preferences
  • Your full Voice & Rules document (voice, personality, banned language, audience cues, hard rules)
  • Any skills associated with the kit, if invoked in the same turn
It uses all of this as creative constraints — not decoration. “Always use natural lighting” in your Voice & Rules means the agent won’t generate studio-lit shots unless you override.

​
Per-deliverable references in briefs

In a Creative Brief, you can @mention specific assets inside individual deliverable sections. This gives you per-image control:
  • @Product Shot in Image 1’s direction — only Image 1 uses that reference
  • @Logo in Image 3’s direction — only Image 3 gets the logo
Assets mentioned at the brief level apply to all deliverables. Assets mentioned inside a specific deliverable apply only to that one.

​
Combining references with brand assets

Drag a mood board image onto the canvas and @mention your brand — the agent matches the reference’s style while staying within your brand’s visual language. Analysis data from the reference (lighting, composition, color) combines with brand constraints (palette, typography, guidelines) to produce work that’s both inspired and on-brand.

​
How photography is selected

Brand photography isn’t dumped into every prompt. The kit’s photo library is searched on the fly so the agent only sees the photos that actually match the brief.
  • Subjects and treatments — when you save a photo (or auto-extract from a brand book), Memo tags it with subjects (“hands”, “product”, “skyline”) and a treatment (“lifestyle”, “product”, “detail”, “editorial”, “portrait”). These power the search.
  • Semantic + keyword search — retrieval blends semantic embedding similarity with keyword matching, so “warm hands holding a mug” finds the close-crop hands shots even if the saved title says nothing about warmth.
  • Reference verification — before generation, the agent verifies the retrieved photos are actually relevant to your prompt. Off-target results are dropped instead of being forced into the output.
This is why a well-tagged photo library produces dramatically better generations than a dumping-ground one. Treat tagging as part of the kit setup, not an afterthought.

​
Color palette enforcement

When a Brand Kit is in scope, the agent treats your palette as a hard constraint, not a suggestion. Generations are guided to stay inside the named colors. To deliberately step outside, override in the prompt (“ignore the brand palette, use only warm earth tones for this one”).

​
Saving generations as brand assets

Generated images can be saved back as brand assets. From the image context menu on the canvas, select Save as Style Reference. The image plus its generation metadata become a first-class asset in your Brand Kit — available for future @mentions. The system compounds. Generate → save → reference → generate again. Each cycle builds on the last.