Brandora: Automating Brand-Compliant Marketing Content Creation with Retrieval- Grounded Cloud Generative AI
Year: 2026
Type: article
Abstract: General-purpose generative models used for advertising often invent prices, discounts, certifications and environmental claims that a brand cannot support. This paper presents Brandora, a hybrid edge and cloud generative AI system that drafts advertisement copy and visuals grounded in a company's own product catalogue and brand guidelines. A retrieval-augmented generation pipeline retrieves the catalogue records closest to a marketer's brief and always adds every mandatory guideline to the context of a locally hosted large language model, which returns a structured brief listing its sources and the requested details it could not support. A text-free prompt is sent to a serverless text-to-image model on Cloudflare Workers AI, and the approved copy is typeset onto the returned image, which avoids the malformed lettering that diffusion models produce. A reviewer approves every poster and each decision is written to an audit log. The paper also specifies extensions to the same architecture and an evaluation protocol of sixty briefs, including adversarial requests, for measuring guideline violations, grounding precision, image text artifacts, latency and reviewer effort. On 200 development queries, the hybrid retrieval stage ranks the correct product first in 97.5 percent of cases.
Institution: Dayananda Sagar University
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7225773029
FWCI:
Cites:
Cited by:
Related to: