IAB Australia releases AI prompting framework for marketing teams
IAB Australia has released a vendor-neutral framework to guide how marketing, advertising and creative teams use large language models. The five-part LLM Prompting Framework addresses inconsistent AI use across briefs, planning, content development, campaign analysis and audience work.
The framework comes as Australian businesses shift from individual AI experimentation to structured adoption across teams. While LLMs speed up tasks like briefing and reporting, inconsistent prompting creates risks around accuracy, privacy, brand safety and creative alignment.
Five editions for different roles
The framework includes editions tailored to specific functions. The Creative Edition is built for creative directors, copywriters, art directors, designers and content creators.
It focuses on brand voice and visual metaphors. Examples cover developing campaign concepts, writing copy across platforms, adapting creative for different channels and formats, building content strategies and refining work through iteration.
The other four editions serve buy-side teams (brand marketers and agencies), sell-side teams (publishers), general users and adtech engineers.
What the framework addresses
Each edition includes practical prompts for common workflows. The Creative Edition provides examples for concepting, copywriting and content production.
The framework aims to improve output quality and consistency while reducing risks linked to privacy, brand safety, errors, hallucinated data and misaligned creative work.
Jonas Jaanimagi, Tech Lead at IAB Australia, said the framework acts as connective tissue between human intent and machine execution. "It is no longer enough to simply write better prompts; businesses must now manage entire agentic workflows within rigorous, industry-standard guardrails for privacy, brand safety, and transparency," he said.
Who built it
The IAB Australia AI Working Group developed the framework with input from 20 member organizations including Adobe, Google, Microsoft, News Corp Australia, Paramount, WPP Media and others.
Mark Titley, Senior Commercial Data Strategist at Paramount and a working group member, said the guidance required cross-functional collaboration. "Developing practical AI prompting guidance for the Australian advertising industry required genuine cross-functional collaboration," he said.
For creatives looking to improve their AI skills, resources on prompt engineering and AI for creatives provide deeper training on these techniques.
Your membership also unlocks:
