More time to create: How AI is supporting the creative industry
This Transformer project shows how AI can enhance creative workflows, improving efficiency while keeping human expertise at the core.
This Transformer project shows how AI can enhance creative workflows, improving efficiency while keeping human expertise at the core.
Whitenoise Studios is an award-winning creative agency specialising in brand, design and visual storytelling for clients across a wide range of sectors.
Known for precision, quality and strong client relationships, the team regularly manages complex document review and revision workflows where accuracy and accountability are critical.
A core part of Whitenoise’s work involves reviewing annotated documents and ensuring client feedback is correctly implemented across multiple revisions. This process was largely manual, requiring designers and project leads to cross-check comments against revised documents page by page.
As projects increased in size and complexity, this approach became:
Whitenoise wanted to explore whether AI could support this process, not by replacing human judgement, but by reducing repetitive manual effort and improving consistency and confidence.
Through the Transformer Programme, Whitenoise saw an opportunity to apply AI to a real operational pain point within their creative workflow.
The goal was to explore whether an AI-driven solution could:
If successful, this could significantly reduce time spent on verification while improving quality assurance and client trust.
Working in partnership with the Artificial Intelligence Collaboration Centre (AICC), Whitenoise developed a proof-of-concept AI tool designed to automatically verify whether reviewer comments in PDF documents had been implemented in revised versions.The collaboration focused on translating a real-world creative workflow into a technically robust but user-friendly AI solution. Together, the teams designed and built a Streamlit-based application that processes pairs of PDF documents, an original annotated version and a revised version, and analyses each comment individually.From a technical perspective, the solution combines several AI and data analysis techniques, including:
capturing comment text, author metadata and precise spatial coordinates from a wide range of PDF editing tools
preserving the relationship between comments and nearby content so the system can detect changes made in the correct context rather than relying on simple text matching
to interpret the intent of reviewer comments (such as requests for deletions, clarifications or additions)
enabling the system to recognise paraphrased or reworded changes rather than only exact text replacements
combining evidence from location-based changes, keyword matches and semantic similarity to classify comments as implemented, partially implemented or not implemented
Results are presented through an interactive dashboard, allowing users to explore outcomes at both document and individual comment level, with clear evidence trails to support human review and decision-making.
Crucially, the system was designed around human-in-the-loop principles, ensuring AI insights support creative teams rather than replace professional judgement.
Early results from the proof-of-concept demonstrate strong potential for operational impact:
By automating the most time-consuming aspects of document verification, Whitenoise’s team can now spend more time on creative work while maintaining confidence that feedback has been accurately addressed.
“This project showed us how AI can support our teams behind the scenes, reducing manual workload while improving confidence, consistency and accountability. It’s not about replacing people, it’s about giving them better tools to do their best work.”
Whitenoise has embed the AI solution directly into its day-to-day workflows, making it available across the entire team to support faster, more consistent document review at scale.
While the proof-of-concept focused on PDF-to-PDF verification, Whitenoise sees this as just the beginning. The ambition is to extend the solution to support larger and more complex review cycles, as well as new formats, from Word documents through to film, motion and other creative outputs, unlocking even greater potential across the creative process.
Following the successful handover of the project, Whitenoise has already secured £200,000 in funding from InterTradeIreland to further develop the solution into proprietary software, with a view to taking it to market.
This next phase marks an important step in turning an internal innovation into a scalable, commercial offering, reinforcing Whitenoise’s position at the forefront of AI-enabled creative practice.
This Transformer project demonstrates how AI can be applied thoughtfully within the creative industries, delivering measurable efficiency gains while keeping human expertise at the centre of the process.
Please note: This case study was written by the AICC team, with support from AI tools including ChatGPT and Claude Sonnet 4 to assist with refinement.
Innovation thrives through connection. Whether you're an SME, researcher, or professional exploring AI, we’re here to help.
