Quilty, an AI startup, has entered the industry claiming its technology can accurately forecast a film's box office success simply by analyzing its script. However, initial user experiences with Quilty's product have been met with skepticism. Despite access to vast datasets, the system erroneously predicted that the script for "Christy," a film that ultimately flopped at the box office, would outperform "Sinners," an Oscar-winning blockbuster.
Following a common refrain among AI executives, Quilty's founders envision their tool as a means to "democratize" the film industry, offering aspiring creatives access to assistive technology. A high Quilty score, for instance, might open doors with producers, while a low score could signal the need for further script revisions. Yet, in its current state, Quilty appears to be a composite of pre-existing AI systems, and the company has not yet demonstrated its technology possesses the nuanced judgment or analytical prowess required to identify a future cinematic hit, let alone a critically acclaimed one.
Founded by film producers Simon Horsman and Daniel Wood, Quilty leverages AI to scrutinize scripts and produce comprehensive reports on a project's likelihood of success. After receiving an unproduced script, Quilty's technology assigns a score from 0 to 100, reflecting elements such as narrative quality, commercial viability, audience resonance, and estimated production costs. The platform positions itself as a foresight tool, offering users a glimpse into a project's future as they navigate the greenlighting process. Horsman and Wood are confident that Quilty is poised to become an indispensable component of how traditional production studios operate.
In a recent discussion, Horsman and Wood emphasized their commitment to "keeping humans in the loop" rather than fully automating the pre-production workflow. During the company's formative stages, they actively sought feedback from other creatives, many of whom expressed reservations about generative AI's potential to negatively impact employment and de-skill human workers.
"We agree with a lot of the negative sentiment towards AI, but what we’re trying to do is enable human creativity," Horsman stated. "Quilty is really about development and giving the users — be they a writer, producer, buyer, financier, or studio execs — as much information as possible to make an informed green light decision."
Instead of relying on a single, proprietary AI model for script feedback, Quilty integrates a variety of widely available AI tools to provide diverse analytical perspectives. Users simply upload their text scripts to the platform, and within minutes, a detailed report is generated. This report includes an estimated budget, outlines of key story beats, and character analyses. The service is priced at $50 per individual analysis, with discounted rates available for bulk purchases.
The concept for this modular analytical approach originated with Daniel Wood, Quilty's CTO, several years ago during a personal legal dispute involving a real estate matter. Opting against hiring an attorney, Wood first consulted ChatGPT, which promptly responded with "I’m not a lawyer; go find someone else to help you."
"Then I went to Gemini, which worked a lot better for a while, because I had a larger context window," Wood recalled. "But then I was on X, and saw stupid Elon Musk talking about Grok getting the best lawyer score ever for an AI model, and I was like, ‘Let me check that out.’" (The outcome of Wood's legal dispute was not disclosed.)
This personal exploration illuminated for Wood how different consumer-grade AI models can excel at specific tasks. His experiences directly influenced Quilty's methodology for assessing a script's potential. For instance, recognizing that "Gemini is fantastic for structure and patterns," Quilty utilizes it to generate "breakdowns" — comprehensive lists detailing all production elements of a film or show. For financial modeling, the company relies on a DeepSeek instance hosted on US servers. Narrative and character analysis, meanwhile, are handled through a combination of Claude and ChatGPT.
Wood explained that Quilty employs "context prompting," providing additional contextual data, to ensure high-quality outputs free from hallucinations. Quilty does not train any of the models it uses for film reports or scores. Wood emphasized that this is a strategic advantage, as it allows Quilty to readily integrate new and improved models into its workflow as they become publicly available.
"When Claude Mythos comes out and I can see that it’s a better LLM, all of a sudden, my whole software gets better," Wood remarked, referring to the powerful new model currently restricted to a select group of organizations for cybersecurity. He added, "If some Chinese models suddenly become better than all these US frontier models, why wouldn’t I just use those instead?"
While the modularity of Quilty's technology stack offers agility in updates, it also introduces complexity in fully comprehending how the platform translates a script into a multitude of metrics that purportedly quantify intangible elements, such as audience reactions to a film that doesn't yet exist. Predicting cinematic success has been fundamental to Hollywood since its inception, traditionally performed by human experts with a nuanced understanding of audiences.
No AI firm has yet developed a model capable of truly replicating human thought processes or the subjective nature of artistic opinion. However, Quilty’s founders believe their "sentiment engine" offers the next best alternative for script assessment. This engine incorporates tools like VADER (Valence Aware Dictionary and sEntiment Reasoner), open-source software that measures the positive or negative sentiment expressed within text.
Horsman and Wood maintain a steadfast belief that Quilty can accurately gauge how a project "addresses the cultural moment" and provide reliable box office projections. They cited "Revenge of the Nerds" as an example of a popular older film that would now receive a lower Quilty score due to its comedic portrayal of sexual assault, which modern audiences would find in poor taste.
When questioned about Quilty’s higher score for "Christy" (which grossed approximately $2 million) compared to "Sinners" (which earned $370 million), Horsman and Wood attributed the platform’s judgment to "the fact that Sydney Sweeney is really, really popular." They argued that, on paper, Sweeney's star power combined with the lower production cost of biographical boxing dramas, made "Christy" a safer bet than fantasy/action features like "Sinners." However, this scenario underscores the inherent limitations in Quilty's predictive logic. Horsman and Wood conceded that there are situations where Quilty simply cannot foresee all factors influencing a film's financial performance or audience reception.
For instance, Quilty could not have predicted that Elijah Bynum’s "Magazine Dreams" (produced by Horsman) would be disrupted by actor Jonathan Majors’ highly publicized legal issues in 2023. Similarly, nothing within "A Minecraft Movie's" script would have indicated to the platform that the "Chicken Jockey phenomenon" would contribute to the film's significant success. Horsman and Wood expressed a long-term aspiration for Quilty to anticipate such events, though the practical realization of this goal remains difficult to envision.
Despite the accompanying fanfare, Quilty essentially offers indirect access to a collection of large language models tasked with predicting the future of unproduced artistic works. While it would be remarkable if these AI tools performed as Quilty claims, most are sophisticated pattern recognition and mimicry machines, still far from possessing a genuine understanding of what humans find entertaining.
The Editorial Staff at AIChief is a team of professional content writers with extensive experience in AI and marketing. Founded in 2025, AIChief has quickly grown into the largest free AI resource hub in the industry.