Symlink is an environmental data system that bridges human and non-human communities through responsive design. In Summer 2023,Symlink was exhibited at Design in the Age of AI at Space10, Copenhagen Architectural Festival, 3 Days of Design Festival, and the World Congress of Architects Conference.

Operated by a large language model, the system encompasses ecosystem data collection, synthesis, and recommendation, materialising through data sensors and installations that mimic the native flora and architectural vernacular of the region. This submission serves as a case study in Sintra, Portugal, employing its own system for design guidance and image creation.

By using mock data of 45 environmental variables specific to the Sintra region, a large language model (GPT-4) is tasked to identify ecosystem health discrepancies and give design recommendations for improvement. The model, contextualised to the Sintra community, translates the suggestions into prompts that Midjourney uses to create images. The output demonstrates potential visuals to incentivise behaviour change in the community, while also showing the potential of the system itself. The system's physical design is aimed to be transparent and accessible to the public, aligning with the ecology and architectural history of the region.

Quantifying changes within complex ecosystems can be challenging. Utilising data as a mediator between human and non-human communities enables adaptations to occur automatically, such as architectural facade modifications, irrigation pathway changes, or energy-sharing dispersal. For manual behavioural changes, the AI suggestions convert multivariate data into a clear set of directions for an individual or community, helping increase the likelihood of the change occurring.

In Sintra, forest and buildings blend as castles and towns intersperse the vegetative landscape, with varying ecological communities in close proximity. Facing environmental challenges such as water management, coastal erosion, and desertification, Sintra is ideal for a data-driven responsive design. The Symlink system was trained on Sintra’s unique population, climate, and ecological issues, and it prioritised the detection of those risks in the mock dataset. For example, due to desertification risk, the system on its own accord proactively recommended action to address declining soil moisture percentages.

Emphasising non-human data points like plant-pollinator interactions and carbon sequestration, this project enables local ecology to influence community decisions through data accessibility. The need for diverse data collection led to a data sensor design that mimics its surroundings. Sensors resembling the Sea Fig plant collect data on their population and visually indicate declining populations on site. Azulejo tile sensors in Sintra gather microclimate data and visualise data, like decreasing air quality, by altering tile colour or pattern. While the system activates ecological data, it also integrates the data into the environment itself.

This vision enables individuals to improve their communities by concentrating on mediating the effects of climate change in their environments, which also enhances human habitation. Rather than offering a one-size-fits-all solution, this process is made to adapt to different communities and their specific needs. The system serves as a foundation for designing unique, context-specific datascapes that reflect the distinct vernacular and needs of a given environment. By focusing on incremental positive change, this inclusive and adaptable Symlink approach should create a future that is fit for the many, rather than the few.