Chronic information dispersion regarding healthcare resources and community partnerships is a major barrier to efficiency in Primary Care. Fragmented data across institutional emails, static lists, and outdated websites hinders timely patient guidance and imposes a heavy administrative burden on healthcare teams.Over a three-month period, a systematic mapping of resources was conducted through a review of institutional communications and direct engagement with local authorities, community associations, and pharmacies. Data were structured into an analytical matrix including service categories, eligibility criteria, referral protocols, costs, and locations. This repository was integrated into a natural language interface (LLM), allowing doctors, nurses, and administrative staff to query the database using plain language. The system provides instantaneous, structured answers to practical queries, such as: "List all psychology consultations available in the area", "Where can a patient measure blood pressure locally and at what cost?", or "What are the eligibility criteria for low-cost dental care?". The interface simulates an interaction with an intelligent, locally-curated resource guide.To develop and implement a dynamic consultation interface based on a Large Language Model (LLM) to centralise and streamline access to local community and healthcare resource data for a Primary Care multi-professional team.Organisational literacy is a cornerstone of integrated care. By reducing the latency between identifying a patient’s need and locating the appropriate resource (e.g., psychology services, pharmaceutical care, or social activities), this tool minimises clinical inertia and enhances the precision of professional recommendations at the point of care.The tool effectively mitigated information compartmentalisation within the unit. It is anticipated that democratising access to this knowledge will allow administrative staff to take a more active role in social and logistical navigation in the future. This task-shifting potential could significantly release clinical time for doctors and nurses, allowing them to focus on diagnostic complexity and direct disease management.The implementation of this AI-driven decision-support interface strengthens the professional-patient relationship by ensuring faster, evidence-based responses. In the long term, the ease of navigating resources translates into a direct benefit for the patient, who receives more efficient access to the health and social support systems available in their community.