"Gloucester County set out to give Virginia residents and building professionals a single, reliable way to access planning, zoning, and parcel information, without navigating multiple disconnected county systems. Tech 42 partnered with the county to design and build an agentic AI solution on AWS, purpose-built for this challenge.
The solution uses an AgentCore-based agent backed by a Bedrock Knowledge Base and a natural-language-to-SQL tool, deployed on a scalable, serverless AWS architecture with built-in guardrails, memory and observability. Together, these let residents and staff ask plain-language questions, such as what permits are required for a project at a given address, and receive precise, sourced answers pulled directly from county ordinances, code values, and parcel records, rather than relying on generic AI knowledge.
Since rolling the solution out to internal subject matter experts, Gloucester County has seen it become a genuine time saver and efficiency gain for staff who previously had to manually search through the same materials to answer resident questions. It's also helped ease reliance on a small number of long-tenured staff who hold critical institutional knowledge, making that expertise more accessible across the team, while surfacing new opportunities to close integration gaps between departments.
Working with Tech 42 has felt less like managing a vendor and more like having a true technology partner — one that delivered exactly to scope, communicated clearly and promptly throughout, and brought genuine expertise to every part of the engagement. That experience has already led Gloucester County to recommend Tech 42 internally for other initiatives, and both teams continue to explore how the solution can expand to support additional use cases and, over time, broader public-facing access."

Britton Hogge
Senior Software Analyst
Gloucester County needed a single, reliable way for residents and staff to access planning, zoning, and parcel information without navigating disconnected county systems. Tech 42 built an AgentCore-based AI agent on AWS with a Bedrock Knowledge Base and a natural-language-to-SQL tool. Staff now get instant answers sourced directly from county ordinances and parcel records, reducing manual lookup time and making institutional knowledge accessible across the team.