24/7 self-service for residents. Less burden for staff.

GXA is Granicus’ governed, multichannel AI conversational and agentic layer, executing through GXC and other third-party systems of record, that helps agencies modernize service delivery and operations safely and efficiently. GXA connects staff and resident interactions to how work gets done, with accountability, auditability, and trust enforced through governed intake, policy-aligned decision paths, traceable handoffs, and human approval at defined points.

Granicus’ unique combination of governed, multichannel AI and built-in government experience services ensures agencies resolve policy ambiguity, prepare content, and design real-world workflows before automation is applied.

GXA draws only from trusted, agency-approved sources (not general web content), understands resident intent (including conversations in non-English), and responds in clear, human-like language with guidance specifically tuned for resident-to-government queries. Unlike commercial LLMs and legacy chatbots, GXA delivers exceptionally accurate, relevant responses by mining the deepest connectivity to your primary citizen services applications. Granicus government experience experts have optimized this strategy with learnings from more than 8 billion interactions and 7,000 government customers supported.

GXA reduces the operational burden of high-volume, informational interactions by handling routine self-service questions residents should be able to resolve independently. This allows staff to focus their time on core responsibilities and higher-value work.

GXA also serves as a trusted knowledge resource for newer staff, accelerating onboarding, reducing reliance on institutional memory, and lowering training costs.

As GXA continues to evolve, agentic AI capabilities will further automate workflows and simplify manual processes—shifting staff time away from busy work and toward improving service quality and community outcomes.

Our GXA onboarding offering includes:

• Activation and training. Our teams offer an efficient, guided process to implement GXA in alignment with your key desired outcomes. These activities include activation input, a readiness assessment, agent configuration, initial outputs review and approval, plus admin console training. We’ll also train your teams on how to create and surface the best content possible to use as source material.

Our GXA optimization offering includes:

• Discovery workshops. Our experts facilitate collaborative workshops with your key stakeholders to understand your business goals and success metrics, identify critical user pain points and expectations, align on scope and timelines, and optimize your data and sources to ensure the best responses.
• Source-of-truth content. We’ll analyze usage data, web traffic, and user interactions to understand top user tasks and needs to build a custom Predefined Response Questions document on which to train GXA with accurate, relevant, in-demand answers for priority questions.
• Key findings and recommendations. After initial onboarding and optimization, our teams will review what your users are asking, whether the agent is meeting their needs, and where drop-offs or dissatisfaction occur. Recommendations for enhancements could include adding or refining pre-written questions, updating website content, or integrating third-party tools or data sources to enhance responses.

Yes. GXA is compatible with all CMS platforms and integrates across Granicus solutions and other third‑party systems of record to connect resident interactions directly to real government work.

Integrations include:

• Service request management, allowing residents to initiate and track service requests through conversational experiences while staffing systems receive structured, actionable submissions.
• Meetings, agendas, and minutes, enabling residents to ask natural questions and receive clear, plain‑language answers grounded in official public records and meeting outcomes.

Because GXA operates inside Government Experience Cloud, these integrations follow a consistent, governed experience — rather than point‑to‑point automation.

Granicus and GXA protect government data and citizen privacy through:

• Data ownership: Agencies retain full control of their data. Customer data is never used to train AI models.
• Data isolation: Secure, private cloud infrastructure and domain validation prevent cross-customer access and unauthorized interaction.
• Encryption & access: End-to-end encryption (HTTPS/TLS), token-based authentication, and secure secrets management with vault tools protect data in transit and at rest.
• Auditability & monitoring: Continuous monitoring and alerting support oversight and accountability.
• Threat protection: Always-on defenses (powered by Akamai) neutralize and block malicious bots and DDoS attacks before they disrupt services.

The foundation of GXA is built on AWS infrastructure designed specifically for statutory environments where traceability, explainability, data ownership, and audit readiness are non‑negotiable operational requirements. GXA leverages Amazon Bedrock to securely access and orchestrate foundation models while ensuring agency data remains isolated, encrypted, and always owned by the customer. Learn more about Granicus’ partnership with AWS here.

We do not collect or share PII. GXA never collects personal information from residents. It does not store names, emails, or anything that could identify someone. All data is encrypted, and every agency’s information is kept completely separate and secure.

Deployment time depends on your agency’s goals and the availability of key staff. Granicus’ Experience Services experts will collaborate closely with your agency to design a customized onboarding and optimization plan. This ensures the right stakeholders are involved in configuration, testing, and validation.

Before launch, we work with you to rigorously test and fine-tune GXA to meet your performance expectations — so you can move forward with confidence in its reliability and impact.

GXA leverages a large language model (LLM) that is already trained to facilitate friendly, professional, safe conversations. GXA adds other technology components to tune the agent’s capabilities to effectively understand resident interactions and generate clear, accurate, and relevant responses, including a custom source library tailored to each agency so that GXA only references official, validated content.

GXA summarizes only the public information an agency explicitly provides in the agent’s source library. GXA is not designed to take, reference, or generate private information. Guardrails are in place to warn residents from submitting private data or other PII.

No customer data is used to train GXA’s model.

The content and data that your agency provides GXA to reference, as well as the data GXA creates to record interaction metadata and conversation is owned by your agency — always. Your agency’s data is contained within your own instance of GXA (not intermixed with data and content from others). Your data is not used to train any models leveraged by Granicus (or anyone else). Your data is not shared with any third parties or sold.

When your contract term is over, you can obtain all of your data for your own use outside of the GXA solution. Granicus would then permanently delete your data.

GXA leverages industry‑leading, proven frontier models that are rigorously evaluated by Granicus, and its flexible architecture allows new models to be incorporated seamlessly as they emerge. This ensures agencies continuously benefit from the latest advancements without needing to replatform or make disruptive changes.

GXA includes multiple layers of safety checks — called guardrails — to ensure responses are accurate, secure, and aligned with public service standards. These guardrails are designed to prevent hallucinations and misinformation by grounding every response in trusted, agency-approved content and keeping humans in the loop.

These guardrails include:

• Approved content: Responses use RAG to pull only from agency-approved sources.
• Source transparency: Answers can be traced back to their cited sources.
• Safe fallback behavior: When confidence is low, GXA avoids guessing and provides alternatives.
• Human review: Agency staff test and validate responses before launch to ensure accuracy and continuously refine.

When triggered, GXA responds with:
“That topic is outside the scope of what I can assist with due to our content guidelines. However, I’m here to help with any other questions you may have.”

These protections are continuously updated to adapt to new risks and help maintain public trust.