# Case Study: Flui Technologies (CSI)

Flui Technologies is a Constellation Software Inc. (CSI) portfolio company — Operating Group: Jonas (Vesta).

**Flui partners with raia to design and deploy a next-generation AI Support Agent, powered by a unified Core Knowledge Model and integrated with ServiceNow, to scale support for its utility-sector software infrastructure and services.** ### Snapshot (planned targets) | Metric | Before raia | After raia (target) | | --------------------------- | ----------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | | First-response time | Baseline to be validated during discovery/pilot | Near-instant responses for common Tier-0 queries, 24/7 (target set after baseline review) | | Case resolution | Baseline to be validated during discovery/pilot | Tier-0/1 deflection + faster Tier-2 resolution via better triage (targets set after baseline review) | | Manual case-handling effort | High manual intake/triage/routing | Reduced manual effort through AI-led intake, pre-diagnosis, and guided resolution (target set after baseline review) | | Support team focus | Repetitive Tier 0–2 tasks consume expert time | Humans focus on complex escalations and exception handling | | Workflow consistency | Varies by agent/tier | Standardized workflows across technical, functional, and operational tiers | **Engagement summary:** raia is partnering with Flui to deploy a Tier 0–2 AI Support Agent inside ServiceNow, grounded in a unified Core Knowledge Model built from Flui’s documentation, workflows, and historical tickets. ### 1. Company & Challenge Flui Technologies is a leading solution provider to the **utility sector** since 1990. They specialise in delivering innovative and scalable software infrastructure and services that facilitate **market competition** and **smart metering**—critical capabilities for the transition toward a **net-zero future**. Supporting utility-sector customers and smart-metering workflows requires fast, consistent responses across technical and operational scenarios. As support demand grows, Flui faced three compounding challenges: 1. **Manual case-handling at scale** — agents spend significant time on intake, triage, routing, and repeated “how-to” questions. 2. **Slower resolutions** — agents often need to search across documentation, workflows, and historical ticket context to reach an answer. 3. **Inconsistent workflows** — support quality and process can vary across tiers, creating operational overhead and uneven customer experience. With complex deployments and high-stakes operational environments, Flui needed a support experience that is **fast, consistent, and knowledge-grounded**—without increasing headcount. Flui needed an always-available system that could **understand Flui’s product ecosystem, documentation, workflows, and historical ServiceNow tickets**—providing Tier 0–2 assistance while cleanly escalating edge cases to humans. ### 2. Why Flui chose raia Flui selected raia to move beyond basic automation and build a scalable support foundation: * **Unified Core Knowledge Model** that consolidates knowledge from documentation, workflows, and historical ServiceNow tickets into a reusable architecture. * **Deep ServiceNow integration** so support teams can operate within their existing system of record instead of managing parallel tooling. * **Tier 0–2 design** that automates the repeatable majority while enabling high-quality handoffs to human experts for complex escalations. * **Long-term AI foundation** designed to support broader AI adoption across departments over time. ### 3. Solution Design The solution centers on an AI Support Agent built on a unified Core Knowledge Model and integrated directly into ServiceNow. | Component | Role | Key Integrations | | ------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------ | --------------------------------------------------------------------------------- | | **AI Support Agent** | Handles Tier 0–2 assistance: answers common questions, guides troubleshooting, captures structured context, and proposes next steps. | ServiceNow (cases/workflows), Core Knowledge Model | | **Core Knowledge Model** | Ingests and structures Flui’s support knowledge so the agent can retrieve accurate, policy-aligned answers and apply consistent workflows. | Product documentation, internal workflows/runbooks, historical ServiceNow tickets | | **Agent handoff & escalation** | Escalates complex cases with full conversation history, captured context, and an AI-generated summary so humans can resolve faster. | ServiceNow Agent Workspace / routing rules | #### Example support flows (illustrative) * **Smart metering configuration guidance:** answer common setup questions, provide step-by-step guidance, and link to the correct internal documentation. * **Market competition / integration troubleshooting:** guide diagnosis using known workflows and past resolution patterns from historical tickets. * **Known issue lookup:** identify likely causes and recommended fixes based on similar ServiceNow cases. * **Escalation with full context:** hand off complex or low-confidence cases with a structured summary, extracted signals, and recommended next steps for the support agent. #### Deployment timeline (illustrative) > Final phases and timing will be defined in the SOW and rollout plan. 1. **Phase 1 — Knowledge ingestion & normalization**\ Aggregate docs/workflows + historical tickets; normalize content for high-precision retrieval. 2. **Phase 2 — Pilot / shadow mode**\ AI drafts responses and triage recommendations; humans approve and provide feedback to reduce failure modes. 3. **Phase 3 — Controlled rollout**\ Expand coverage by category with monitoring, escalation policies, and continuous improvement loops. 4. **Phase 4 — Scale & standardize**\ Broaden Tier-2 assist coverage and operationalize reporting for measured outcomes. ### 4. Expected Impact (targets; measured results to follow) Flui’s target outcomes for the engagement include: * **Reduced manual case-handling effort** through automated intake, triage, and guided resolution (targets set after baseline review). * **Faster time-to-resolution** by grounding responses in Flui-specific knowledge and standardized workflows (targets set after baseline review). * **Higher consistency across tiers** via shared playbooks embedded into ServiceNow workflows (targets set after baseline review). * **Improved team leverage** by shifting human effort toward complex escalations and exceptions. ### 5. Lessons for Prospective Clients 1. **Start with knowledge architecture, not just a chatbot.** A unified model prevents “AI sprawl” and makes improvements reusable. 2. **Meet teams where they work.** ServiceNow-native workflows drive adoption and reduce operational friction. 3. **Design for escalation, not perfection.** The highest ROI comes from handling the repeatable majority while enabling great human handoffs. ### 6. What’s Next Flui and raia plan to expand beyond reactive support into: * **Proactive support** (surfacing best practices, predicting issues, and reducing avoidable tickets). * **Workflow expansion** across additional support categories and internal teams. * **Broader AI adoption** using the same Core Knowledge Model foundation across departments. ### 7. Key Takeaway Flui is building a **ServiceNow-integrated AI Support Agent** powered by a **unified Core Knowledge Model**—designed to deliver Tier 0–2 assistance, reduce manual case-handling, accelerate resolution time, and standardize workflows across support tiers, while creating a reusable foundation for long-term AI adoption.