Case Study: Ideal
SOFTWARE
IDEAL automates 24 / 7 Tier-1 support with raia’s AI Agentic Workforce
Snapshot
First-response time
2-4 h during office hours
<60 s, 24 / 7 live-chat
Ticket resolution
0 % automated
50 % solved end-to-end by AI
Agent triage quality
Manual note-taking
AI pre-diagnoses remaining 50 % for humans
Staffing demand
Team capped at 10 reps
AI output ≈ 5 FTEs worth of capacity
1 | Company & Challenge
IDEAL, a Constellation Software business unit, provides vertical ERP and point-of-sale software to hundreds of equipment dealers across North America. A growing catalogue of products and always-on dealerships drove three pain points:
Night-time & weekend queries that waited hours for a response.
Fragmented knowledge spread over 10 k support articles plus thousands of historical tickets.
Rising ticket volume outpaced the Tier-1 team’s headcount budget.
IDEAL needed an always-available support channel that could surface precise answers from deep product documentation and integrate with its existing ticketing stack.
2 | Why IDEAL chose raia
Launch Pad & Vector Store ingest large knowledge bases in minutes and index them for semantic search, turning 10 k Markdown articles and legacy transcripts into AI-ready context .
CoPilot human-feedback loop lets support reps rate and correct answers during pilot mode, rapidly improving accuracy .
Live-chat skill out-of-the-box meant zero custom code to embed chat on IDEAL’s customer portal .
3 | Solution Design
Tier-1 Support Agent
Resolve common “how-to”, licensing and configuration questions via live-chat; escalate edge-cases.
Knowledge Base Vector Store, Zendesk API
Copilot Shadow Mode
Used internally for 90 days to draft answers and collect thumbs-up / corrections.
CoPilot feedback UI
Deployment timeline
Week 1-2 – Data prep: Content engineering team cleaned and bulk-converted articles & tickets to Markdown, then uploaded to Launch Pad .
Week 3 – Pilot in CoPilot: Support reps used AI-drafted responses inside Zendesk; feedback loop refined prompts & gaps.
Week 12 – Public go-live: Chat widget released to all customers.
4 | Measurable Impact (90 days post-launch)
50 % of inbound tickets fully resolved by AI—equal to five full-time agents.
100 % of remaining tickets pre-diagnosed, with reproduction steps and knowledge-article links attached, cutting triage time by 40 %.
Customer CSAT +12 points (4.1 → 4.6) driven by instant answers after hours.
Ops saving: ~$350 k annualised labour and overtime costs.
5 | Lessons for Prospective Clients
Start in shadow mode. CoPilot let IDEAL iterate safely before exposing customers to AI, accelerating trust and quality .
Invest in knowledge hygiene. Converting legacy PDFs & transcripts to clean Markdown ensured high-precision retrieval .
Let AI triage, not just solve. Even unsolved tickets reached human reps with contextual breadcrumbs, boosting Tier-2 productivity.
6 | What’s Next
Expand the Agent to proactive in-app guidance (surfacing tips based on user behaviour).
Add a billing & licensing Pack so AI can execute licence upgrades without human touch.
Integrate sentiment analytics to flag at-risk accounts for success managers.
7 | Key Takeaway
IDEAL’s experience shows that raia turns sprawling support knowledge into a self-service frontline, delivering round-the-clock answers, happier customers and a 50 % reduction in human ticket load—all within a single quarter.
Last updated