From AI Complaints to 67% Deflection: How Innovorder Scaled Support Across 20+ Product Modules with Pluno

How Innovorder scaled from zero to 67% ticket deflection across 20+ product modules with Pluno AI in just six months.

Aurélien Wei

Team Lead Support at Innovorder

Core Challenges

  • Knowledge lived across Notion, Zendesk, Jira, and past tickets. Agents spent significant time just finding answers, often re-diagnosing issues that had already been solved.
  • Every AI tool they tried before Pluno generated customer complaints. Customers could tell they were talking to a bad AI, which damaged trust and created more work for agents cleaning up after it.
  • Response times on chat and WhatsApp ranged from 20 minutes to over an hour. For restaurant operators dealing with live service issues, this was unacceptable.
  • The product’s complexity meant new hires took 6–8 weeks before they could work independently. With 12 agents and constant growth, this training burden compounded.

Solutions

  • Deflection Agent auto-resolves repeat questions on chat and WhatsApp before they reach the queue.
  • AI Copilot helps agents diagnose complex issues and draft accurate responses across 20+ modules.
  • Multi-source knowledge sync pulls from Notion, Jira, past tickets, and documentation. No separate knowledge base needed.
  • One-click ticket closing auto-fills fields, renames tickets, and generates closing emails.
  • Under 1-hour setup: connect Zendesk, add guidelines, and auto-replies start immediately.

Key Results at a Glance

Before

  • Deflection: 0%
  • Chat Response Time: 20 min – 1 hour
  • New Hire Onboarding: 6–8 weeks
  • Customer Complaints About AI: Ongoing Complaints

After

  • Ticket Deflection Rate: 67%
  • Chat Response Time: < 1 min
  • New Hire Onboarding: 1–3 weeks
  • Customer Complaints About AI: Zero

The Challenge

3,000+ Tickets, 20+ Modules, and AI That Made Things Worse

Innovorder’s product spans 20+ modules with thousands of configuration options. Approximately one-third of their 3,000 monthly tickets involve hardware and software bugs across multiple product areas and device brands. The remaining two-thirds are how-to questions and configuration requests, intensified by high restaurant industry staff turnover requiring constant new employee onboarding.

  • Knowledge scattered everywhere: Knowledge lived across Notion, Zendesk, Jira, and past tickets. Agents spent significant time just finding answers, often re-diagnosing issues that had already been solved.
  • Previous AI tools hallucinated: Every AI tool they tried before Pluno generated customer complaints. Customers could tell they were talking to a bad AI, which damaged trust and created more work for agents cleaning up after it.
  • Slow response times on chat: Response times on chat and WhatsApp ranged from 20 minutes to over an hour. For restaurant operators dealing with live service issues, this was unacceptable.
  • 6–8 week onboarding for new agents: The product’s complexity meant new hires took 6–8 weeks before they could work independently. With 12 agents and constant growth, this training burden compounded.

“With every tool we tried before Pluno, customers could tell, and they complained. If we have complaints about the AI, it’s a bad AI.”
— Aurélien Wei, Team Lead Support

The Solution

Zero Complaints, Under One Hour to Set Up

Innovorder needed AI that could handle their product complexity without hallucinating, integrate with their scattered knowledge sources, and deliver results from day one. They implemented Pluno with setup taking under one hour.

“My CEO tested it once, asked one question, and immediately saw that the AI was impressive. That was it.”
— Aurélien Wei

What Pluno delivered

  • Deflection Agent auto-resolves repeat questions on chat and WhatsApp before they reach the queue.
  • Generates zero customer complaints about AI — a first for Innovorder.
  • AI Copilot helps agents diagnose complex issues and draft accurate responses across 20+ modules.
  • Suggests diagnostic paths based on similar past tickets and hands off cleanly. New agents see suggested responses; experienced agents explore troubleshooting paths before escalating.
  • Multi-source knowledge sync pulls from Notion, Jira, past tickets, and documentation. No separate knowledge base needed.
  • Synthesizes answers across sources with links to original material for agent verification.
  • One-click ticket closing auto-fills fields, renames tickets, and generates closing emails.
  • This feature was requested and shipped within one week.
  • Under 1-hour setup: connect Zendesk, add guidelines, and auto-replies start immediately. No lengthy onboarding or custom integration work — Pluno was live and deflecting tickets the same day.

“Setup took under one hour. We connected Zendesk, added guidelines, and auto-replies started immediately.”
— Aurélien Wei

The Results

67% Deflection, Zero AI Complaints, +15 CSAT Points

  • Deflection Rate: 0% → 67%
  • Chat Response Time: 20 min – 1 hour → < 1 min
  • New Hire Onboarding: 6–8 weeks → 1–3 weeks
  • Customer Complaints About AI: Ongoing Complaints → Zero
  • CSAT Improvement: +15 pts
  • Tickets Per Order Ratio: +25% orders, −5% tickets

“Two-thirds of incoming tickets on chat and WhatsApp are resolved by AI without reaching agents. Three recently hired agents are resolving tickets independently within their first few weeks.”
— Aurélien Wei

The Takeaways

Test It. You’ll See Results on Day One.

Skip weeks of configuration, separate knowledge base maintenance, and inconsistent results. Setup takes under one hour. Testing for one day reveals results. For Innovorder’s international expansion including a major cruise ship operator, maintaining high-quality, complaint-free AI experience is essential to scaling without proportional headcount increase.

“My team feels like they could not live without it.”
— Aurélien Wei, Team Lead Support

Stop settling for AI that needs constant babysitting

See how Pluno resolves 70% of tickets, including complex cases, while supercharging agent productivity.