> For the complete documentation index, see [llms.txt](https://docs.raiaai.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.raiaai.com/use-cases/case-study-ideal.md).

# Case Study: Ideal

**IDEAL automates 24 / 7 Tier-1 support with raia’s AI Agentic Workforce**

***

**Snapshot**

|                      | Before raia               | After raia                                 |
| -------------------- | ------------------------- | ------------------------------------------ |
| 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:

1. **Night-time & weekend queries** that waited hours for a response.
2. **Fragmented knowledge** spread over 10 k support articles plus thousands of historical tickets.
3. 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

| AI Agent                 | Role                                                                                               | Key Integrations                         |
| ------------------------ | -------------------------------------------------------------------------------------------------- | ---------------------------------------- |
| **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**

1. **Week 1-2 – Data prep**: Content engineering team cleaned and bulk-converted articles & tickets to Markdown, then uploaded to Launch Pad .
2. **Week 3 – Pilot in CoPilot**: Support reps used AI-drafted responses inside Zendesk; feedback loop refined prompts & gaps.
3. **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

1. **Start in shadow mode.** CoPilot let IDEAL iterate safely before exposing customers to AI, accelerating trust and quality .
2. **Invest in knowledge hygiene.** Converting legacy PDFs & transcripts to clean Markdown ensured high-precision retrieval .
3. **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.

{% embed url="<https://youtu.be/4oo7259gUbg>" %}


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter, and the optional `goal` query parameter:

```
GET https://docs.raiaai.com/use-cases/case-study-ideal.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.