> For the complete documentation index, see [llms.txt](https://raia2.gitbook.io/raia/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://raia2.gitbook.io/raia/ai-training/partner-training/raia-labs-training/best-practices.md).

# Best Practices

**Agent Naming Conventions in raiaAI Launch Pad**

Proper agent naming is crucial for organization and team collaboration, especially when managing multiple agents for different clients. Follow these naming conventions to ensure clarity and easy identification:

**Function-First Naming:** Always start agent names with their primary function, making it immediately clear what the agent does. This approach scales well as you build multiple agents for the same client.

**Recommended Naming Pattern:** `[Function] Agent - [Client/Department] - [Specific Use Case if needed]`

**Good Examples:**

* "Support Agent - TechCorp"
* "Sales Agent - RetailPlus - Lead Qualification"
* "Analyst Agent - FinanceInc - Report Generation"
* "Support Agent - MedDevice - Technical Troubleshooting"

**Poor Examples to Avoid:**

* "Mary" (no indication of function)
* "TechCorp Bot" (unclear what it does)
* "Agent 1" (not descriptive)
* "Customer Helper" (too vague)

**Benefits of Function-First Naming:**

* Immediate clarity on agent purpose when browsing the Launch Pad
* Easy sorting and organization by function type
* Simplified handoffs between team members
* Clear audit trails and reporting
* Easier troubleshooting and maintenance

**Model Selection Standards**

raiaLabs primarily uses OpenAI's most advanced models to ensure optimal performance and capabilities for client agents:

**Primary Models:**

* **GPT-4o**: The standard model for most agent deployments, offering excellent performance across all agent types
* **GPT-5**: Used for the most demanding applications requiring cutting-edge capabilities

**Model Selection Guidelines:**

* **Support Agents**: GPT-4o provides excellent knowledge retrieval and conversational abilities
* **Sales Agents**: GPT-4o or GPT-5 for sophisticated persuasion and objection handling
* **Analyst Agents**: GPT-4o for most analytical tasks, GPT-5 for complex data analysis requiring advanced reasoning

**Consistency Across Client Deployments:** Using standardized models ensures consistent performance and makes it easier to:

* Predict agent behavior and capabilities
* Troubleshoot issues across different client implementations
* Maintain training materials and best practices
* Scale successful patterns to new clients

This foundational understanding of agent types, naming conventions, and model standards will inform all subsequent training modules, helping you make appropriate decisions about instruction design, knowledge base development, and workflow integration based on the specific agent type you're building.


---

# 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://raia2.gitbook.io/raia/ai-training/partner-training/raia-labs-training/best-practices.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.