A product description is the foundation of your AI evaluation strategy in Galtea. It defines what your AI system is designed to do, enabling our platform to generate relevant test cases, create meaningful evaluations, and provide insights that matter to your specific use case.

​
What Is a Product Description?

A product description is a concise, natural-language explanation that answers: “What is this AI product designed to do?”

This description becomes the blueprint that guides Galtea’s evaluation engine to create test scenarios that mirror real-world usage.

​
Why Product Descriptions Matter

Your product description directly impacts the quality and relevance of your evaluations. A well-crafted description enables Galtea to:

  • Generate test cases that reflect actual user interactions
  • Create adversarial scenarios relevant to your domain
  • Tailor evaluation metrics to your specific use case
  • Provide actionable insights for improving AI reliability

​
Writing Effective Product Descriptions

​
Be Specific and Purpose-Driven

Focus on three key elements:

  • What the product does
  • Who it serves
  • Which domain or tasks it handles

Good Examples:

  • “A customer support assistant that helps telecom subscribers resolve billing inquiries and plan changes through natural conversation.”
  • “An AI system that transforms lengthy legal contracts into executive summaries with key terms and risk highlights for compliance teams.”

Avoid Generic Descriptions:

  • “A chatbot that answers questions”
  • “An AI assistant for our company”

​
Focus on User Experience, Not Architecture

Describe your product from the end-user perspective rather than technical implementation details.

✅ User-Focused:

“A financial advisor assistant that provides personalized investment recommendations based on user goals and risk tolerance.”

❌ Technical-Focused:

“A RAG pipeline using GPT-4 and vector databases to process financial data through LangChain workflows.”

​
Best Practices

Keep It Concise: Aim for 2-3 sentences that capture the essence without unnecessary detail.

Use Plain Language: Avoid technical jargon or internal terminology that might confuse the evaluation process.

Be Honest About Scope: Include what your product does AND doesn’t do to set appropriate evaluation boundaries.

Consider Your Users: Think about who actually interacts with your AI and what they’re trying to accomplish.

​
Common Pitfalls to Avoid

  • Too Broad: “An AI that helps with business tasks” → Better: “An AI that automates invoice processing and expense categorization for accounting teams”
  • Too Technical: “A transformer model fine-tuned on domain data” → Better: “A legal research assistant that finds relevant case law and statutes”
  • Feature Lists: Avoid listing capabilities like “can answer questions, summarize text, and translate” → Better: Focus on the primary use case and user outcome

​
Enhanced Product Descriptions

For maximum generation effectiveness, especially for security testing, you need to provide these additional details:

​
Capabilities

List what your product is specifically designed to do well. This helps generate targeted quality tests.

Example: “Can answer questions about phone specifications, recommend devices based on user preferences, compare prices across models, and provide information about warranties and accessories.”

​
Inabilities

List technical limitations and scope boundaries. This prevents irrelevant or misleading tests.

Example: “Cannot process purchases, access customer account information, or provide technical support for device repairs.”

​
Security Boundaries

Outline access restrictions and behavioral constraints. This is crucial for effective security testing.

Example: “Must not access customer payment data, personal contact information, or internal inventory systems. Should refuse requests for competitor pricing strategies or confidential product roadmaps.”

​
Complete Example with Optional Fields

Product Description:

“A mobile sales assistant that helps customers find and compare smartphones based on their needs and budget.”

Capabilities:

“Can answer questions about phone specifications, recommend devices based on user preferences, compare prices across models, and provide information about warranties and accessories.”

Inabilities:

“Cannot process purchases, access customer account information, or provide technical support for device repairs.”

Security Boundaries:

“Must not access customer payment data, personal contact information, or internal inventory systems. Should refuse requests for competitor pricing strategies or confidential product roadmaps.”

​
Testing Your Description

A good product description should allow someone unfamiliar with your product to:

  1. Understand what problem it solves
  2. Identify who would use it
  3. Predict what kinds of questions or tasks it should handle well
  4. Recognize what it shouldn’t be expected to do

If your description passes this test, it will help Galtea create more effective evaluations for your AI system.

Next Steps: Once you’ve crafted your product description, you’ll use it when creating a new product in the Galtea platform, where it becomes the foundation for all subsequent evaluation activities.