Skip to main content
Your chatbot description is the foundation for all Botster simulations. It directly impacts persona generation and scenario creation quality, making it one of the most important inputs for accurate testing.

​
What Is a Chatbot Description?

A chatbot description tells Botster what your chatbot is, who it serves, and what it does. This information grounds both persona generation and scenario creation, ensuring simulations reflect realistic user interactions. This is not the place for historical data or conversation examples. Use the historical data upload feature for that. Descriptions should focus on defining purpose and capabilities.

​
What Makes a Good Description?

The best descriptions naturally answer these questions:
  • What does your chatbot do? The core functionality and value it provides
  • Who is it for? The types of people who use it and their typical goals
  • What can users ask? The kinds of questions, problems, or tasks it handles
  • What are its boundaries? What it doesn’t do, when it escalates, or topics it avoids
Write naturally—don’t worry about following a rigid format.

​
Writing Guidelines

  • Start simple — 2-3 sentences covering what your chatbot does, who uses it, and what they ask about
  • Be specific but not exhaustive — “Customer support for billing issues” beats “helps users with stuff”
  • Focus on user value — Describe what users experience, not how the chatbot is built
  • Don’t include examples — Use historical data upload for conversation examples
  • Iterate — Start basic and expand as you learn what works

​
Examples

​
Good Examples

Customer Support Assistant (Basic)
“A support chatbot for an online electronics retailer. Helps customers with order tracking, returns, warranty questions, and shipping estimates. Escalates complex issues to human agents.”
Educational Tutor (More Detail)
“An AI tutor for high school math students. Explains concepts step-by-step, provides practice problems, and offers hints when students are stuck. Covers algebra, geometry, and basic calculus. Encourages students without giving direct answers. For students aged 14-18 who are preparing for exams or need homework help.”
Sales Qualifier (Comprehensive)
“A B2B sales qualification chatbot for a SaaS project management tool. Engages website visitors to understand their team size, current tools, pain points, and budget timeline. Qualifies leads based on fit criteria and schedules demos with sales reps. Target users are team leads and project managers at mid-size companies (50-500 employees). Does not discuss pricing specifics—refers to sales for quotes. Maintains a professional but friendly tone.”

​
Poor Examples

Too Vague
“A chatbot that helps users.”
Why it’s bad: Doesn’t specify what kind of help, who the users are, or what topics are covered. Too Technical
“Uses GPT-4 with RAG pipeline connected to Pinecone vector store. Implements function calling for API integrations. Deployed on AWS Lambda with 512MB memory.”
Why it’s bad: Describes implementation, not user experience or purpose. Includes Irrelevant Information
“Built by our amazing engineering team over 6 months. We’re really proud of it and it won an internal hackathon. It helps with customer support.”
Why it’s bad: Background information doesn’t help simulation quality. Lists Features Instead of Purpose
“Has buttons, can send images, supports markdown, remembers context for 10 turns, integrates with Slack.”
Why it’s bad: Lists capabilities without explaining what users accomplish.

​
Next Steps