This article provides a comprehensive guide on building and using agents within the Vurvey platform, with options for both DIY creation and Vurvey-built solutions.
What is an Agent?
Think of an agent as a smart intern within Vurvey. These AI-powered assistants can take on different roles, depending on your needs:
Assistant Agents can handle specific tasks based on your instructions and provided data
Persona Agents can take on the personality of a specific customer segment, allowing you to chat with them and innovate together
Product Agents can take on the attributes, descriptions, makeup, etc. of a specific SKU or product, allowing you and or your customers to chat with it and innovate together, provide feedback to it, learn what it is good at and how it applies to certain situations, etc.
Image Generation Agents can be trained on your brand, your aesthetic, and your design standards and powered by Stable Diffusion, IMAGEN, or DALL-E to generate stunning visuals inside of Vurvey.
Unlike generic AI, Vurvey agents are context-aware, understand your workspace and objectives, and are capable of being grounded in your proprietary consumer responses from campaigns.
Key Features:
Contextual Understanding: Agents are trained to comprehend and work within your specific Vurvey workspace
Task-Oriented: Designate specific tasks for your agents, such as summarizing information, writing content, or generating ideas
Data-Driven: Provide agents with relevant data, such as market research or product specifications, to ensure tailored outputs
Personalized Personas: Craft unique personas by defining an agent's personality, tone, and output structure
Understanding Agent Creation Options
DIY Agent Creation
What it means: You can create customized AI agents within the Vurvey platform that serve specific research or business needs (like a "Consumer of the Future" agent) using your own data and specifications.
What you need:
Access to a Vurvey workspace
Relevant datasets uploaded to your workspace and/or consumer insight survey campaigns in the workspace
Clear understanding of agent purpose and expected outputs
The DIY process:
Navigate to your desired workspace
Select "Create New Agent" from the dashboard
Define agent:
Name
Description (typically about 15-20 words that explain to users who the agent is and how they can help)
Background: Think of this as the history and life experience that made the agent who they are and helps them make decisions. You can be as detailed as you like here to increase effectiveness of the agent and is very much an iterative process.
Behaviors: This is where you define personality, output style, things like how often they use bullet points or what types of methodologies they prefer when analyzing something, etc. Similar to background, this is an iterative and incremental thing that can grow and expand over time.
Use relevant datasets/campaigns in Vurvey to pull out insights or things you want the agent to know/use in their background and behaviors and write them into those sections
Test your agent with sample queries (be sure to attach the training datasets/campaigns to the conversation as this will give them access to all of that data in a similar way to how our brains operate with long-term memory)
Refine agent settings based on output quality
TIP: Use your AI Conversations feature in Vurvey to help you create your agent's background and instruction set. You can ask the AI to help you. Here is a sample prompt: "Train yourself as an expert at training and creating AI agent personas. Now create an agent background for Tommy, the master of Margaritaville who knows everything about mixed drinks and can help anyone make better margs."
Benefits: Immediate creation, no additional costs, full control over the agent's capabilities and knowledge base.
Vurvey-Built Agent Creation
What it means: Our expert team creates a highly customized agent based on your specific requirements, handling all technical aspects and optimization.
What you need to provide:
Completed Agent Requirements Questionnaire
Relevant data/documents to inform the agent (PDFs, research, etc.)
Sample outputs you deem as acceptable quality outputs for testing against
Feedback during testing phase
The Vurvey-built process:
Requirements collection meeting
Data/research collection and cleaning
Agent construction by Vurvey team
Testing and validation against benchmarks
Delivery with summary report and usage guidelines
Pricing:
Fixed credit allocation/cost based on agent complexity (usually ranges from $5,000-$25,000 USD but most are at the $5,000 level)
Typically ranges from 25-100 credits
Custom pricing available for specialized requirements and custom model builds to power agents with quantitative data
Working with Datasets
Datasets provide the foundational knowledge for your agents.
Creating Datasets:
Upload files in various formats (video, document, text, spreadsheet) directly to your workspace
Provide a clear and descriptive name for each dataset
Using Datasets:
When initiating a chat with an agent, specify the relevant dataset for it to reference
Agents can analyze and extract insights from the provided datasets
Tips for Success:
Start with a Clear Objective: Clearly define the agent's purpose and intended tasks
Experiment with Creativity Levels: Adjust the creativity settings to control the diversity and imagination of the agent's responses
Iterate and Refine: Continuously test, provide feedback, and adjust your agent's instructions to improve its performance
Leverage the Power of AI: Don't hesitate to use the AI system to assist in generating agent backgrounds, instructions, and even image prompts
Common Questions
Q: How do I know which option is right for me?
A: DIY is best for straightforward agents using existing data. Choose Vurvey-built for complex agents that require advanced data analysis or specialized capabilities.
Q: Can I modify an agent after creation?
A: Yes, both DIY and Vurvey-built agents can be refined over time. DIY agents can be updated directly, while Vurvey-built agents may require support for complex changes.
Q: How do I manage workspace access for agent creation?
A: Workspace administrators can control access permissions, unhide workspaces, and rename them as needed through the workspace settings menu.
Q: Is training available for DIY agent creation?
A: Yes, Vurvey offers guided training sessions for power users. Contact your account manager to schedule a recorded training session for your team.
Q: Are agents and datasets workspace-specific?
A: Yes, any agent or dataset created within a workspace is only accessible to users with access to that workspace.
Q: How do I generate images within an agent chat?
A: Use the command "/image" before your prompt to trigger image generation. For dedicated image generator agents, this command might not be necessary.
Getting Started
To begin creating your own agent or to request Vurvey to build one for you, contact your Vurvey account manager or email [email protected] with "Agent Creation Request" in the subject line.