Skip to main content

​
How agent creation works

When you describe the assistant you want, Gainable’s Agent Planner analyzes your request and the Agent Builder creates the agent. The agent stays synced with your app. As you add data models or features, the agent can be updated to work with them.
1

Describe your agent

Tell Gainable what kind of assistant you want, what it should know, and how it should behave.
2

Agent Planner analyzes

The Agent Planner determines the agent’s name, instructions, functions, and configuration.
3

Agent Builder creates

The Agent Builder sets up the agent with all its properties and connects it to your app.
4

Agent stays synced

As your app changes, you can update the agent through follow-up prompts.

​
Agent properties

PropertyDescription
NameDisplay name shown in the copilot header (e.g., “Sales Coach”)
DescriptionShort summary of what the agent does, shown to users
InstructionsSystem prompt that defines the agent’s behavior, tone, and rules
Conversation startersPre-defined prompts displayed as buttons to help users begin
Web searchWhether the agent can search the web for additional information
FunctionsConnections to your app’s API endpoints for reading and writing data
KnowledgeUploaded documents the agent can reference when answering

​
Writing good prompts for agent creation

Be specific about what the agent should do, who it helps, and what data it needs access to. 
Create an AI agent called "Sales Coach" for our sales team.
It should:
- Help reps find deals by status, company, or amount
- Answer questions about our sales process
- Use a friendly, encouraging tone
- Start conversations with: "Show my open deals",
  "What deals are closing this month?",
  "Find deals over $10k"
- Have access to deals and contacts data
- Be able to search the web for company information

​
Writing effective instructions

The agent’s instructions act as its system prompt. They define how the agent behaves in every conversation. Good instructions include:
  • Role definition: Who the agent is and what it specializes in
  • Tone and personality: How it should communicate
  • Rules and boundaries: What it should and shouldn’t do
  • Data awareness: What data it has access to

​
Example instructions

You are Sales Coach, a helpful AI assistant for the sales team.

Your role:
- Help reps find and analyze their deals
- Provide pipeline insights and status updates
- Suggest next steps based on deal stage

Tone:
- Friendly and encouraging
- Concise, prefer bullet points over long paragraphs
- Use data to back up suggestions

Rules:
- Always confirm before making changes to deals
- If you don't know something, say so
- Focus on deals and sales, redirect other questions

​
Conversation starters

Conversation starters are pre-defined prompts displayed as clickable buttons when the copilot opens. They help users discover what the agent can do.

​
Best practices

  • Keep them short: 3-8 words per starter
  • Make them varied: Cover different capabilities
  • Be domain-specific: Match your agent’s purpose
  • Use action language: Start with verbs
"Show my open deals"
"Deals closing this month"
"Find deals over $10k"
"Pipeline summary"
Enabling web search lets the agent look up external information during conversations. When to enable:
  • The agent needs current information (news, market data, company details)
  • Users might ask questions beyond your app data and documents
When to skip:
  • The agent only works with internal data
  • You want to keep responses focused on your content
  • Sensitive contexts where external information could be misleading

​
Managing and updating agents

You can update agents through follow-up prompts at any time: 
Update the Sales Coach agent to also greet users by name
and add a conversation starter for "Top deals this week"

Change the support agent's tone to be more formal
and remove the web search capability

Add a new conversation starter: "Check order status"

​
Tips

An agent that “helps with everything” is less useful than one focused on a specific area like sales, support, or HR.
Agents feel more natural when they have a consistent personality. Specify whether it should be formal, casual, encouraging, or direct.
Tell the agent what data models it should use: “Give it access to deals and contacts” is much clearer than “let it see the data.”
After creating an agent, try asking it the kinds of questions your users would ask. Refine instructions based on the results.

​
Learn more

Agent functions

Connect your agent to app data

Knowledge bases

Upload documents for your agent

Copilot

Embed the agent in your app

Overview

Back to AI Agents & Copilot overview