Skip to main content

Understanding AI Agents

AI Agents are customizable, sharable agents that can be invoked on selected code or entire files in your IDE. Use prebuilt agents or create your own with specific instructions, tools, and commands. At the top of the AI Agents screen, you’ll find tabs that help you filter and navigate between different types of agents:

All

Shows all available agents

Zencoder

Displays prebuilt agents created by Zencoder (with the number indicating how many are available)

Custom

Shows your custom agents (with the number indicating how many you’ve created)
AI Agents Selection This categorization makes it easy to distinguish between default agents and your own custom creations.

Creating an Agent

1

Adding a New Agent

  1. Click the three dots menu (⋮) at the top right corner.
  2. Select Agents
  3. Click the Add custom agent button in the top right Create a Custom Agent
2

Configuring an Agent

When adding or editing an agent, you’ll need to set these properties:Basic Settings:
  • Name: A descriptive name for your agent (required)
  • Share: Control who can see and use this agent
    • Personal: Visible only to you
    • Shared: Visible to your entire organization (all users within your organization can share agents with others)
Configuration:
  • Command/Alias: The chat command to invoke your agent (required)
  • Instructions: Detailed prompt instructions that define your agent’s behavior (required)
  • Tools: Enable specific tools your agent can access Configuring an Agent
3

Instructions Format

Define clear instructions for your agent that explain its purpose and how it should operate. Here’s an example of instructions for a Repository Analyzer agent:
Consider the currently open project and repository. 
Understand its structure, mutual relations between files, folders, dependencies, and more. 
Please provide me with an in-depth structured understanding of this repo
Your instructions should be specific enough to guide the agent’s behavior, but also flexible enough to work across different contexts.
4

Tool Selection

Agents can access various tools to enhance their capabilities:
  • git
  • File Search
  • Full Text Search
  • Web Search
  • Fetch Webpage Content
  • Semantic Code Search
  • File Editor
  • Execute Shell Command
  • Gather Requirements
Simply click on the tools your agent should have access to in the Tools section.Configuring Agent tools
5

Sharing Agents

If you’re an admin, you can share agents with your organization:
  1. When editing an agent, find the Share dropdown
  2. Choose between:
    • Personal: Visible only to you
    • Shared: Visible to the whole organization Sharing Agent

Contributing Your Own Agents

You can submit custom agents to the marketplace via the zenagents-library GitHub repo.

Using Agents in Your Workflow

Once configured, you can use agents by:
  1. Selecting code in your editor or focusing on an entire file
  2. Invoking the agent using its command (e.g., /unittests, /review)
  3. The agent will perform its specialized task on the selected code
Core agents and features that work alongside your custom AI agents:

Coding Agent

The primary development agent that your custom agents can complement

Web Dev Agent

Build web UIs and extend web development workflows with specialized web dev agent

Unit Testing Agent

Generate tests for code created by your custom agents

E2E Testing Agent

Create comprehensive test scenarios for applications built with custom agents

Ask Agent

Quick questions and explanations for your custom agent development

Repo Info Agent

Provides project context that enhances all custom agents