# Using Agents

Discover and deploy powerful automation agents created by the K3 Labs community. This guide shows you how to find, configure, and manage agents for your automation needs.

### Finding Agents

#### Browse the Agent Gallery

The Discover page is your gateway to all available agents:

* All Agents: Browse the complete collection of public agents
* My Agents: View agents you've created or deployed
* Favorite Agents: Quick access to agents you've saved
* Search: Find specific agents by name or function
* Categories: Filter agents by use case (Finance, Operations, AI Agents, etc.)

<figure><img src="/files/zOTvuW77b0jsyMQlvOyn" alt=""><figcaption></figcaption></figure>

#### Agent Cards Display

Each agent card shows:

* Agent name and type (Official/Community)
* Brief description
* Update timestamp
* Action count (number of steps)
* Creator badge (for official agents)

#### Direct Links

Agents can also be shared directly via links. Click any shared agent link to view and deploy it instantly.

### Understanding Agent Details

When you click on an agent, you'll see a comprehensive preview:

<figure><img src="/files/M24FbmV5L4IExNQ1cqte" alt=""><figcaption></figcaption></figure>

#### Overview Section

* Description: Detailed explanation of what the agent does
* Use Cases: Who should use this agent and why
* Requirements: Any prerequisites or necessary accounts

#### Categories

Tags that help you understand the agent's primary functions (e.g., Finance, Operations, AI Agents)

#### Statistics

* Actions: Number of workflow steps in the agent
* Last Updated: When the agent was last modified
* Usage Count: How many times it's been deployed (when available)

#### Agent Steps Overview

A high-level view of what the agent does:

1. Each step is numbered and shows its function type
2. Descriptions explain what happens at each stage
3. Only visible steps are shown (hidden logic remains private)

### Deploying an Agent

#### Step 1: Click "Use Agent"

When ready to deploy, click the blue "Use agent" button. This opens the configuration interface.

<figure><img src="/files/d4VFOZ1ut8dc9puxxWbf" alt=""><figcaption></figcaption></figure>

#### Step 2: Configure Required Inputs

You'll only see fields that need your input:

Common Input Types:

* Schedule Settings: Choose frequency (hourly, daily, weekly, etc.)
* Contact Information: Email addresses or Telegram handles for alerts
* Wallet Addresses: Addresses to monitor or interact with
* Thresholds: Price limits, percentages, or other numeric values
* Token Selection: Choose from pre-configured options

Example Configuration:

Scheduled: Every 24 Hours

Email: <your-email@example.com>

#### Step 3: Preview the Workflow (Optional)

Toggle to Workflow View to see the complete automation logic:

* Understand the full process flow
* Verify the steps match your expectations
* Note: This view is read-only

#### Step 4: Deploy

1. Click the "Deploy" button
2. Give your agent instance a memorable name
3. Confirm deployment

Your agent is now active and will run according to your configuration!

### Managing Deployed Agents

#### Access Your Agents

Find all your deployed agents in the Dashboard:

* View running status
* Monitor execution history
* Check for any errors

#### Edit Configuration

Need to change settings? You can update your deployed agents:

1. Navigate to your agent in the Dashboard
2. Click to open the agent
3. Modify any configurable fields
4. Save changes

Changes take effect immediately for future executions.

#### Pause or Stop Agents

Control your agents directly from the Dashboard:

* Pause: Temporarily stop execution while keeping configuration
* Delete: Permanently remove the agent instance

### Tips for Success

#### Before Deploying

* Read the full description to understand the agent's purpose
* Check the steps overview to verify it matches your needs
* Ensure you have necessary accounts (wallets, APIs, etc.)
* Start with conservative settings (lower frequencies, higher thresholds)

#### Common Configurations

Monitoring Agents

* Set reasonable check intervals to balance timeliness and action usage
* Use specific wallet addresses rather than monitoring everything
* Configure alert thresholds to avoid notification overload

Trading Agents

* Start with small amounts to test behavior
* Set appropriate price limits and slippage tolerance
* Ensure your wallet has sufficient funds for gas

Analytics Agents

* Choose report frequencies that match your decision-making cadence
* Select relevant data sources and metrics
* Configure delivery to your preferred communication channel

#### Troubleshooting

Agent Not Running?

* Check if you've completed all required fields
* Verify your wallet has funds for gas (if applicable)
* Ensure external services (email, Telegram) are properly connected

Not Receiving Alerts?

* Confirm email address is correct
* Check spam folders
* Verify Telegram bot connection

Unexpected Behavior?

* Review the workflow view to understand logic
* Check if thresholds or conditions are too restrictive
* Contact the agent creator for complex issues

### Best Practices

#### Start Simple

* Deploy one agent at a time
* Use default settings initially
* Gradually adjust based on results

#### Monitor Performance

* Check execution logs regularly
* Track action usage
* Optimize schedules based on actual needs

#### Security Considerations

* Only enter information you're comfortable sharing
* Verify official agents have the official badge
* Review agent logic before entering sensitive data
* Remember that wallet connections are always secure and isolated

### Next Steps: Learn how to build your own agents

{% content-ref url="/pages/JNbze6Lbbb626oQDWeGj" %}
[Creating Agents](/introduction/k3-agents/creating-agents.md)
{% endcontent-ref %}


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.k3-labs.com/introduction/k3-agents/using-agents.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
