Generate and Edit Images with Your AI Agent – Botsify Help Center

The Image Generation feature allows your AI agent to create and edit images based on user prompts. By integrating an image provider, your agent can generate visuals dynamically and even refine them through follow-up instructions.

STEP 01

Go to agentic.botsify.com and create a new agent.

STEP 02

Enter the name of your agent and click on Create Agent.

STEP 03

Add a prompt to define your agent’s behavior (e.g., what you want the agent to do or specialize in).

STEP 04

From the left-side menu, click on Settings.

STEP 05

From the top menu, select Image Providers, then click on + Add Your First Provider.

You will be redirected to the provider setup screen.

5.1 Enter the required details:

Provide a name for your provider (any name of your choice).
Select a provider (e.g., OpenAI).

5.2 To get your API key, visit the provider’s platform.
For OpenAI:
Go to https://platform.openai.com/playground/prompts and log in. After that Click on Create API keys

5.3 Click on Create Secret Key.

5.4 Copy the API key and paste it into Botsify.

STEP 06

Click on Test Connection.

6.1 A test image will be generated, confirming that your integration is working correctly.

STEP 07

Enable the Enable Provider option and click on Save.

STEP 08

Go back to your agent and click on Connect Apps.

8.1 Click on Add App, select Image Providers, and choose the provider you just added.

8.2 Click on Add Server.

8.3 Click on Add.

Your image provider is now successfully connected to your agent.

STEP 9

Click on Test Agent to verify functionality.

Enter a prompt describing the image you want (e.g., “I need some photos of hoodies for my Instagram page”).

9.1 The agent may ask follow-up questions to better understand your requirements before generating images.

STEP 10

To edit generated images, open them in the canvas.

10.1 Click on Edit for the image you want to modify.

10.2 Provide your editing instructions (e.g., “Add a mannequin wearing the hoodie”).
The agent will update the image accordingly.

You can generate multiple images, refine them through prompts, and customize outputs based on your needs. This feature enables your AI agent to assist with creative tasks such as product visuals, social media content, and design concepts.