Create and Manage Agentspublic

Validated on 15 Aug 2024 • Last edited on 17 Apr 2025

The DigitalOcean GenAI Platform lets you work with popular foundation models and build GPU-powered AI agents with fully-managed deployment, or send direct requests using serverless inference. Create agents that incorporate guardrails, functions, agent routing, and retrieval-augmented generation (RAG) pipelines with knowledge bases.

How to Create Agents

Create an agent with domain-specific knowledge to provide information or take action.

How to Configure Agent Model Settings Using the Model Playground

Evaluate, compare, and configure model settings in Model Playground.

How to Route to Multiple Agents

Integrate multiple generative AI agents.

How to Route Functions in Your Agent

Enable the foundation model in your agent to access the external data sources using functions.

How to Test Agents

The Agent Playground provides an interface where you can test the full agent experience with all the directions and features you’ve configured.

How to Use Agents in Your Applications

Use your agent in an application or through a chat bot interface.

How to View Agent Runtime Logs

View the runtime logs for your agents to troubleshoot issues.

How to View Agent Insights

View the runtime logs for your agents to troubleshoot issues.

How to Destroy Agents Using the Control Panel

Delete agents from your GenAI platform.

How to Add, Edit, or Delete Partner Provider Keys

Add, edit, or delete API keys to use their models with your agents.

How to Rollback to a Previous Version of Agents

Rollback to a previous version of an agent to undo changes made to it.

We can't find any results for your search.

Try using different keywords or simplifying your search terms.