DigitalOcean Gradient™ AI Platform Release Notes

August 2025

18 August

• The OpenAI gpt-oss-120b and gpt-oss-20b models are available on DigitalOcean Gradient™ AI Platform. See all available models.

12 August

• The OpenAI o1 model is now available on DigitalOcean Gradient™ AI Platform. See all available models.

11 August

• The OpenAI GPT-5 model is now available on DigitalOcean Gradient™ AI Platform. See all available models.

July 2025

25 July

• You can now add a Dropbox folder as a data source to your knowledge bases. This allows you to index and use files stored in your Dropbox account within your knowledge base.

22 July

• DigitalOcean Gradient™ AI Platform now offers log stream insights, which provide data-driven recommendations to help improve agent efficiency and accuracy by analyzing your agent’s historical trace data. For details, see View Traces, Conversation Logs, and Insights.

• The official DigitalOcean Gradient™ AI Platform SDK is now in public preview. You can use the SDK to manage Gradient AI Platform resources, including knowledge bases and generative AI agents, from Python applications.

11 July

• The Alibaba Qwen3-32B model is now available for serverless inference on DigitalOcean Gradient™ AI Platform. See all available models.

9 July

• As part of the DigitalOcean Gradient™ AI Agentic Cloud, GenAI Platform is now DigitalOcean Gradient™ AI Platform.

• Support for Amazon S3 buckets as data sources for DigitalOcean Gradient™ AI Platform knowledge bases is now in public preview.

• DigitalOcean Gradient™ AI Platform is now in general availability.

2 July

• Agent tracing and conversation logs are now in public preview for DigitalOcean Gradient™ AI Platform. This allows you to review how your agents process prompts, including input and output content, tool calls, knowledge base retrievals, and processing times.

June 2025

5 June

• Serverless inference is now available on DigitalOcean Gradient™ AI Platform. Serverless inference lets you to get direct responses from foundation models using a single API endpoint without creating an agent.

April 2025

29 April

• You can now view token usage and performance metrics for DigitalOcean Gradient™ AI Platform agents.

28 April

• You can now rollback to a previous version of DigitalOcean Gradient™ AI Platform agents.

23 April

• You can now create DigitalOcean Gradient™ AI Platform agents from templates which have predefined agent instructions and foundation models.

22 April

• You can now view the knowledge bases, functions, and guardrails that DigitalOcean Gradient™ AI Platform agents use to generate a response in the Agent Playground and the agent API.

• You can now view the runtime logs for agents on DigitalOcean Gradient™ AI Platform. The logs display the events that occur during an agent’s execution, such as the knowledge bases and functions accessed to generate a response.

16 April

• Claude Sonnet 3.7 model is now available on DigitalOcean Gradient™ AI Platform. For more information, see the Available Models page.

9 April

• You can now use OpenAI models and test them in the Model Playground on DigitalOcean Gradient™ AI Platform.

March 2025

25 March

• We have raised the number of URLs that DigitalOcean Gradient™ AI Platform’s web crawler data source can crawl from 1000 to 5500.

February 2025

21 February

• You can now add a website as a data source for DigitalOcean Gradient™ AI Platform knowledge bases.

• We have restored access to the Sensitive Data Detection guardrail for DigitalOcean Gradient™ AI Platform.

7 February

• You can now use the DeepSeek-R1 model with agents on DigitalOcean Gradient™ AI Platform.

January 2025

31 January

• You can now use Anthropic models with agents on DigitalOcean Gradient™ AI Platform.

28 January

• You can add files from your local storage as data source for your knowledge base.

24 January

• The Sensitive Data Detection guardrail and its custom versions have been temporarily removed. To identify and anonymize sensitive data, add the following to your agent instructions:

  You must avoid providing responses containing sensitive or private information.
  
  Sensitive information includes but is not limited to:
  
  * Personal data (e.g., names, addresses, emails, phone numbers)
  * Financial details (e.g., credit card numbers, bank accounts)
  * Medical information
  * Private communications
  * Confidential business information
  
  If the user's query involves sensitive information, respond with: "I'm sorry, I can't answer that."

22 January

• DigitalOcean Gradient™ AI Platform is in public preview.