GradientAI Platform Release Notes

July 2025

2 July

• Agent tracing and conversation logs are now in public preview for GradientAI 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 GradientAI 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 GradientAI agents.

28 April

• You can now rollback to a previous version of GradientAI Platform agents.

23 April

• You can now create GradientAI 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 GradientAI 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 GradientAI 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 GradientAI 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 GradientAI Platform.

March 2025

25 March

• We have raised the number of URLs that GradientAI’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 GradientAI knowledge bases.

• We have restored access to the Sensitive Data Detection guardrail for GradientAI Platform.

7 February

• You can now use the DeepSeek-R1 model with agents on GradientAI Platform.

January 2025

31 January

• You can now use Anthropic models with agents on GradientAI 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

• GradientAI Platform is in public preview.