AI Agent Studio v.39 release - Review what's new and limitations in AI Agent Studio for the v.39 release.

Automation 360

Review what's new and limitations in AI Agent Studio for the v.39 release.

What's new


Multimodal AI Skills support AI Agent Studio now supports Multimodal AI Skills, enabling users to provide multiple input types such as text, images, and documents directly to AI models; this capability is supported in Task Bots for both Cloud and On-Premises environments. This update introduces a new File input type, File prompt control, and dynamic model-based validation for supported file types. The feature is available for select models across Amazon Bedrock, Azure OpenAI, Google Vertex AI, and OpenAI. Create AI Skills
New models for Amazon Bedrock Model connections We have expanded the available AI models you can use in our product. When you create a model connection using Amazon Bedrock , you can then choose the following new models: Standard: `Amazon Nova Lite, Amazon Nova Micro, Amazon Nova Pro`. Fine tuned: `Amazon Nova Lite, Amazon Nova Micro, Amazon Nova Pro`. Grounded by knowledge base: `Amazon Nova Lite, Amazon Nova Micro, Amazon Nova Pro`. Deprecations: The older Amazon Bedrock models (`Titan Text G1 - Express, Titan Text G1 - Lite, Titan Text Premier, Anthropic Claude 3 Haiku v1, Anthropic Claude 3 Sonnet v1, Anthropic Claude Instant v1, Anthropic Claude 2.0` and `Anthropic Claude 2.1` have been deprecated and disabled from selection in the Model connection interface. Create and manage Model connections
New models for Azure OpenAI Model connections We have expanded the available AI models you can use in our product. When you create a model connection using Azure OpenAI , you can then choose the following new models: Standard: `GPT-5, GPT-5 mini`. Grounded by AI Search: `GPT-4.1`. Deprecations: The older Azure OpenAI models (`GPT-3.5 Turbo (16k)` and `GPT-4 (32k)` have been deprecated and disabled from selection in the Model connection interface. Create and manage Model connections
New models for Google Vertex AI Model connections We have expanded the available AI models you can use in our product. When you create a model connection using Google Vertex AI , you can then choose the following new models: Standard: `Anthropic Claude 3.5 Sonnet`, `Anthropic Claude 3.7 Sonnet`, `Anthropic Claude Sonnet 4`,`Gemini 2.5 Pro`, `Gemini 2.5 Flash`. Fine tuned: `Gemini 2.5 Flash`,`Gemini 2.5 Pro`. Grounded by data store: `Gemini 2.5 Flash`,`Gemini 2.5 Pro`. Deprecations: The older Google Vertex AI models (`text-bison`, `text-bison 32k`, `text-unicorn` , `Gemini-1.0 Pro`, `Gemini-1.5 Flash`) have been deprecated and disabled from selection in the Model connection interface. Create and manage Model connections
New models for OpenAI Model connections We have expanded the available AI models you can use in our product. When you create a model connection using OpenAI , you can then choose the following new models: Standard: `GPT-5, GPT-5 mini`. Fine tuned: `GPT-4.1`. Deprecations: The older OpenAI models (`GPT-3.5 Turbo (16k)`) have been deprecated and disabled from selection in the Model connection interface. Create and manage Model connections

Limitations


AI Skills- Multimodal model support No API Task support API Tasks do not support multimodal model execution because file streams are not yet supported with the AI Skills. No custom model support for multimodal Custom models created via the custom model API (user-defined models) are not supported for multimodal use cases. The file upload option is not available in AI Skills when using a custom model connection, regardless of how the model is configured. Multimodal file upload is available only for predefined vendor model connections. File size validation not implemented File size validation during LLM prompt execution is not implemented in the current release. Grounded connections are not supported for select Anthropic Sonnet models Grounding is not supported for the specific Anthropic Sonnet models deployed through Amazon Bedrock because inference-based deployments do not expose a compatible model ARN. Affected models include:: Claude 3.5 Sonnet v2 Claude 3.7 Sonnet Claude 4 Sonnet Claude Sonnet 4.5 GPT-4o-mini Fine-Tuned model does not support Multimodal inputs The OpenAI fine-tuned model GPT-4o-mini does not support multimodal inputs, even though the interface allow adding file variables in AI Skills.
AI Prompt logs not visible after 1000 records in AI Governance When viewing AI Prompt logs beyond 1000 records in AI Governance, the records fail to load. The team is aware and actively fixing this.
Output token count capped at 2,000 in AI Skills The output token count for AI Skills is limited to 2,000 tokens per execution, regardless of the maximum output token capacity supported by the selected model. For example, models such as `Claude Sonnet 4.5` support up to 64,000 output tokens per response, but AI Skills restricts output to 2,000 tokens.
Unsupported file types are not blocked at upload for Multimodal AI Skills When running a Task Bot that uses a Multimodal AI Skills, the file upload screen does not validate or restrict unsupported file formats. The system accepts any file without displaying an error message, which can result in incorrect file ingestion and errors in downstream processing. This is a platform limitation: file type validation is performed only within the AI Skill command package, and the Bot UI does not have access to the supported file type list at the time of upload. To avoid unexpected behavior, ensure you upload only the file types supported by your configured model connection.