KNIME is releasing Analytics Platform 5.5, introducing new capabilities for building AI agents.
Now, users can easily build tool workflows from scratch or turn existing workflows into agent tools, effectively handle agent conversation data with structured message support, and interact naturally with agents through a chat interface.
The update offers more choice when selecting AI models with new connectors, enabling the use of Anthropic Claude, Gemini models from Google AI Studio and Vertex AI, as well as models from IBM watsonx.ai.
Additionally, KNIME Analytics Platform 5.5 offers several user interface improvements, improved date and time handling, direct integration with Microsoft Fabric, and more.
This release makes agent development even more accessible and easier for anyone who wants to build them, without the need to deal with complex integrations, coding, or steep learning curves, the company said.
KNIME Analytics Platform 5.5 lets you easily build new tool workflows from scratch or convert existing workflows into agent tools:
- You can now parameterize tool workflows with configuration nodes you already use (for e.g., String Configuration), and define agent-tool communication using the Tool Message Output node.
- Use Workflow Input and Workflow Output nodes to handle data transfer in agent workflows. Agents can now pass large data tables to and from tools.
- The new Workflow to Tool node reads your tool workflows and connects them directly to agents via the Agent Prompter or Agent Chat View nodes.
Existing users can now create agents from scratch using the same concepts with no new learning curve. New users can also use KNIME's visual workflow building to create agents without coding.
With KNIME Analytics Platform 5.5, users get a new Message data type that structures all this conversation data with clear roles and content. All Prompter nodes now operate with Messages.
The new Message Creator node lets you build structured messages without any scripting, while the Message Part Extractor node extracts specific message components without custom code.
KNIME is offering a new series of free courses to get started with KNIME Analytics Platform 5.5:
For more information about this news, visit www.knime.com.