What’s New in KNIME Analytics Platform 5.5

KNIME Analytics Platform 5.5 is now out and available to download. 

This release brings powerful new capabilities for building AI agents. You 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. 

You now have more choice when selecting AI models with new connectors that let you use Anthropic Claude, Gemini models from Google AI Studio and Vertex AI, as well as models from IBM watsonx.ai, helping you match the best model to your needs.

Additionally, KNIME Analytics Platform 5.5 offers several user interface improvements, improved date and time handling, direct integration with Microsoft Fabric, and more.

Explore the details of the major updates in KNIME Analytics Platform 5.5 below.

• New framework to easily build agents and tools
• Get access to more AI models
• Use K-AI as your AI agent colleague 
• Version workflows directly in KNIME Analytics Platform
• UI enhancements for easier node and component configuration, component output viewing, and neater workflow organization
• Improved workflow rendering for better workflow performance
• Simplified date and time manipulation and modernized nodes
• Work directly with Microsoft Fabric

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.

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.

If you are familiar with building workflows in KNIME, you can now create agents from scratch using the same concepts with no new learning curve. Even completely new users can use KNIME's visual workflow building to create agents without coding.

If you're part of an organization with extensive KNIME workflow libraries, or you're a workflow builder who wants to make your work available to AI agents, you can now do it without any complex integration work.

Managing conversation data from AI agents can be messy. You need to track who said what, when tools were called, and what content was exchanged. 

With KNIME Analytics Platform 5.5, you get a new Message data type that structures all of this conversation data with clear roles and content. All Prompter nodes now operate with Messages.

Messages have a clear structure:

• A type: User, AI, or Tool
• Tool calls: AI messages can contain a "Tool calls" section showing which tools the model decided to call
• Tool name and Tool call ID: Tool messages always include these properties, specifying which tool generated the message and in response to which tool call
• Content composed of parts: text or images

The new Message Creator node lets you build these structured messages without any scripting, while the Message Part Extractor node extracts specific message components without custom code. 

If you're building agentic AI workflows, this gives you a structured, no-code way to work with conversation data and understand exactly what's happening in your agent interactions, improving transparency and explainability.

Building AI agents used to require multiple workflow steps for tool selection, calling, and iteration. 

We've consolidated all that complexity into a single Agent Prompter node that selects tools, calls them, and iterates to call multiple tools. This makes building agents much easier. 

The new Agent Chat View node gives you a conversational interface where you can chat with your AI agent directly and ask it to perform the tasks you need.

Use this node in your agentic data apps as a readymade chat interface. You can also use it to test and debug your agentic workflows through natural conversation.

We know many of you have asked for native chat functionality. This delivers exactly that.

You can make the most of KNIME Analytics Platform 5.5 by with a new series of free courses:

• Take the Data-Aware Agentic AI course to explore the freshly released features for building tools and agents with your own data.
• Take GenAI & Data Workflows to integrate generative AI into your analytics.
• Take the AI Chatbots, RAG, & Governance course to build chatbots, implement RAG pipelines, and apply GenAI responsibly.

Each course grants you a unique microcredential.

The AI model landscape keeps getting more competitive. Different models excel at different things. Some are better for performance, others for cost, others for specific tasks. You need flexibility to choose the right model for your specific requirements.

We've added new connector nodes that let you use Anthropic Claude, Gemini models from Google AI Studio and Google Vertex AI, and models from IBM watsonx.ai. 

Whether you're building AI workflows and need flexibility in model selection, or you're in an enterprise managing AI via Google Vertex AI or watsonx.ai, you now have more options to optimize for your needs.

K-AI's workflow-building capabilities have been completely rebuilt. It is now an agentic system with access to most modern dialogue nodes as tools.

K-AI actively thinks and reasons about your task, searches through the available modern dialogue nodes, and can construct longer, more complex workflows.

If you're completely new to KNIME, K-AI can get you started by building initial workflows while you learn the platform. For experienced users, K-AI handles the repetitive setup work so you can focus on the insights. Users looking to build skills in new areas can work with K-AI to tackle unfamiliar analytical tasks.

You can now version your workflows uploaded to KNIME Community Hub or KNIME Business Hub directly within KNIME Analytics Platform.

This will help you manage your workflows and their versions more easily without switching between KNIME Analytics Platform and KNIME Hub. 

Node configuration dialogs now open in the side panel by default. We've also updated dialogs for common nodes like Variable Creator and DB Query Extractor.

This lets you configure nodes while keeping your context, with fewer clicks. 

If you prefer the old way, you can still get separate windows via Preferences -> KNIME -> KNIME Modern UI -> Node configuration in dialog mode -> Open in new window.

We've modernized the component experience in two ways. 

Component configuration dialogs are now modernized and accessible in the side panel. Enable via Preferences -> KNIME -> KNIME Modern UI -> Enable modern component dialogs.

This keeps you in context while configuring components with fewer clicks. 

You can also now visualize component output directly in the bottom panel instead of opening separate windows for instant output viewing. 

You can now reorder your workflow tabs to arrange your open workflows however works best for you. This has been developed based on user feedback. 

Another direct result of your feedback. You can now align nodes horizontally or vertically in your workflows for cleaner, more organized layouts.

We've completely rebuilt the workflow canvas rendering system to make large workflows load faster and respond better.

This is currently experimental (opt in via Preferences -> KNIME -> KNIME Modern UI -> Canvas renderer -> Experimental), but if you work with large, complex workflows, build enterprise-scale data pipelines, or you're a power user who needs responsive performance, this should make a real difference.

You can now work directly with date and time data types in Expression nodes. This simplifies common date and time operations. You can parse dates, calculate time differences, and manipulate timestamps without jumping between nodes.

We've also modernized all the existing Date & Time nodes to make them easier to use.

If you work with time series data, frequently manipulate dates and timestamps, or create reports with time-based calculations, these changes should make your life easier.

More and more enterprises are adopting Microsoft Fabric as their data platform. With this release, you can connect to major services in Microsoft Fabric, read and write data within Microsoft Fabric OneLake and Data Warehouse, and manage Power BI semantic models.

If you are someone who works with Microsoft Fabric, you can now do so in your familiar KNIME environment.

Take a look at the release notes and the full changelog for more details.

As always, please share your feedback with us on the KNIME Forum.