Introducing Kasal

2026-03-09 · Source: Databricks · Field: Technology & Digital — Artificial Intelligence & Machine Learning, Software Development & Engineering, Cloud Computing & IT Infrastructure · Depth: Intermediate, quick

Summary

Databricks has introduced Kasal, an agent-powered platform designed to simplify the creation, development, and deployment of agentic AI systems for both experts and non-experts. Kasal addresses challenges like the shortage of skilled AI talent and the rapid evolution of AI technologies by offering an intuitive visual interface. It allows users to design single and multi-agent workflows via drag-and-drop or conversational prompts, automatically generating orchestration code. Built on the open-source CrewAI framework, Kasal integrates deeply with Databricks, providing features like workspace authentication, governance, MLflow for tracing, Vector Search for memory, and Databricks Apps for serving. The platform also supports exporting workflows as code for advanced customization and offers live observability for monitoring agent interactions and debugging model performance.

Key takeaway

For AI/ML Directors seeking to accelerate agentic AI adoption and overcome talent gaps, Kasal offers a compelling solution. Its visual workflow designer and deep Databricks integration enable both non-experts and seasoned engineers to build and deploy production-grade AI agents efficiently. You should evaluate Kasal to streamline your team's agent development lifecycle and ensure enterprise-ready deployments with integrated governance and observability.

Key insights

Kasal democratizes agentic AI development through a visual, Databricks-native platform for diverse skill levels.

Principles

• Visual design simplifies complex AI orchestration.
• Platform integration enhances enterprise readiness.
• Code export enables expert customization.

Method

Design agentic workflows visually or via conversational prompts, connect tools, run agents, and observe behavior. Kasal generates orchestration code, leveraging CrewAI and Databricks services for deployment and monitoring.

In practice

• Build AI agents using a drag-and-drop UI.
• Export visual workflows to code for refinement.
• Monitor agent performance with MLflow tracing.

Topics

• Agentic AI Systems
• AI Workflow Orchestration
• Databricks Integration
• Kasal Platform
• Visual AI Development

Code references

• databrickslabs/kasal

Best for: CTO, VP of Engineering/Data, Director of AI/ML, AI Engineer, MLOps Engineer, AI Product Manager

Related on AIssential

• Custom Agents now available on Databricks — Databricks Custom Agents streamline AI agent development and deployment with serverless infrastructure and integrated governance.
• #353 The Data Team's Agentic Future with Ketan Karkhanis, CEO at ThoughtSpot — AI agents are transforming data analytics by automating tasks, shifting human roles, and demanding data readiness.
• How World Bank Group uses databricks to eradicate poverty through shared knowledge — The World Bank Group unified disparate data on Databricks, using AI agents and RAG to democratize knowledge and accelerate global impact.
• The Rise of Cloud Coding Agents — Cloud-based AI coding agents enable asynchronous, autonomous development workflows, enhancing scalability over traditional desktop agents.
• DataRobot + Nebius: An enterprise-ready AI Factory optimized for agents — The AI Factory for Enterprises accelerates AI agent deployment and governance through specialized cloud infrastructure and comprehensive lifecycle management.
• The Agentic Enterprise Just Got Real — AI's primary challenge is context management, not intelligence, requiring robust governance for agentic systems.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Databricks.