Rasa NLU | Structured Intent Recognition with LLM Flexibility

NLU that evolves with you

Start with structured, intent-based understanding and expand with LLM-powered flexibility when your use cases demand more.

Understand users on your terms

Understand users on your terms.
Get full control over how your agents interpret messages—so you can tailor intent and entity recognition to your use case, not someone else’s defaults.

• Train models with your own domain-specific data for high accuracy
• Choose how LLMs participate in comprehension: first-pass understanding, fallback, or hybrid
• Customize and optimize your NLU pipeline with modular components for accuracy, control, and cost efficiency

Extend NLU precision with LLM flexibility

Rasa is all about optionality. Keep NLU where it is working well, and opt for language models when you need more powerful dialogue understanding.

• Classify intent with structured NLU, and fall back to LLMs only when confidence is low
• Use LLMs to improve conversational quality without giving up control over logic
• Let Flows drive behavior, while LLMs support phrasing, repair, and natural understanding

Build on the most battle-tested NLU in conversational AI

Rasa has led NLU innovation for nearly a decade with the research, tools, and real-world experience to prove it.

Classify intent with structured NLU, and fall back to LLMs only when confidence is low

Spot and fix misunderstood examples without breaking what already works

The building blocks for real-world-ready AI agents

Features

• Chat: Power structured, multi-turn conversations across every messaging channel.

• Voice: Turn your agent into a real-time voice experience with enterprise-grade performance.

• Agentic AI: Blend autonomy with guardrails to create AI agents that adapt while staying under control.

• Multilingual AI: Expand globally with agents that switch languages, track context, and maintain brand consistency.

See what our customers are saying

Enterprise teams use Rasa to build and deploy high-trust AI agents that perform in production.

• Daniel Schupmann
  Head of CAI/ GenAI @B2C and Digital Care Platforms/ Experience: "Our goal was to align cutting-edge AI technology with customer needs to provide seamless and innovative experiences. Partnering with Rasa allowed us to rethink how conversational AI could transform support."

• James Bradley
  Senior Director of Data Science & Machine Learning: "We needed a solution that could scale with our ambitions. Rasa solves some hard problems related to conversational AI that enable us to move faster."

• Wayne Foley
  Director Software Engineering, Digital Innovation Group, at Providence: "We've built a scalable, compliant platform with Rasa that supports real patient needs and drives measurable outcomes. CALM gives us a framework to keep that momentum going, with the flexibility to grow responsibly as expectations around AI continue to evolve."

• Bogdan Stešević
  Head of the Group for Quality of Services and Development of AI at eUprava: "With Rasa, we launched quickly and gave citizens a simpler way to access government services. The system allows us to expand at our own pace while controlling how services are delivered. Studio and CALM allow us to build new use cases while maintaining stability as the platform grows."

• Loic Mayet
  Information Systems Director, Groupe IMA: "We’re not experimenting with voice. We’re deploying it. That’s the difference."

• Edmundas Balčikonis
  CEO, Eddy Travels: "Switching to Rasa accelerated development. We now process thousands of conversations each month with 96% accuracy, which resulted in better user engagement and more searches per conversation."

• Richard Popa
  Project Leader and Solutions Manager, Orange: "We developed a real partnership with Rasa based on developing skills rapidly, correcting bugs quickly, and sharing a wish list with the dev team."

• Albert Heijn: "Albert Heijn adopted Rasa and began migrating to CALM through a coexistence strategy — starting with a single flow and gradually expanding coverage, achieving a 22% improvement in prevented contact rate and a 37% increase in quality score."

AI that adapts to your business, not the other way around

Build your next AI agent with Rasa

Power every conversation with enterprise-grade tools that keep your teams in control.