Skip to content

Your customers are unique, with unique ways of talking about their needs

Understanding the nuances of your user base and building to their needs is the heart of any great customer experience.

Conversation-driven development is the process of listening to your users and using those insights to improve your AI assistant.

The 6 principles of conversation-driven development

Conversation-driven development is a set of practices that help teams build more resilient, more natural-sounding virtual assistants. It’s a user-centered approach that’s baked into every feature Rasa ships.

Share

Learn about users’ needs by sharing your assistant with test users early in development. Train your assistant on test users’ conversations to improve accuracy.

Review

Read conversation transcripts between your assistant and your customers. Use conversation reviews to see the impact of model changes and updates.

Track

Use both internal metrics and external signals to measure how well your assistant is helping users. Tag conversations to track successes and what’s not working.

Annotate

Source training data from real-life conversations by annotating user messages. Create a virtuous cycle of learning from what users actually say.

Fix

Apply improvements and bug fixes in short, iterative development cycles. Create test cases from successful conversation flows.

Test

Strive for complete test coverage across your assistant. When changes are pushed to production, run automated tests to catch regressions.

Ready to get started? Learn how to put conversation-driven development into practice

Get resources and practical guides on conversation-driven development, to help teams ship better virtual assistants.

CDD Playbook

Includes 5 guided activities to help teams adopt conversation-driven development.

Learn more →

6 steps to CDD

Watch this on-demand webinar for an in-depth look at conversation-driven development.

Learn more →

Rasa X

Rasa X is a tool for building assistants according to conversation-driven development.

Learn more →

Start creating your own contextual AI assistant!