https://retellai.com/?utm_source=discord&utm_medium=seo logo
Could you share best practices and documentation o...
# ❓・ai-evy-support
d
@AI Evy Could you share best practices and documentation on setting up and working with staging and production environments for RetellAI, following a standard software development lifecycle?
a
Thanks for tagging me @Duc. I'll look through relevant sources and get back to you shortly.
### Answer Retell AI does not currently have dedicated documentation for multi-environment setups (staging/production) as a native feature. However, here's what's available: Version Control for Agents You can now create and manage agent versions directly in the Agent Builder: [(1) ]() - Make changes and test your agent safely—without affecting your live production calls - Revert to any previous version with a single click Hit the "Deployment" button to save a version, and use the history button to view and restore previous versions. Workspaces for Environment Separation You can have up to 50 workspaces, along with folders and unlimited agent creation. [(2) ]() This allows you to create separate workspaces for dev, staging, and production environments. Enterprise DevOps Practices For enterprise-level CI/CD and multi-environment best practices, it's recommended to contact founders@retellai.com for queries and support related to enterprise plans. [(3) ]() API-Based Approach You can programmatically create and manage conversation flows via the API, which enables infrastructure-as-code patterns:
Copy code
javascript
import Retell from 'retell-sdk';
const client = new Retell({
  apiKey: 'YOUR_RETELL_API_KEY',
}) ;
const conversationFlowResponse = await client.conversationFlow.create({
  model_choice: { model: 'gpt-4.1', type: 'cascading' },
  nodes: [
    {
      id: 'start',
      instruction: { text: 'Greet the customer and ask how you can help them.', type: 'prompt' },
      type: 'conversation',
    },
  ],
  start_speaker: 'agent',
}) ;
[(4) ]() This API approach allows you to script agent deployments across environments. Would you like a general answer on how to structure multi-environment workflows using these available features?
​ To learn more, see the sources I considered: [[1] Platform Changelogs | Retell AI](https://www.retellai.com/changelog) [[2] Multi env support](https://discord.com/channels/1186424376300679209/1273014207197216798) [[3] Best practice for devops: environments, versioning and CI/CD?](https://discord.com/channels/1186424376300679209/1263770777346637874) [[4] Create Conversation Flow](https://docs.retellai.com/api-references/create-conversation-flow) ​
Feel free to tag @AI Evy with additional questions. I also appreciate feedback, it helps me improve.
d
@User any limitation with API approach? Can we view visual diagram of agents ? any examples?