Skip to main content
Studio V2 cannot be pre-configured in values.yaml. Adding studioV2.enabled, STUDIO_V2_ENABLED, or any similar key to your Helm values has no effect — Helm silently ignores unrecognized keys. The BUILT_IN_LLM_PROVIDER, BUILT_IN_LLM_MODEL, and BUILT_IN_LLM_API_KEY chart values are for a separate platform AI feature (prompt improvement, flow chat). Setting them does not configure Studio V2.
This guide enables Crew Studio V2 on a running deployment. You need platform access and at least one LLM provider API key.

​
Prerequisites

  • CrewAI Platform is running and accessible at its configured hostname
  • Admin access to the web UI
  • An API key for a supported LLM provider (Anthropic, OpenAI, or any LiteLLM-compatible model)

​
Step 1: Create the studio-v2 LLM Connection

In the web UI:
  1. Navigate to Settings → LLM Connections
  2. Click New Connection
  3. Set the name to exactly studio-v2 (lowercase, no spaces)
  4. Select your LLM provider and enter the model name and API key
  5. Click Save
The connection name must be exactly studio-v2 (lowercase). The install commands in Step 3 look up this name specifically — a different name or capitalisation will cause them to fail.

​
Step 2: Set as Default Connection

  1. Navigate to Settings → Crew Studio
  2. Under Default Connection, select studio-v2
  3. Click Save

​
Step 3: Run Install Commands

Run the following commands in order. Each must complete successfully before running the next. 
# 1. Install the Studio agent
kubectl exec -it deploy/crewai-web -- bin/rails studio:agent:install

# 2. Sync and index tools
kubectl exec -it deploy/crewai-web -- \
  bin/rails studio:tools:sync_crewai_tools \
       studio:tools:sync_enterprise_tools

# 3. Install the Studio runner
kubectl exec -it deploy/crewai-web -- bin/rails studio:runner:install
studio:agent:install will fail if the studio-v2 LLM Connection does not already exist in the UI. Complete Steps 1 and 2 before running any of these commands.

​
Step 4: Verify

Check that the Studio assistant deployment is running: 
kubectl get deploy | grep studio
kubectl logs -l app=studio-assistant --tail=20
Both the studio-assistant and studio-runner deployments should show Running.

​
Change the Studio Agent Model (Optional)

By default the Studio Agent uses an Anthropic model. To use a different model, update the MODEL field in the studio-v2 LLM Connection (Settings → LLM Connections → studio-v2 → Edit). The Studio Agent supports any model available through LiteLLM.
After changing the model in the studio-v2 LLM Connection, manually restart the studio-assistant deployment for the change to take effect. The platform does not trigger an automatic restart.
kubectl rollout restart deployment/studio-assistant