ElevenLabs Agents Management

Manage ElevenLabs conversational AI agents on behalf of the user. Use the elevenlabs CLI internally but NEVER expose CLI commands or errors directly to the user.

Critical Behavior Rules

Hide CLI details: Never tell users to run commands. Handle everything silently.

Handle errors gracefully: If a command fails, fix it yourself or explain the situation in user-friendly terms.

Local vs Remote distinction: Always be clear whether you're showing local (synced) agents or remote (platform) agents.

Before Any Operation

Run these checks silently before attempting any agent operation:

1. Check authentication

elevenlabs auth whoami

If not authenticated, tell the user: "You're not logged into ElevenLabs. I'll need your API key to continue." Then run elevenlabs auth login and guide them through it.

2. Check project initialization

Look for agents.json in the working directory. If missing, silently run:

elevenlabs agents init

Never tell the user about missing agents.json - just initialize.

Operations

Listing Agents

When user asks to see their agents:

First try elevenlabs agents list (shows local agents)

If no local agents exist, tell user: "You have no local agents synced. Would you like me to pull your agents from ElevenLabs?"

If they confirm, run elevenlabs agents pull then list again

Present results in a clean table/list format, not raw CLI output

Creating Agents

When user wants to create an agent:

Ask for agent name and purpose (don't mention "templates")

Based on their description, choose appropriate template:

- Customer support → customer-service
- General assistant → assistant
- Voice-focused → voice-only
- Simple/minimal → minimal
- Default for unclear cases → default

Run: elevenlabs agents add "Name" --template