Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.opendot.ai/llms.txt

Use this file to discover all available pages before exploring further.

Agent Studio is the first step in the OpenDot flow. It creates draft voice agents that become the anchor for pipeline tuning, model settings, knowledge configuration, live testing, and hardware binding.
OpenDot Agent Studio screen

​
What you see in the UI

Agent Studio has two panels:
  • Create voice agent: creates a new draft agent.
  • Draft agents: lists persisted agents and switches the selected agent.
The selected agent drives the rest of the console. Configuration edits its pipeline, Browser Test authorizes runtime sessions for it, and Dot Device can bind it to hardware.

​
Create voice agent

Each agent starts with:
  • Agent name: a short label such as Lobby guide
  • Description: the job the agent should perform
When you click Create draft agent, OpenDot attaches the default four-stage pipeline: 
VAD -> STT -> LLM -> TTS
The new agent becomes the selected agent immediately.

​
Draft agents

Use the agent list to switch between drafts. Each row shows the agent name, description, and last update time. Selecting a row changes:
  • which pipeline is edited in Configuration
  • which agent the console uses when it asks the platform API for a runtime voice-session token in Browser Test
  • which voice config can be bound to a device in Dot Device

​
Persistence model

The platform API persists the agent and its default pipeline in PostgreSQL as:
  • agents
  • agent_versions
  • pipelines
  • pipeline_versions
Editing an agent or its pipeline writes a new draft version. The current prototype is still single-workspace, but the data model is already shaped around durable agent and pipeline configuration rather than browser-only state. See Database inspection to inspect the stored rows and Platform architecture for the full control-plane flow.

​
Next phase

Open Configuration to tune the selected agent’s VAD, STT, LLM, and TTS stages.