LILITHLOCAL INTELLIGENCE
WATCH / V3

Lilith V3 - subagent tracking and display controls

A real narrated Lilith V3 conversation, recorded from pinned source 536edbbdbb6eb3be1ef9d1e3a31dc5465f3aa92a using its version-specific test conversation.

Gemma 4Ollama
Open the portrait recording ↗Inspect this version's code ↗

What happens in this recording

You: Run greeting scenario with name Alex and tone warm and concise. Lilith: Good morning, Alex! I'm Lilith, your helpful personal AI assistant. How can I assist you today? You: Run greeting scenario with name Alex and tone warm and concise again. Lilith: Good morning, Alex! I'm Lilith, your helpful personal AI assistant. I hope you have a wonderful day. How can I assist you this morning?

Conversation XML

The complete XML script used for this recording, including its settings, system prompt and every scripted message.

XML / FULL RECORDING CONVERSATIONStructureInputsTools / C#StepsExit
<video title="Lilith V3 - subagent tracking and display controls" version="3.0.0-alpha.2" backend="Ollama" model="gemma4" mode="chat" showSubagents="false" voice="af_heart" progressSeconds="3" pauseSeconds="1.5">
  <systemPrompt>You are Lilith. When asked to run greeting, call run_scenario with scenario_name greeting and supplied string input values. Never invent a scenario result. Keep replies concise.</systemPrompt>
  <messages>
    <message>Run greeting scenario with name Alex and tone warm and concise.</message>
    <message>/subagents</message>
    <message>/subagents show</message>
    <message>Run greeting scenario with name Alex and tone warm and concise again.</message>
    <message>/subagents hide</message>
    <message>/subagents</message>
  </messages>
</video>
Download conversation XML

Explore the implementation

Read the relevant source and compare its changes before trying the workflow locally. Video playback does not execute any tools in your browser.

Open the source archive ↗