V3 / CUSTOM EXAMPLE

A decision with visible trade-offs

Compare supplied options against explicit constraints, then hand a compact recommendation back to the main agent. It demonstrates the respond exit without external research.

V3Website only · not bundledExit: respond

Use this scenario

Run

Run decision_matrix scenario with decision choosing a weekend project, options repair a shelf; build a planter, and constraints one afternoon and a small budget.

Use run_scenario with the saved scenario name and string-valued inputs. Required values are requested before execution.

View invocation JSON
JSON
{
  "scenario_name": "decision_matrix",
  "inputs": {
    "decision": "your decision",
    "options": "your options",
    "constraints": "your constraints"
  }
}
SCENARIO BLUEPRINT

Read the workflow.

decision_matrix3 INPUTS / 0 TOOLS / 3 STEPS
01

Inputs

PARAMETERS
InputRequirementDefault value
decisionRequiredNo default
optionsRequiredNo default
constraintsRequiredNo default
02

Agent instructions

SYSTEM PROMPT

Compare only the supplied options and information. Separate assumptions from facts. Do not invent prices or claim current research.

03

Tool access

CAPABILITIES

No tools are granted to this child conversation.

04

Ordered steps

EXECUTION
  1. 01
    CHAT TURN 01

    For {{decision}}, list the supplied options: {{options}}. Turn {{constraints}} into three comparison criteria.

  2. 02
    CHAT TURN 02

    Compare each option against those criteria. Explain unknowns instead of inventing measurements.

  3. 03
    CHAT TURN 03

    Choose a provisional option and state the strongest trade-off, the key uncertainty and one next action.

05

Return to main

RESPOND EXIT

Give the user a concise recommendation based on the child result. Preserve its uncertainties and do not invent additional research.

The main agent receives the result and these instructions, then composes the final reply.

EVERY XML ELEMENT / IN FILE ORDER

Every part, briefly.

Short explanations of every element and chat step in this scenario.

  1. 01
    <scenario>

    Names and versions the workflow.

    Writing example ↗
  2. 02
    <inputs>

    Declares input values.

    Writing example ↗
  3. 03
    <input>decision

    Requires a supplied value.

    Writing example ↗
  4. 04
    <input>options

    Requires a supplied value.

    Writing example ↗
  5. 05
    <input>constraints

    Requires a supplied value.

    Writing example ↗
  6. 06
    <systemPrompt>

    Sets the child's instructions.

    Writing example ↗
  7. 07
    <tools>

    Defines available capabilities.

    Writing example ↗
  8. 08
    <steps>

    Orders the chat turns.

    Writing example ↗
  9. 09
    <step 1>

    Define comparison criteria.

    Writing example ↗
  10. 10
    <step 2>

    Compare the supplied options.

    Writing example ↗
  11. 11
    <step 3>

    Recommend a next action.

    Writing example ↗
  12. 12
    <exit>

    Lets the main agent respond.

    Writing example ↗

Make the example yours.

These XML files are documentation downloads only. Reading or downloading one does not install it, execute it, or add it to the Lilith source archive.

Start with the bundled Scenarios directory from Lilith V3. Copy that matching catalog to a trusted editable folder and add your example XML alongside it. Keep the filename equal to its scenario ID.

Point LILITH_SCENARIOS_ROOT at that folder before starting Lilith. A custom root replaces the bundled catalog rather than merging with it, so keep the bundled files you still need, including greeting.xml for startup and scheduled greetings. Then ask Lilith to run the scenario by name and supply its required values.

Saved XML is trusted application content. Embedded C# executes with the host's permissions and requires the .NET SDK; it is not sandboxed. Workspace and scheduling operations keep their selected version's access and approval rules. Examples are authored against the documented contract; they are not live model execution guarantees.