Board Meeting: Simple Corporate Scenario

The Board Meeting template is the simplest showcase example—a 5-entity, 3-timepoint corporate scenario perfect for fast iteration, testing, and learning the Timepoint Pro workflow.

Template: board_meeting | Mode: FORWARD | Cost: ~$0.05 | Duration: ~2 minutes

The Scenario

A tech startup board meeting where the CEO proposes an acquisition. Five executives with competing agendas navigate high-tension strategic maneuvering:

CEO: Pushing the acquisition
CFO: Concerned about financial risk
Lead Investor: Evaluating exit timing
Board Chair: Balancing stakeholder interests
VP Engineering: Worried about technical integration

Temporal mode: FORWARD (standard causality—causes precede effects) Narrative arc: 3 hours compressed into 3 timepoints

Why Start Here?

This template is ideal for:

Learning the Workflow

Simple enough to understand in one run, complex enough to show core mechanisms

Fast Iteration

~2 minutes, ~$0.05 per run—perfect for testing parameter changes

Voice Tuning

5 distinct characters with archetypal profiles (executive, technical, investor)

Relationship Dynamics

Clear power dynamics, trust evolution, alignment tracking

Running the Simulation

Install and configure

git clone https://github.com/timepoint-ai/timepoint-pro.git
cd timepoint-pro
pip install -r requirements.txt
export OPENROUTER_API_KEY=your_key_here

Run the simulation

./run.sh run board_meeting

Expected output:

3 timepoints (3 hours of meeting time)
5 entities all at dialog resolution
~$0.05 cost
~2 minutes duration

Explore the outputs

# View narrative export
cat datasets/board_meeting_example/narrative_*.markdown

# Check dialog transcripts
./run.sh export last --format json

# Generate screenplay format
./run.sh export last --format fountain

Output Artifacts

Dialog Transcripts
Entity States
Relationship Tracking
Knowledge Flow

Each timepoint generates multi-party dialog with tracked confidence scores:

Timepoint 1 — Opening Proposal (Hour 1)

CEO: I want to bring a proposal to the board today. We have an 
     opportunity to acquire SyncTech for $12M. Their customer base 
     aligns perfectly with our roadmap.

CFO: $12M is a significant commitment given our current runway. 
     Can you walk us through the due diligence and expected ROI?

Lead Investor: What's the timeline on this? We're 8 months from 
               our Series B raise, and I want to understand how 
               this affects our valuation story.

VP Engineering: I'm more concerned about technical integration. 
                Do we have a staffing plan for onboarding their 
                engineering team?

Independent LLM calls per character
PersonaParams derived from entity state
Voice discipline applied (no AI-sounding phrases)

Each entity maintains cognitive and emotional state:

{
  "ceo": {
    "emotional_valence": 0.35,
    "emotional_arousal": 0.72,
    "energy_budget": 118.0,
    "role": "CEO pushing acquisition",
    "archetype": "executive_director"
  },
  "cfo": {
    "emotional_valence": -0.15,
    "emotional_arousal": 0.68,
    "energy_budget": 112.0,
    "role": "CFO concerned about financial risk",
    "archetype": "executive_director"
  }
}

Valence and arousal propagate through interactions, affecting dialog generation parameters.

M13 tracks trust and alignment between entities:

{
  "ceo -> cfo": {
    "type": "cooperative",
    "trust": 0.65,
    "alignment": 0.50
  },
  "cfo -> lead_investor": {
    "type": "aligned",
    "trust": 0.75,
    "alignment": 0.80
  },
  "ceo -> vp_engineering": {
    "type": "tense",
    "trust": 0.55,
    "alignment": 0.40
  }
}

Relationships evolve across timepoints as arguments unfold.

M3 tracks who knows what, when:

[
  {
    "entity": "cfo",
    "knowledge": "SyncTech acquisition proposal ($12M)",
    "source": "ceo",
    "timepoint": "tp_000",
    "confidence": 0.95
  },
  {
    "entity": "lead_investor",
    "knowledge": "Series B raise timeline (8 months)",
    "source": "scene_initialization",
    "timepoint": "pre_tp_000",
    "confidence": 1.0
  },
  {
    "entity": "vp_engineering",
    "knowledge": "Technical integration concerns",
    "source": "self_generated",
    "timepoint": "tp_000",
    "confidence": 0.90
  }
]

Mechanisms Featured

This template demonstrates 4 core mechanisms:

M1: Heterogeneous Fidelity

All 5 entities start at TENSOR_ONLY resolution and elevate to DIALOG as the meeting begins. In more complex scenarios, background attendees would remain at TENSOR while key speakers elevate.Try this: Modify initial_resolution in the template to start entities at different levels and observe lazy elevation.

M7: Causal Chains

Events occur in proper temporal order:

CEO proposes acquisition (tp_000)
CFO raises financial concerns → CEO responds with ROI data (tp_001)
Board vote with updated context (tp_002)

Each event references causal history from previous timepoints.

M11: Dialog Synthesis

Per-character turn generation with:

LangGraph steering: Selects next speaker based on narrative goals
Character node: Independent LLM call per character
PersonaParams: Arousal → temperature, energy → max_tokens
Voice discipline: 7-principle block prevents AI-sounding output
Archetype profiles: Executive rhetorical style (short sentences, business framing, decisiveness)

M13: Relationship Tracking

Trust and alignment values evolve:

CEO-CFO trust starts at 0.65, may degrade if financial concerns are dismissed
CFO-Lead Investor alignment high (0.80)—both focused on financial prudence
CEO-VP Engineering tension (0.40 alignment)—strategic vs. operational focus

Relationship state affects dialog generation (low trust = more hedging, higher arousal).

Template Configuration

{
  "scenario_description": "Simulate a tech startup board meeting where CEO proposes an acquisition",
  "world_id": "board_meeting_example",
  "patch": {
    "name": "Boardroom Brass",
    "category": "corporate",
    "tags": ["conflict", "decision", "multi-entity", "negotiation"],
    "description": "High-tension executive dynamics with competing agendas and strategic maneuvering"
  },
  "entities": {
    "count": 5,
    "types": ["human"],
    "initial_resolution": "tensor_only",
    "animism_level": 0
  },
  "timepoints": {
    "count": 3,
    "resolution": "hour"
  },
  "temporal": {
    "mode": "forward",
    "dramatic_tension": 0.5,
    "token_budget": 80000.0,
    "fidelity_template": "balanced"
  },
  "outputs": {
    "formats": ["json", "markdown"],
    "include_dialogs": true,
    "include_relationships": true,
    "include_knowledge_flow": true,
    "narrative_detail_level": "summary"
  }
}

Customization Ideas

Add More Entities

"entities": {
  "count": 7,
  "types": ["human"]
}

Add legal counsel, product lead, or advisors

Extend Timeline

"timepoints": {
  "count": 5,
  "resolution": "hour"
}

Multi-session board meetings

Enable Branching

"temporal": {
  "mode": "branching",
  "enable_counterfactuals": true
}

Explore: What if CFO votes yes vs. no?

Increase Tension

"temporal": {
  "dramatic_tension": 0.8
}

Higher arousal, more conflict

Iteration Workflow

This template is perfect for testing parameter changes:

Baseline run

./run.sh run board_meeting

Establish baseline dialog quality and cost

Modify parameters

Edit generation/templates/showcase/board_meeting.json:

"temporal": {
  "dramatic_tension": 0.8,  // was 0.5
  "token_budget": 120000.0  // was 80000.0
}

Compare outputs

./run.sh run board_meeting
./run.sh convergence e2e board_meeting --runs 3

Analyze:

Did higher tension increase arousal values?
Did dialog become more confrontational?
How did cost change?

Cost Optimization

Because this template is cheap (~$0.05), it’s ideal for testing cost reduction strategies:

Strategy 1: Use Free Models

./run.sh run --free board_meeting

Uses best available free model (cost: $0)

Strategy 2: Lower Token Budget

"temporal": {
  "token_budget": 50000.0,  // was 80000.0
  "token_budget_mode": "hard"  // enforce strict limit
}

Strategy 3: Reduce Resolution

"entities": {
  "initial_resolution": "scene"  // less detail than dialog
}

Strategy 4: Model Selection

# Use smaller model for this simple scenario
./run.sh run --model qwen/qwen-2.5-7b-instruct board_meeting

Export Formats

Screenplay (Fountain)
Training Data (JSONL)
Narrative (Markdown)

./run.sh export last --format fountain

Generates industry-standard screenplay:

INT. BOARDROOM - DAY

CEO
I want to bring a proposal to the board today.
We have an opportunity to acquire SyncTech
for $12M.

CFO
$12M is a significant commitment given our
current runway.

Properly formatted with Courier 12pt, standard margins.

./run.sh export last --format jsonl

Structured prompt/completion pairs:

{"prompt": "=== CAUSAL HISTORY ===\ntp_000: CEO proposes acquisition...\n=== ENTITY STATE ===\ncfo: valence -0.15, arousal 0.68...\n=== PREDICTION TASK ===\nPredict CFO's response", "completion": "CFO raises financial risk concerns, requests ROI data"}

Auto-generated summary with LLM enhancement:

# Board Meeting Simulation

## Summary

CEO proposes $12M acquisition of SyncTech. CFO raises 
financial concerns about runway impact. Lead Investor 
questions timing relative to Series B. VP Engineering 
worries about technical integration complexity.

## Key Decision Points

- Hour 1: Proposal presented
- Hour 2: Financial analysis and debate
- Hour 3: Board vote (outcome varies by run)

Next Steps

Mars Mission Portal

Try backward reasoning with PORTAL mode

Castaway Colony

Explore all 19 mechanisms in full showcase

Create Custom Scenario

Build your own corporate simulation from scratch

Convergence Testing

Learn to measure causal graph stability

Pro Tip: Run this template 3-5 times to observe convergence behavior. Questions to explore:

Does the CFO always raise financial concerns first?
Is the CEO-CFO relationship consistently tense?
What’s the variance in board vote outcomes?

Getting Started

Core Concepts

Temporal Modes

Mechanisms

Guides

Examples

Board Meeting

Board Meeting: Simple Corporate Scenario

The Scenario

Why Start Here?

Learning the Workflow

Fast Iteration

Voice Tuning

Relationship Dynamics

Running the Simulation

Output Artifacts

Mechanisms Featured

Template Configuration

Customization Ideas

Add More Entities

Extend Timeline

Enable Branching

Increase Tension

Iteration Workflow

Cost Optimization

Strategy 1: Use Free Models

Strategy 2: Lower Token Budget

Strategy 3: Reduce Resolution

Strategy 4: Model Selection

Export Formats

Next Steps

Mars Mission Portal

Castaway Colony

Create Custom Scenario

Convergence Testing

Getting Started

Core Concepts

Temporal Modes

Mechanisms

Guides

Examples

​Board Meeting: Simple Corporate Scenario

​The Scenario

​Why Start Here?

Learning the Workflow

Fast Iteration

Voice Tuning

Relationship Dynamics

​Running the Simulation

​Output Artifacts

​Mechanisms Featured

​Template Configuration

​Customization Ideas

Add More Entities

Extend Timeline

Enable Branching

Increase Tension

​Iteration Workflow

​Cost Optimization

​Strategy 1: Use Free Models

​Strategy 2: Lower Token Budget

​Strategy 3: Reduce Resolution

​Strategy 4: Model Selection

​Export Formats

​Next Steps

Mars Mission Portal

Castaway Colony

Create Custom Scenario

Convergence Testing

Board Meeting: Simple Corporate Scenario

The Scenario

Why Start Here?

Running the Simulation

Output Artifacts

Mechanisms Featured

Template Configuration

Customization Ideas

Iteration Workflow

Cost Optimization

Strategy 1: Use Free Models

Strategy 2: Lower Token Budget

Strategy 3: Reduce Resolution

Strategy 4: Model Selection

Export Formats

Next Steps