You are the CFO of a $50M/year commercial HVAC contractor.

Last quarter, three projects closed at 6.8% realized margin against a 15.2% bid margin. This is no longer an anomaly — it’s a pattern.

Dashboards show data.
You need something that thinks.

Your mission is to build an AI agent — not a chatbot — that autonomously monitors a portfolio of HVAC construction projects, identifies margin erosion risks, investigates root causes, takes action, and reports back.

The agent must:

• Scan the entire portfolio
• Detect margin risk signals
• Investigate by chaining tool calls
• Produce actionable outputs
• Support follow-up questions with memory
• Communicate findings clearly in business language

This is not a dashboard challenge.
This is not a chatbot challenge.

You are building an autonomous AI agent using:

• An LLM (reasoning brain)
• Tool calling (data access + calculations)
• Memory
• A looping mechanism (stopWhen)
• Email capability (proactive reporting)

Your agent should continue investigating until it understands the situation — not stop after one query.

Participants receive a realistic construction portfolio dataset (~18K records), including:

• contracts.csv
• sov.csv
• sov_budget.csv
• labor_logs.csv
• material_deliveries.csv
• billing_history.csv
• billing_line_items.csv
• change_orders.csv
• rfis.csv
• field_notes.csv (~1,300 unstructured reports)

Embedded within the data are real-world signals:

• Labor overruns
• Scope drift
• Verbal approvals
• Billing lags
• Pending change orders
• RFI-related exposure

Not every project is failing.
Not every risk is obvious.
Your agent must find the story.

Given a prompt like:

Your agent should autonomously:

1. Assess overall margin health
2. Identify high-risk projects
3. Investigate root causes (labor, materials, billing, change orders, RFIs, field notes)
4. Quantify financial exposure
5. Recommend specific recovery actions
6. Send an email summary or alert
7. Support follow-up conversation with context memory

• Agent Intelligence (40 pts)
  - Autonomous reasoning across portfolio - Multi-step tool chaining - Accurate financial calculations - Actionable outputs (not vague flags)
• Agent Experience (30 pts)
  - Transparent step-by-step reasoning - Real-time streaming responses - Conversational follow-up with memory - Clear, business-friendly communication
• Implementation Quality (20 pts)
  - Built using required stack - Proper use of Granola - Email reporting works - Handles ~18K records efficiently - Reasonable performance - Deployed and accessible
• Business Insight (10 pts)
  - Explains why margin erosion occurs - Quantifies exposure - Forecasts potential outcomes
• Bonus (Up to +20 pts)
  - Proactive alerting without user prompt - Cross-project pattern detection - Confidence levels / uncertainty acknowledgment - Deep multi-turn conversational memory