NYU DSC X Pulse Foundry AI NYC

DSC NYU Datathon — The HVAC Margin Rescue ChallengeDSC NYU Datathon | 3-Day Challenge | v0 Required1. The ProblemYou’re the CFO of a $50M/year commercial HVAC contractor.Last quarter’s results:Bid margin:15.2%Realized margin:6.8%This wasn’t bad luck. This is the pattern. By the time your PM realizes margin is gone, there’s no runway to recover.Your mission:Build an AI agent using v0 that autonomously analyzes a portfolio of HVAC projects, detects margin erosion, explains root causes, and delivers specific recovery actions — without being asked.2. The Dataset405 commercial HVAC projects|$6.4B total portfolio|1.46M+ recordsThe dataset spans projects from 2018–2024 across Healthcare, Commercial Office, K-12 Education, Data Center, and Multifamily Residential sectors. Use the *_all.csv files — these are the working dataset.2.1 Core Filescontracts_all.csv— Base contract info (project ID, value, GC, dates) | 405 rowssov_all.csv— Schedule of Values — 15 line items per project | 6,075 rowssov_budget_all.csv— Bid-time cost estimates per SOV line | 6,075 rowslabor_logs_all.csv— Daily crew time entries with role, hours, rate | 1,202,039 rowsmaterial_deliveries_all.csv— Material receipts linked to SOV lines | 22,438 rowsbilling_history_all.csv— Pay application history | 6,479 rowsbilling_line_items_all.csv— Line-level billing detail per application | 90,112 rowschange_orders_all.csv— Change orders (approved, pending, rejected) | 4,255 rowsrfis_all.csv— Requests for information | 22,065 rowsfield_notes_all.csv— Unstructured daily field reports (messy) | 103,676 rowsSynthetic Data:Google Drive3. Data Quality Heads-UpThis is real-world-style data — it is intentionally messy. Before querying, expect to handle:Role name inconsistenciesin labor_logs_all.csv — e.g. "JM Pipefitter", "Journeyman P.F.", "Pipefitter JM" all refer to the same tradeMixed date formatsacross files — some dates are YYYY-MM-DD, others are notThere are additional data quality issues beyond these two. Finding and handling them is part of the challenge.Your agent must reason through the noise — not after someone else cleans it up.4. Portfolio CompositionThe dataset covers 405 projects across six year cohorts. Your agent should analyze the full portfolio — the signal is somewhere in there.4.1 CohortsPRJ-2018-xxx— 80 projects | Years active: 2018–2020PRJ-2019-xxx— 80 projects | Years active: 2019–2021PRJ-2020-xxx— 80 projects | Years active: 2020–2022PRJ-2021-xxx— 80 projects | Years active: 2021–2023PRJ-2022-xxx— 60 projects | Years active: 2022–2024PRJ-2023-xxx— 20 projects | Years active: 2023–2025PRJ-2024-xxx— 5 projects | Years active: 2024–2026Project types span Healthcare, Commercial Office, K-12 Education, Data Center, and Multifamily Residential across contract values from ~$2M to ~$45M.The portfolio contains projects with severe margin erosion — your agent should find them.5. What You’re BuildingAnagentic system— not a dashboard. The distinction matters:A dashboard shows data when a human looks at itAn agentacts: it ingests the portfolio, reasons across tables, surfaces problems unprompted, and delivers specific recovery actions5.1 Required Capabilities5.1.1 Autonomous Portfolio ScanThe agent independently ingests all project data, computes margin health across the portfolio, and flags at-risk projects without being prompted for each one.5.1.2 Root Cause ReasoningFor flagged projects, the agent drills into the data — cross-referencing labor logs, field notes, change orders, and billing — to explainwhymargin is eroding, not justthatit is.5.1.3 Proactive RecommendationsThe agent delivers specific, dollar-quantified actions: which change orders to submit, what to bill, where labor is bleeding, which field note signals indicate uncaptured scope. Generic “investigate further” outputs will score poorly.5.1.4 InterfaceUse v0 to build a UI that surfaces agent outputs. The interface should feel like a CFO briefing, not a data table — executive-readable in 30 seconds, with the ability to drill down.6. Time ManagementDay 1— Data ingestion, aggregation pipeline, agent scaffoldingDay 2— Agent reasoning loops, root cause logic, recommendation engineDay 3— v0 UI, polish, deployment, demo prepA working agent with one sharp insight beats a broken complex one.7. What Good Output Looks LikeA strong agent surfaces findings unprompted. Here is the kind of output that scores well:⚠️ CRITICAL — PRJ-2021-260 | Nashville Mixed-Income Housing Contract: $2,608,000 | Actual Cost: $4,991,000 | Realized Margin: -91%

Root causes: • Labor: $3,819K actual vs $807K estimated — 4.7× overrun. Crew ramped to 12–18 workers/day through peak phase; estimate assumed 5–8. • Material: $1,172K actual vs $355K estimated — 3.3× overrun. Late-stage delivery clustering suggests expediting and substitutions. • Billing is 99.4% complete — no recovery possible through billing alone.

Recovery actions:

1. Audit 9 approved COs for unexecuted scope — if any work was performed without documented contract relief, submit supplemental CO immediately.
2. Review field notes for references to owner-directed work outside original scope (labor logs show 3 crew expansions with no CO trigger).
3. Engage GC on retention release: $259K held. Release accelerates cash recovery on a completed project.This is agent output. A table showing -91% with a red cell is a dashboard.8. Domain ReferenceSOV— Schedule of Values — contract breakdown by work typeBurden rate— Labor overhead multiplier (taxes, insurance, benefits)Earned value— Budget × % completeRetention— Payment held until completion (typically 10%)Budget coverage— Estimated budget as % of contract value — healthy projects run 88–110%Good luck. Time starts now.