Scoreboard AI
Eliminates the manual scope review that costs general contractors change orders and competitive bids
scoreboardai.netProduct Overview
What It Is
Scoreboard AI automates scope buyout and procurement for commercial general contractors, turning thousands of pages of plans and specs into trade-by-trade scope inclusion packages that can be sent straight to subcontractors.
The Problem It Solves
Current Approach
After winning a project, a general contractor has roughly a month to convert the estimate into a firm price. That means engaging around 30 subcontractors and soliciting three to five bids per package, with apples-to-apples comparison across them. The workflow is manual: project managers, procurement managers or estimators work through drawings and specs in Bluebeam, mark them up, and rewrite scope into Word or Excel to become the scope exhibit in the subcontract. Most teams do not have time to do this properly, so the shortcut is to hand a subcontractor a division and a set of drawings and push the burden onto them. Subs then either pad their numbers to cover assumptions, making them less competitive, or miss items tucked into the corner of a sheet. Missed items resurface later as change orders the contractor has to eat.
How It Changes
The platform parses every element across the plans, specs and supporting documents, including geotech reports, assigns each item to the responsible trade, and generates a scope inclusions report per bid package. Each line item links back to its source page so reviewers can verify provenance, which is a deliberate guardrail against hallucination. Output can be exported as PDF, CSV, or as a set of highlighted drawings showing only the sheets relevant to that trade.
Area of Focus
Pre-construction, specifically the scope buyout phase between award and firm price. There is adjacent value during design-build, where the revisions feature tracks whether decisions from owner-architect-contractor discussions actually made it into the issued set.
Key Features
Scope inclusions report
Auto-generated per bid package, editable line by line, with each item linked back to its source page in the plans or specs.
Highlighted drawing exports
The system outputs a filtered set showing only the sheets relevant to a given trade. For a signage subcontractor, that means the 12 pages out of 300 they actually need to look at.
Custom reports
Start with pre-built report templates, such as acceptable manufacturers and basis of design, or spec versus drawing discrepancies, or create your own. Pull information from specific locations across the project documents and turn it into clear summaries, side-by-side comparisons, and easy-to-scan reports the team can act on.
Conflict detection
Flags inconsistencies between plans and specs. In the demo, the specs called for basketball backstops on a project where the drawings only showed tennis courts.
Centralized checklist of risk items
A never-get-burned-by-this-again list maintained at company level rather than by individual project manager, so institutional memory does not walk out the door when staff turn over.
Revision management
Upload bulletins, addenda and revised sets, and Scoreboard summarizes additions, removals and changes detail by detail.
Used By
Target Customer Types
Balfour Beatty
$13.6B revenue, 26,000 employees
“”
—
Hawaiian Dredging Construction Company
$1.1B revenue, 900 employees
“”
—
S+B James
$200M revenue, 129 employees
“”
—
Operating Locations
US nationwide, with customers from New York to Hawaii.
Implementation & Onboarding
Setup: drag and drop PDF upload. A 500-page set takes roughly 48 hours to process. Trades and a checklist of common gotchas come configured by default but are fully customizable, and users can submit their own scope matrix for Scoreboard to configure bid packages to match, such as whether Division 26 and Division 27 are bought together or separately, or whether rigid paving sits with concrete or exterior specialties. Onboarding: a one-week free trial. Drawings uploaded Monday, system configured by Wednesday, a mid-week check-in Friday, and wrap-up the following Tuesday. Customization: trade definitions are fully configurable. A standard inclusions upload, so the system can suppress generic items already covered by the contractor's boilerplate and surface only job-specific scope, was on the near-term roadmap at the time of the demo.
Security & Privacy
ROI & Value
Direct time savings
Measured by what percentage of generated inclusions customers accept directly into their invitations to bid.
Risk reduction
Measured by errors and scope gaps caught before they become change orders.
Founding Team
Charles Ma, P.E.
CEO and Co-Founder
A construction problem solver and structural engineer with an MS from UCLA. Charles helped build a construction technology startup from bootstrap to an $80M Series B as employee number one, owning everything customer-facing. He has a knack for listening between the lines and mapping problems to solutions, describes himself as a lifelong learner, and believes relationships make life meaningful.
LinkedIn
Serafim Sukhenkiy
CTO and Co-Founder
A founding engineer with more than 20 years building products from zero to scale. Serafim writes the code, shapes the architecture, deploys the infrastructure and ships, scaling teams when needed and making the hard calls when it matters. He has deep experience across full stack with Python, Django, React and Next.js, machine learning including vision models, document understanding and transformers, and LLM-based systems covering agents, retrieval-augmented generation and tool use. His technology decisions start with customer problems rather than tickets.
LinkedInFunding
Total Raised
Undisclosed
About the Company
Roadmap
Near-term: a standard inclusions upload to suppress boilerplate and improve relevance, particularly for larger trades. Visual revision reports, moving from the current text summary to a click-through visual format matching the scope inclusions experience. Export in customer template format, to remove copy-paste into invitation-to-bid documents. Medium-term: Procore, ACC and Egnyte integrations on ingestion, and Procore and Building Connected integrations on output. Longer-term: today's product is text-heavy, and the team is building visual understanding capabilities covering symbols, drawing elements and diagrammatic content, using proprietary models trained from scratch. Work previously sized as 12 to 18 months out is now 1 to 2 months out, attributed to the acceleration that comes from training their own models rather than fine-tuning.
Defensibility
The model training trajectory is the stated moat, moving from fine-tuning to fully proprietary purpose-built models, with a data flywheel from customer document ingestion. The construction-specific scope ontology and the verifiable source-of-truth linkage, which is harder than it looks to do reliably, are the operational moats.
Pricing
Usage-based, structured to reduce adoption friction. General contractors pay $5 per drawing sheet and $0.10 per spec sheet. Specialty contractors pay $2 per drawing sheet and $0.10 per spec sheet.