Bid Reasoner reads each sub's bid PDF, normalizes the line items to your scope, and scores all 5–15 bidders across price, scope, schedule, compliance, performance, and risk. Pick a winner under any of 7 decision modes, see the evidence behind every score, and auto-generate the award memo that holds up when the owner asks why.
| Bidder | As-submitted | AI overall score | Top finding | Risk score |
|---|---|---|---|---|
| RECSlate Hill Constructors | $6,934,048 | 0.78 | 15 unbalanced unit prices @ $1.00 | 0.35 · Med |
| Vector Construction | $7,759,264 | 0.65 | 9 unbalanced unit prices @ $1.00 | 0.35 · Med |
| Kubricky-Jointa Lime | $8,197,940 | 0.59 | 8 unbalanced unit prices @ $1.00 | 0.40 · Med |
Every adjustment is labeled. Every projection shows its work. Your senior estimator can still argue with it — that's the point.
Per-package recommendation page with AI bidder evaluations across six dimensions, reasoning evidence backed by quotes from each PDF, click-to-explain confidence scores, and a what-if challenge box. Switch between seven decision modes to see how price-priority vs risk-priority changes the winner.
When you award against the AI's recommendation, an override category and reason are required — not optional. Every disagreement creates a permanent audit record. When an owner asks "why this bidder?" six months later, the answer is one click away.
Seven Word document types — Reasoned Award Memo, Bid Reasoning Report, Evidence Report, Bidder Scorecard, Executive Summary, Clarification Recommendations, Project Handoff Rationale — populated from the underlying data. Real .docx, not screenshots.
Not opaque AI: unbalanced unit prices (≤ $1.00), peer outliers (>2× or <0.5× peer median), total-bid outliers (>20% deviation), and front-loaded mobilization (>10% of total). Click any chip to filter the matrix to those flagged items.
Deep-dives into the parts of the workflow heavy-civil GCs search for by name.
Normalize 5–15 mixed-format subcontractor bids to your scope and make every bidder apples-to-apples.
Put every bidder side-by-side in one ranked matrix — sort by price, scope, schedule, or risk.
Auto-build the bid tab straight from the sub bid PDFs — no more hand-keyed Excel.
Score every bidder across six dimensions, with page-cited evidence and four deterministic risk flags.
Find the items nobody quoted — and the scope creep — across every bid, before you award.
Auto-generate the reasoned award memo and audit trail that defend your subcontractor pick.
The sub-bid evaluation layer of precon — it complements HeavyBid and B2W, not replaces them.
Level the sub bids on your state-DOT projects in any US state — every bidder normalized against peer median, no government data required.
Built for GCs receiving sub bids on bridge, highway, tunnel, and transit packages — where scope is contested, bids run 5–15 deep per package, and bid day matters.
Works in any U.S. state on day one — every bidder is normalized against the peer median of your own bids, so no government data is required to start. Government pay-item baselines are already built in for New York and New Jersey, with more states added as partners come online. Reasoning, scoring, evidence, and the override audit trail work on every project, regardless of state or code system.
Bid Reasoner is live in private beta with a hand-picked group of heavy-civil general contractors. Founding partners get introductory pricing, founder-direct support, and direct influence on what the model learns from their team's decisions. Once the cohort is full, the founding rate goes away.