The problem
Construction bids depend on reading blueprint sets and coordinating quantities and costs across trades.
← Selected work
Construction tech
Build IG
QPOI built Build IG's estimation engine and project workflows. The platform turns blueprint PDFs into estimates that teams can review and edit, then uses those figures across quotations, bid packages, contracts and project budgets.
- Client
- Build IG
- Platform
- Web
- Stack
- Angular / .NET
- Duration
- Ongoing
- Engagement
- End-to-end architecture
- Status
- In production
The project at a glance
What QPOI delivered
QPOI built the analysis engine, estimate review tools and connected project workflows, so reviewed figures carry through to quotes, contracts and budgets.
Delivery evidence
In production. A documented analysis run fell from 23 to 12 minutes before human review; this measures processing time, not total estimating time.
Document analysis pipeline, as builtView diagramHide diagram
1.0
The challenge
Preparing a construction bid means reading blueprint sets, calculating quantities and coordinating costs across multiple trades. The client needed to reduce that manual work while keeping the estimate open to review and correction.
The challenge extended beyond generating an initial estimate. When a reviewer changed a quantity, product or rate, the resulting quotes, contracts and budgets needed to stay aligned. Reviewers also needed to see which reports required regeneration.
2.0
The AI estimation engine
QPOI built the pipeline, its background processing and the review tools used to check generated estimates before preparing a bid.
2.1
Blueprint to complete estimate
The pipeline analyses blueprint PDFs across 16 trades, producing material quantities, labour breakdowns and combined costs. Later stages prepare schedules, supporting reports and quotation documents for review.
2.2
Parallel pipeline architecture
Independent trade analyses run in parallel; stages that depend on their results run afterwards. In the documented comparison, runtime fell from 23 minutes to about 12. All 32 stages and 16 trades completed, with the material total within 0.1% of the sequential baseline.
2.3
Deterministic numbers, AI at the edges
Reviewed quantities and costs live in a shared estimate store. Line-item edits recalculate totals in code and update the documents that use them. Specification changes can also update contract wording, with ambiguous text matches skipped to avoid changing the wrong item.
2.4
Human review built in
Reviewers can compare estimate versions, replace individual items and see which reports an edit has made out of date. A refresh regenerates the affected reports without rerunning the whole analysis.
3.0
Wider platform engineering
Beyond the engine, QPOI built the platform around it: the systems that turn an analysis pipeline into a product construction teams use every day.
Real-time infrastructure
SignalR / dual-channel streaming
Designed and built the real-time layer: two SignalR hubs, one broadcasting analysis progress and workflow status, the other streaming AI responses token by token, so users watch long-running operations instead of waiting on them.
Performance engineering
Query profiling / request coalescing / Web Workers
Profiled and rebuilt the hot paths on both sides of the wire: a heavy calendar session went from 654 backend queries to 254, and the estimation screen from 53 API calls to 27. Request coalescing and caching on the frontend, identity-resolution caching on the backend, and Web Workers keeping report compilation off the main thread.
Marketplace and geo search
SQL Server spatial / Google Maps clustering / RxJS
Built the subcontractor marketplace: map-based search and filtering over live job data using SQL Server geography types and clustered Google Maps rendering, so trades find relevant work near them.
Enterprise team architecture
RBAC / seat management / tokenized onboarding
Designed and built team-based access: roles and seat management aligned to how construction companies actually operate, with tokenized invitation flows for workspace onboarding.
Bid packages and contracts
Trade packages / AI-drafted contracts
Per-trade bid packages generated from the estimate, trade award flows, and AI-drafted contractor-client contracts that stay consistent with the reviewed takeoff figures instead of quoting stale numbers.
Budget, timeline, and assistant
Budget sync / scheduling / AI chat
Budget tracking synced from the takeoff, timeline and task scheduling with a project calendar, and an in-app AI assistant that answers questions over the project's own context.
4.0
Delivery and measured improvements
- The documented analysis run fell from 23 minutes to about 12, before human review
- Shared estimate figures support updates across quotes, contracts, budgets and reports
- The measured calendar session used 254 backend queries instead of 654; estimation API calls fell from 53 to 27
- Delivered end-to-end and in production: AI pipeline, frontend, backend, real-time, and team infrastructure
Behind the build / Engineering notes
How it works, in detail
The pipeline stage by stage, how the parallelisation proved it kept the same numbers, and the faults the validation gates caught before users could.
Built with
- .NET Core 8
- Angular 16+
- Google Gemini
- Azure Cloud
- SignalR
- SQL Server
- Hangfire
- RxJS
- Web Workers
- Docker
- CI/CD Pipelines
Next project
Voice Sales Assistant