QuoteerAI

QuoteerAI turns electrical RFQs into structured, auditable quotations using Gemini-powered extraction, engineering review, catalogue matching, pricing, and human approval.

Comment

Inspiration

QuoteerAI began with a problem I know firsthand as an electrical engineer and the owner of Albadr Electric.

Preparing a professional electrical quotation is rarely just a matter of entering prices. A real RFQ or BOQ may contain incomplete descriptions, technical specifications, catalogue references, quantities, units, and commercial requirements. Engineers must interpret these requirements, match them against suitable products, verify technical compliance, source missing items, apply pricing rules, obtain approvals, and finally produce a customer-ready quotation.

Much of this work is still fragmented across spreadsheets, PDFs, catalogues, price lists, email, and manual engineering judgment.

QuoteerAI was built to bring that entire workflow into one AI-native system.

What it does

QuoteerAI transforms electrical RFQs into structured, auditable quotation workflows powered by Gemini.

The workflow includes:

  • Catalogue and price-list ingestion
  • Gemini-powered RFQ and BOQ extraction
  • Structured engineering line-item creation
  • Human engineering review and correction
  • Domain-aware catalogue matching
  • Manual sourcing when no suitable match exists
  • Pricing and price-history workflows
  • Commercial review and approval controls
  • Auditability of engineering and commercial decisions
  • Final quotation generation in PDF and Excel formats

The system is designed around human control. Gemini assists with extraction, interpretation, and workflow acceleration, but engineering and commercial authority remain with the human user.

How we built it

QuoteerAI was developed as an AI-native product around the real workflow of an electrical supply business.

Gemini is used inside the live application to interpret technical request data and convert unstructured customer requirements into structured engineering information. The resulting data then moves through human review, matching, pricing, approval, and quotation generation.

The application also supports engineering source data such as electrical catalogues and commercial price lists, allowing product information and pricing information to become part of the same controlled quotation workflow.

The current macOS application demonstrates the complete path from source data and RFQ ingestion through final commercial quotation output.

Challenges

One of the main challenges was designing the system so that AI could accelerate engineering work without silently replacing engineering judgment.

Electrical products cannot be treated as generic text records. Lighting, cables, circuit breakers, panels, wiring devices, and other domains have different technical attributes and matching logic.

Another challenge was maintaining traceability across extraction, engineering review, sourcing, pricing, approvals, and final quotation generation while keeping the workflow usable for a small business.

What we learned

The most important lesson was that AI becomes much more valuable when it is embedded into a real operational workflow rather than used only as a standalone assistant.

For professional engineering work, the combination of AI automation, domain knowledge, structured data, and human control is more important than any single model response.

What's next for QuoteerAI

QuoteerAI began inside Albadr Electric, but the goal is to develop it into a commercial platform for electrical contractors, distributors, suppliers, engineering offices, and other small businesses that depend on accurate and fast quotation workflows.

The long-term vision is to make professional engineering quotation capability more accessible to smaller companies while creating new opportunities around AI-assisted engineering, catalogue intelligence, sourcing, and commercial operations.

Built With

Share this project:

Updates