How One Restoration Firm Clawed Back $500 a Proposal

A restoration CEO bottled his negotiation playbook into an AI that compares insurance docs in minutes — freeing 30% of his executives' week and recovering $500 more per deal.

30%

Freed in executive leadership time

2–4 months

Implementation Time

Jack Weissenberger

Co-founder & CTO

Ciridae

Connect ↓

The Challenge

A home restoration firm's CEO and COO were personally spending three hours on every proposal review — comparing contractor estimates against insurance adjustments line by line, hunting for discrepancies worth negotiating. The process consumed 20 to 30 percent of their combined executive time. Deals that required multiple review rounds lost momentum and sometimes clients. The bottleneck wasn't fieldwork. It was paperwork sitting on the desks of the two people who could least afford to be doing it.

What They Built

Ciridae spent time on-site with the team before writing a line of code — encoding the CEO's negotiation expertise as structured rules the system could apply at scale. The resulting AI pipeline ingests both documents, classifies every line item, flags discrepancies, and produces an annotated comparison document in minutes. Human review happens before negotiation, not instead of it. The system deployed in 48 hours. Outcomes surprised even the client: the AI identified discrepancies more accurately than humans 10% of the time, and average recovery per proposal increased by approximately $500 — with projected enterprise value running into the millions.

Ciridae began with on-site discovery at the restoration firm — time spent understanding the specific negotiation logic the CEO applied when reviewing proposals before encoding it as structured AI-executable rules. This knowledge-capture step was the foundational work that made downstream automation possible. The pipeline was built to ingest two document types simultaneously: contractor estimates and insurance adjustment documents. Every line item is classified, and the system applies the encoded negotiation rules to flag discrepancies — items where the contractor's scope and the insurer's adjustment diverge in ways worth challenging. The output is an annotated comparison document ready for human review before negotiation, not instead of it. The full solution deployed in 48 hours using the Ciridae platform, integrating Claude, OpenAI, and Gemini models. The system immediately outperformed the prior manual process — identifying discrepancies with greater accuracy than human review 10% of the time — and recovered an average of $500 more per proposal from the first week of use.

AI Role

Claude, OpenAI, and Gemini models work within the Ciridae platform pipeline to ingest contractor estimate and insurance adjustment documents, classify every line item, identify discrepancies between them, and produce an annotated comparison document. The AI applies the CEO's encoded negotiation expertise as structured rules, surfacing recoverable dollars the manual process was missing.

AI Model

Claude

Infrastructure

Ciridae Platform (cloud-hosted document ingestion and classification)

Integration Points

Multi-model AI orchestration via Ciridae Platform (Claude, OpenAI, Gemini called per task)

Impact

30% of Leadership Time Freed

The CEO and COO reclaimed 20–30% of their combined executive time, previously consumed by manual line-by-line proposal comparisons that now happen automatically.

10% More Accurate Than Humans

The AI pipeline identified proposal discrepancies with greater accuracy than manual human review, catching recoverable dollars that the previous process was leaving behind.

~$500 More Per Proposal

Average recovery per proposal increased by approximately $500, with the cumulative impact projected to significantly multiply the firm's enterprise value over time.

Technology Utilized

Implementation Complexity

Cost Reduction

Time Savings

Revenue Growth

The solution required translating the CEO's negotiation expertise into structured, AI-executable rules — a knowledge-encoding step requiring deep domain collaboration before any code was written — followed by building a document ingestion and classification pipeline integrating multiple AI models through the Ciridae platform. The domain-specific knowledge encoding adds meaningful complexity beyond a generic document comparison tool.

Best Fit For

Home restoration firms, contractors, and insurance-adjacent service companies where proposal reconciliation against adjustments is a recurring, manual executive burden.

Jack Weissenberger

Co-founder & CTO

Ciridae

CTO and Cofounder at Ciridae, delivering AI-native workflow automation and enterprise transformation for mid-size and complex operators across finance, operations, and home services sectors.

Connect with the Expert

Industry:

Construction & Engineering

Insurance

Business Function:

Operations

Finance & Accounting

Company Size:

1-50

Project Cost:

Cost not disclosed

Ownership:

Founder-Owned

Organization Type:

Private Company

AI Pattern:

Document Processing & Extraction

Decision Support & Scoring

Process Automation (RPA + AI)

Value Type:

Cost Reduction

Time Savings

Revenue Growth

AI Model:

Claude

Frequently Asked Questions

How did a small home-services firm reclaim $500 per proposal with document-processing AI?

The experts spent time on-site capturing the CEO's negotiation logic and encoding it as structured, AI-executable rules before building anything. The pipeline ingests contractor estimates and insurance adjustment documents together, classifies every line item, applies the encoded rules to flag discrepancies worth challenging, and produces an annotated comparison for human review before negotiation. It recovered an average of $500 more per proposal from the first week.

What AI tools and models were used at the home-services firm?

The solution was built on the experts' own platform, integrating Claude, OpenAI, and Gemini models, with the CEO's negotiation expertise encoded as structured rules the system applies at scale. The approach combined document processing, decision support and scoring, and process automation.

What results did the home-services firm achieve?

The firm recovered about $500 more per proposal, the CEO and COO reclaimed 20–30% of their combined executive time previously lost to manual line-by-line comparison, and the AI identified discrepancies more accurately than human review 10% of the time.

How long did the deployment take?

The full solution deployed in 48 hours.

Who is this document-processing AI approach best for?

Home restoration firms, contractors, and insurance-adjacent service companies where reconciling proposals against adjustments is a recurring, manual executive burden.