Insurtech MGA Reduces Contract Processing Costs by 90% and Achieved 95% AI Extraction Accuracy
Case Study
Insurtech MGA Reduces Contract Processing Costs by 90% and Achieved 95% AI Extraction Accuracy
About the Client
Our client is a US-based insurtech organization operating as a Managing General Agent (MGA) platform across multiple commercial insurance programs.
The company manages complex contractual relationships involving MGAs, carriers, underwriting programs, products, territories, and compliance obligations. Its operations depend heavily on large volumes of insurance agreements, endorsements, amendments, underwriting guidelines, and coverage documents that drive underwriting, sales, governance, and compliance workflows.
As contract volumes increased, our client needed a more scalable way, through AI integration and adoption, to structure, manage, and operationalize the intelligence locked inside these documents.
Business Challenge
Our client managed large volumes of highly detailed MGA agreements, endorsements, underwriting guidelines, amendments, exclusions, and territory-specific clauses.
Critical business information was buried within lengthy, unstructured insurance agreements that frequently exceeded 100 pages and evolved continuously through amendments, renewals, and guideline revisions. The data inside the documents drove decisions across sales, underwriting, and compliance, yet none of it was structured, stored, or queryable.
Each contract was read, interpreted, and manually extracted by trained resources who spent several hundred hours a month.
AI Adoption for Document Intelligence
The issue our client faced wasn’t limited to extracting text from PDFs using LLMs. They wanted visibility into the economics of production-scale AI before committing to deployment. Token usage, infrastructure sizing, model costs, and document processing expenses all needed to be validated upfront.
The contracts contained highly variable insurance language, amendment relationships, nested clauses, and multiple versions of the same contractual obligations. Traditional extraction approaches could not reliably structure the information without losing context.
The obvious answer was AI, yes. But that opened a different can of worms.
- What would it cost to run the solution in production?
- How could token consumption be accurately forecasted at production?
- What infrastructure capacity would be required at scale?
- How could compliance teams validate and audit extracted data?
- How could every extracted data point be explained, cited, and verified?
As long as contract data lived only in PDFs, our client could not build reliable downstream intelligence. Sales teams could not query coverage details. Underwriting could not access historical terms. Compliance had no audit trail. The platform was sitting on a goldmine of structured intelligence locked inside documents that no system could read.
Our client faced four compounding problems with no clear path forward
MGA insurance contracts
100+ page documents · monthly amendments · 40+ business-critical attributes locked inside
Manual processing at scale
Each contract required 4+ hours to review.100+ contracts monthly = 800+ person-hours.
Volume was growing with no ceiling in sight.
Unpredictable AI costs
Early tests cost ~$20 per contract.Token usage in production couldn’t be forecast.
No cost model meant no deployment approval.
Financial risk made scaling impossible.
Compliance explainability gap
Insurance is a regulated environment.Every extracted value needed a citation — page-level, clause-level, section-level.
Uncited AI outputs were unusable in audits.
No production integration path
New contracts and amendments arrive daily.AI had no connection to live workflows.
Underwriting and sales ran on separate rails.
No pipeline meant results stayed siloed.
Trigent Solution
Trigent approached the engagement as an AI cost validation and production engineering exercise, limited not only to document and contract intelligence.
We began by first analyzing the client’s existing contract ecosystem, including MGA agreements, amendments, underwriting guidelines, exclusions, and territory-specific documents. Our team studied how information moved across underwriting, compliance, sales, and governance workflows and identified the exact contract attributes required downstream.
Our team standardized more than 40 business-critical contract attributes, including underwriting rules, carrier information, product definitions, amendment histories, clause language, territorial restrictions, and eligibility conditions. A relational data structure was created to preserve relationships between contracts, amendments, clauses, and downstream operational entities.
During the evaluation phase, we tested multiple AI approaches and hyperscaler platforms against real 90–100-page MGA contracts.
Benchmarking Hyperscaler AI Solutions
Azure AI Foundry and AWS Bedrock were evaluated first using agentic workflows and commercially available LLMs. While both platforms demonstrated acceptable early extraction capabilities, several production limitations became clear during testing:
- Extraction accuracy remained below production thresholds.
- Processing times exceeded operational requirements.
- Source citation capabilities were limited.
- Long-form contracts created large token consumption patterns.
- Document processing costs escalated quickly during scaling tests.
Validating The AI Economics
The initial AI workflows our client used processed contracts at nearly $20 per document during evaluation. It became apparent that processing costs could increase rapidly across large contract volumes without tighter orchestration and token optimization.
Trigent then shifted the evaluation framework to ArkOS AI Workbench to gain greater flexibility across models, orchestration logic, prompt engineering, and workflow routing.
Using ArkOS, Trigent benchmarked multiple frontier models against the complete 40-attribute extraction workload. Each model was evaluated on:
- Extraction accuracy.
- Token efficiency.
- Cost per contract.
- Reliability across complex amendment structures.
- Long-document processing behavior.
Trigent’s AI team evaluated multiple Frontier Models that were commercially available at that time and documented the performance in terms of its accuracy and cost involved to process a given contract document. The findings after testing multiple LLMs are detailed below:
| Frontier Model | Data Extraction Accuracy % | Speed | Comparative Cost |
|---|---|---|---|
| Llama 3.2, 3.3 | Average - 85% | Slow | Low |
| Qwen 2.5 | Average - 80% | Very Slow | Low |
| DeepSeek R1 / V3 | Poor - <70% | Slow | Low |
| Claude 4.5 Sonnet | Very Good - 95% | Fast | Very High |
| Open AI GPT 4o mini | Poor - <70% | Average | Low |
| Open AI GPT nano | Poor - <70% | Average | Low |
| Open AI GPT 5 nano | Average - 82% | Average | Medium |
| Open AI GPT 5.1 | Good - 89% | Fast | High |
| GPT 5.2 (Selected) | Very Good - 95% | Fast | Medium |
OpenAI GPT 5.2 ultimately delivered the strongest balance between extraction accuracy and processing economics.
Engineering a Multi-Agent Architecture for Scale
Even with the right model selected, processing performance remained a challenge initially.
Early single-agent workflows forced the model to process entire 90–100-page contracts sequentially. This increased token usage, slowed processing times, and introduced contextual inefficiencies because the model was analyzing large sections of irrelevant information during every extraction cycle.
To solve this, Trigent redesigned the system around a specialized multi-agent architecture.
Instead of using a single extraction workflow, the platform deployed dedicated AI agents responsible for specific contract functions such as:
Contract classification
Amendment reconciliation
Company and carrier extraction
Clause extraction
Product extraction
Underwriting guideline extraction
Contract-level metadata processing
Each agent processed only the sections of the contract relevant to its responsibility.
This architectural shift fundamentally changed the platform’s economics and reliability.
By narrowing context windows and reducing unnecessary token processing:
- Contract processing time dropped from 4 hours to roughly 15 minutes.
- Token consumption reduced by nearly 40%.
- Hallucinations were eliminated in production workflows.
- Extraction accuracy increased to 95%.
- Document processing costs dropped from nearly $20 to approximately $2 per contract.
Trigent then optimized the platform further through specialized prompt engineering and workflow refinement.
Building Explainable, Audit-Ready AI Workflows
Each agent was equipped with custom prompts tailored to specific insurance extraction tasks, amendment logic, and clause interpretation requirements. The system was also designed to preserve full source traceability, allowing every extracted field to map directly back to the originating contract language and page reference.
The final solution delivered a production-grade contract intelligence platform capable of transforming large unstructured insurance agreements into structured, queryable, audit-ready business data while maintaining predictable operating economics at scale.
Client Benefits
The solution delivered measurable improvements across processing speed, operating costs, extraction accuracy, and AI efficiency.
Client Benefits
- Reduced contract processing time from 4 hours to approximately 15 minutes per document.
- Eliminated more than 400 hours of monthly manual extraction and validation effort.
- Reduced dependency on manual document review workflows.
Cost Savings
- Reduced document processing costs from approximately $20 per contract during early AI evaluation to nearly $2 per contract in production.
- Lowered monthly operating costs from roughly $11,500 in manual effort to approximately $700 in AI infrastructure and LLM costs.
- Delivered monthly savings of nearly $10,800.
- Generated annual operational savings exceeding $130,000.
AI Optimization
- Reduced token consumption by nearly 40% through the multi-agent architecture.
- Improved processing efficiency by limiting each agent to task-specific contract sections.
- Established predictable AI operating economics for production-scale deployment.
Extraction Accuracy and Scale
- Achieved 95% extraction accuracy across more than 40 contract attributes.
- Eliminated hallucinated outputs in production workflows.
- Generated more than 40,000 structured records within the first month of deployment.
- Processed 90 contracts across 9 MGAs during the initial production rollout.
Technology Stack
