Resources for Modern Underwriting Teams

Agentic AI has the potential to change commercial insurance underwriting by allowing artificial intelligence to do more than answer questions or summarize documents. AI agents can work toward defined objectives, gather information, use approved tools, evaluate conditions, and help move underwriting workflows forward.

But giving AI more autonomy introduces a fundamental challenge.

An AI system that can act needs to understand the context behind the information it is using.

Commercial P&C underwriting is not simply a document-processing problem. Underwriters make decisions based on relationships between businesses, locations, exposures, classifications, losses, coverages, limits, appetite rules, historical information, and external risk signals.

A general-purpose AI model may be highly capable at reading language while still lacking the specialized commercial insurance knowledge required to interpret those relationships reliably.

This is why insurance-specific risk context is becoming increasingly important as carriers and MGAs explore generative AI, AI agents, and more autonomous underwriting workflows.

The question for underwriting leaders is no longer simply:

Which AI model should we use?

A more important question is:

What information and insurance context is that model grounded in when it supports an underwriting decision?

What Is Insurance-Specific Risk Context?

Insurance-specific risk context is the structured information that helps an AI system understand what commercial insurance data means and how different pieces of information relate to one another.

A commercial submission might contain:

• Named insured information

• Business descriptions

• Industry classifications

• Revenue

• Payroll

• Locations

• Property characteristics

• Vehicles

• Employees

• Loss history

• Limits

• Coverages

• Supplemental risk information

Simply extracting these values does not necessarily create underwriting intelligence.

The system also needs to understand the relationships between them.

For example, an address might represent:

• Corporate headquarters

• A mailing address

• An insured property

• A warehouse

• A manufacturing location

• A construction project

Those distinctions can materially affect the underwriting analysis.

Similarly, a loss record only becomes useful when the system understands which insured, location, exposure, and policy period it relates to.

Insurance-specific context gives AI the structure required to interpret those relationships.

Why General-Purpose AI Is Not Enough for Commercial Underwriting

General-purpose large language models are trained to understand and generate language across an enormous range of subjects.

That makes them powerful tools for:

• Summarization

• Drafting

• Search

• Question answering

• Document interpretation

• Conversational interfaces

However, fluency should not be confused with underwriting expertise.

Commercial underwriting contains specialized terminology, classifications, data structures, and relationships that may not be obvious from the text alone.

Consider a submission describing a business as:

Commercial painting contractor.

A general-purpose AI model may understand what painting is.

An underwriting system may need to understand considerably more:

• Does the business perform interior or exterior work?

• Does it work at height?

• Does it perform industrial painting?

• Does it work on bridges or infrastructure?

• Are employees using scaffolding?

• Does it subcontract work?

• Which classification is appropriate?

• Which exposures matter for the requested coverage?

These questions require insurance context.

The model needs more than a dictionary definition of the business.

It needs to understand how that business description connects to commercial P&C risk evaluation.

Convr’s current Risk Context Engine positioning reflects this distinction. The company describes its RCE as a commercial P&C-specific knowledge graph and semantic ontology designed to ground AI underwriting in structured insurance context rather than relying solely on general-purpose model inference. (convr.com)

Agentic AI Raises the Importance of Context

The need for contextual grounding becomes more important as AI takes on a more active role.

Consider two uses of AI.

AI Assistant

An underwriter asks:

Summarize the information in this submission.

The AI produces a summary.

The underwriter reviews it and decides what to do next.

AI Agent

The agent is given an objective:

Evaluate whether this submission fits appetite and determine the appropriate next workflow step.

The AI may need to:

1. Interpret the submission.

2. Identify the business.

3. Determine relevant exposures.

4. Gather additional information.

5. Compare the risk against underwriting criteria.

6. Identify missing data.

7. Determine whether referral is required.

8. Route the account.

The second scenario carries more responsibility.

The AI is not merely producing text.

It is using information to influence what happens next.

If the underlying context is wrong, the workflow decision can also be wrong.

Agentic AI Needs Grounding, Not Just Intelligence

Grounding connects an AI system to trusted information that can support its responses and actions.

For underwriting, grounding may include:

• Original submission documents

• Structured risk information

• Carrier guidelines

• Internal underwriting data

• Historical account information

• Approved external data

• Classification structures

• Authority rules

• Insurance-specific knowledge models

Without grounding, the AI may rely too heavily on general model knowledge or inference.

That creates a problem because underwriting decisions frequently depend on organization-specific information.

An AI agent should not invent a carrier’s appetite.

It should use the actual appetite criteria it has been authorized to access.

It should not guess which exposure applies to a particular location.

It should use structured information that connects the location with the relevant risk.

It should not assume a requested limit falls within an underwriter’s authority.

It should evaluate the applicable authority rules.

Grounding turns an AI model from a general source of language intelligence into a tool capable of operating within a specific underwriting environment.

What Is a Knowledge Graph in Commercial Insurance?

A knowledge graph represents information as connected entities and relationships.

Instead of storing every piece of information as an isolated field, a graph can show how information relates.

A simplified commercial risk might contain relationships such as:

Named Insured

↓

Operates

↓

Business Activity

↓

At

↓

Location

↓

Associated With

↓

Exposure

Losses, policies, classifications, and other information can also be connected to the appropriate entities.

This structure is useful for AI because commercial underwriting depends heavily on relationships.

An underwriter does not simply ask:

What addresses appear in the submission?

They need to know:

Which locations represent insured exposures?

They do not simply ask:

What losses exist?

They need to understand:

Which operations or exposures generated those losses?

A knowledge graph can help preserve that context.

Convr currently positions its Risk Context Engine around this architecture, combining a commercial P&C knowledge graph, ontology, schema, and semantic layer to create a normalized view of risk information used across its underwriting capabilities. (convr.com)

What Is an Insurance Ontology?

An ontology defines concepts and relationships within a particular domain.

For commercial insurance, that domain may include concepts such as:

• Business

• Insured

• Exposure

• Location

• Classification

• Loss

• Coverage

• Limit

• Building

• Vehicle

• Employee

The ontology helps the system understand what those concepts represent and how they relate.

This becomes particularly useful when different data sources describe the same thing differently.

For example, one source might use:

Annual sales

while another uses:

Annual revenue

The system needs to determine whether those fields represent the same concept within the underwriting context.

Similarly, multiple classification systems may describe a business using different codes or terminology.

A domain-specific ontology can help normalize those differences into a more consistent representation.

Semantic Understanding Helps Connect Fragmented Submission Data

Commercial insurance data rarely arrives through one clean database.

A submission may include:

• PDFs

• Emails

• Spreadsheets

• ACORD forms

• Loss runs

• Statements of values

• Supplemental applications

• Third-party data

The same risk may be represented differently across those sources.

A semantic layer helps connect information based on its meaning rather than relying only on identical field names.

This matters because an AI agent may need to evaluate information from several sources before determining what should happen next.

If the data remains fragmented, the AI risks treating related information as separate facts or failing to identify important relationships.

Convr’s underwriting architecture unifies structured and unstructured submission data into a normalized commercial insurance model, which then supports AI, analytics, and underwriting workflows. (convr.com)

Risk Context Can Help Detect Conflicting Information

Grounding is not only about finding information.

It can also help identify when information disagrees.

Suppose a submission contains:

Application revenue: $15 million

Financial statement revenue: $22 million

A simple extraction system might successfully extract both values.

But the underwriting problem is not extraction.

The problem is determining that there is a discrepancy that may need investigation.

The same issue can occur when:

• Business descriptions differ

• Named insureds do not match

• Locations appear inconsistently

• Classifications conflict

• Loss totals differ

• Employee counts vary between sources

An AI system with stronger contextual understanding can surface these conflicts rather than simply presenting multiple values.

That allows the workflow to pause or escalate when information needs human review.

Traceability Matters as AI Becomes More Autonomous

If an AI system only generates an internal summary, an underwriter can independently verify the information.

If the system begins influencing triage, referrals, appetite decisions, or workflow routing, traceability becomes much more important.

The user should be able to determine:

• Where the information came from

• Which source contained it

• Which data point influenced the action

• Which rule was applied

• Why the system reached its conclusion

For example, an AI agent might state:

Referral required because the requested limit exceeds configured authority.

The underwriting team should be able to inspect:

• The requested limit

• Its original source

• The applicable authority threshold

• The workflow rule

• The resulting action

That is very different from receiving an unexplained recommendation from a black-box model.

Convr’s RCE and MCP positioning emphasizes this concept by making underwriting context available to AI agents while preserving source traceability for the information returned. (convr.com)

Explainability and Traceability Are Not the Same Thing

These concepts are related but distinct.

Explainability

Explains why the system reached a conclusion.

For example:

This risk requires additional review because the exposure falls outside standard appetite criteria.

Traceability

Shows the information that supports that conclusion.

For example:

• Original business description

• Classification

• Exposure information

• Applicable appetite rule

• Source document

An AI system may produce a convincing explanation without having strong traceability.

For underwriting organizations, both matter.

The conclusion should make sense, and users should be able to inspect the evidence behind it.

Insurance-Specific Context Can Support More Consistent Decisions

Commercial carriers often have large underwriting teams operating across:

• Regions

• Offices

• Distribution channels

• Lines of business

• Experience levels

Two underwriters can interpret the same information differently.

Human judgment is an important part of underwriting, but inconsistency in routine data interpretation or guideline application can create unnecessary variability.

Insurance-specific AI can help create a more consistent foundation.

For example, the system can help ensure that:

• The same risk data is interpreted consistently

• Classifications are evaluated against the same framework

• Relevant information is surfaced systematically

• Mandatory referral conditions are checked

• Source information is preserved

The goal is not to eliminate underwriting judgment.

It is to give underwriters a more consistent information layer on which to apply that judgment.

The Underwriter Still Owns the Decision

A stronger contextual foundation does not mean every underwriting decision should become autonomous.

Commercial risks can involve nuance that is difficult to reduce to a universal set of rules.

An experienced underwriter may consider:

• Broker knowledge

• Management quality

• Loss explanations

• Risk controls

• Market conditions

• Strategic account value

• Coverage structure

• Pricing considerations

Insurance-specific AI can organize the evidence and automate repeatable checks.

The underwriter can then focus on interpreting what the evidence means.

This represents an important principle for agentic underwriting.

The more effectively technology manages context, data gathering, and repeatable workflow decisions, the more attention human underwriters can give to the areas where professional judgment creates the greatest value.

AI Grounding Is Becoming an Underwriting Infrastructure Question

As insurers evaluate AI, attention naturally goes to the models themselves.

Which model is most accurate?

Which model is fastest?

Which model can handle the largest documents?

Those questions matter.

But commercial underwriting AI also depends on what surrounds the model.

Underwriting leaders increasingly need to consider whether their AI environment can:

• Understand insurance concepts

• Preserve relationships between risk information

• Normalize fragmented submission data

• Connect to approved sources

• Apply carrier-specific rules

• Trace information to its origin

• Support controlled workflow actions

Without those capabilities, increasing AI autonomy may simply increase the speed at which uncertain information moves through the underwriting process.

With the right risk context, agentic AI has the potential to become something much more valuable: a governed decision-support layer that understands the commercial insurance environment in which it is operating.

What Insurance-Specific Context Changes in Practice

Insurance-specific context changes what AI can do with underwriting information.

A general model may be able to summarize a submission. A context-aware underwriting system can connect that information to the concepts, rules, and relationships that matter for the risk.

That can improve several parts of the workflow.

Submission Triage

The system can identify missing information, evaluate whether a submission appears to fit appetite, and determine whether it should proceed, stop, or be escalated.

Risk Enrichment

External information can be connected to the correct insured, location, operation, or exposure rather than added as disconnected data.

Guideline Application

Carrier-specific rules can be evaluated against structured risk information instead of relying on a model to infer what the organization considers acceptable.

Referral Preparation

The system can identify the relevant trigger, gather supporting evidence, and prepare information for human review.

The more active AI becomes in the workflow, the more important this context becomes.

Context Can Help Reduce Hallucination Risk

One of the best-known risks of generative AI is hallucination, where a model produces information that sounds plausible but is unsupported or incorrect.

In underwriting, a model should not invent:

• A business classification

• A loss event

• A property characteristic

• An appetite rule

• An authority threshold

Grounding helps reduce this risk by directing the AI toward trusted underwriting information.

It does not remove the need for governance or human review. It gives the model a stronger evidence base.

For underwriting leaders, the key question is not whether AI can produce a convincing answer.

It is whether the answer can be tied back to trusted commercial insurance data and the rules governing the decision.

Source Lineage Supports Better Governance

Source lineage preserves the connection between a data point and where it originated.

If an underwriter reviews a location-level exposure, they may need to know whether the value came from:

• The application

• A statement of values

• A prior policy record

• An external data source

• A manually entered field

If sources disagree, lineage helps the underwriter understand the conflict.

As AI agents become more involved in referrals, routing, appetite checks, and other workflow decisions, source lineage also makes those actions easier to review and audit.

Context Should Travel With the AI Workflow

Insurance-specific context should not exist inside one isolated application.

Carriers may use several AI models, assistants, and agents across underwriting.

A stronger approach is to make trusted risk context available wherever approved AI workflows need it.

That could include:

• Underwriting workbenches

• Internal AI assistants

• Agentic workflows

• Portfolio analytics

• Decision-support tools

If several AI systems are evaluating the same account, they should not each reconstruct the risk independently from fragmented source documents.

A shared contextual layer can provide a more consistent understanding of the insured and its exposures.

Model Flexibility Matters

The AI model landscape is changing quickly.

Carriers may use different models for different tasks or change providers as capabilities improve.

The commercial insurance context, data relationships, underwriting rules, and source lineage should remain valuable even when the underlying model changes.

The model can provide reasoning and language capabilities.

The underwriting context provides the domain-specific knowledge that makes those capabilities useful.

This creates a more durable AI architecture than tying underwriting intelligence to one model alone.

Human-AI Collaboration Improves When Evidence Is Visible

Insurance-specific context can also improve the underwriter experience.

An underwriter may ask:

Why was this account referred?

A context-aware system should be able to identify the relevant rule and the information that triggered it.

The underwriter might then ask:

Which source provided that value?

The system should be able to show the supporting evidence.

This makes AI easier to challenge, validate, and trust.

The goal is not to remove underwriting judgment. It is to give underwriters stronger information and reduce the manual work required to reach a decision.

A Practical Roadmap for Context-Aware Agentic AI

Underwriting organizations can approach agentic AI in stages:

1. Identify trusted sources for important underwriting information.

2. Normalize concepts such as insureds, locations, exposures, losses, classifications, and coverages.

3. Connect the relationships between those entities.

4. Preserve source lineage back to the original information.

5. Ground AI workflows in relevant risk context and carrier rules.

6. Define which actions agents can take and which require human approval.

7. Start with focused use cases such as triage, risk enrichment, referral preparation, or renewal review.

8. Measure accuracy, speed, overrides, and underwriter trust before expanding autonomy.

This creates a more controlled path toward agentic underwriting than attempting to automate the entire underwriting process at once.

Frequently Asked Questions

Why does agentic AI need insurance-specific context?

Agentic AI needs insurance-specific context because commercial underwriting depends on specialized concepts and relationships between insureds, locations, exposures, losses, classifications, coverages, and carrier rules. General AI may understand the language without fully understanding its underwriting significance.

What is grounding in insurance AI?

Grounding connects an AI system to trusted underwriting information, such as submission data, carrier guidelines, internal risk information, approved external sources, and structured insurance knowledge. It helps responses and actions rely on evidence relevant to the insurer’s actual environment.

What is a knowledge graph in commercial insurance?

A commercial insurance knowledge graph represents businesses, locations, exposures, losses, policies, and other entities as connected information rather than isolated fields. This helps AI understand how different data points relate to the same commercial risk.

Can insurance-specific context reduce AI hallucinations?

Grounding AI in trusted insurance data can reduce unsupported outputs by giving the model a stronger evidence base. It does not remove the need for validation, governance, or human oversight, particularly for material underwriting decisions.

Why is source lineage important for underwriting AI?

Source lineage allows underwriters to see where information originated and which evidence supported an AI recommendation or action. This helps resolve conflicting data, supports auditability, and builds trust in AI-assisted underwriting.

Give Agentic AI the Commercial Insurance Context It Needs With Convr

The future of underwriting AI will not be determined by model capability alone.

Commercial insurers need AI systems that can understand the structure of commercial risk, connect fragmented information, preserve source lineage, apply relevant underwriting context, and operate within governed workflows.

That foundation becomes even more important as organizations move from generative AI assistants toward agentic systems that can recommend or take actions.

Convr is built specifically for commercial P&C underwriting. Its Risk Context Engine provides an insurance-specific foundation for structuring, connecting, and contextualizing risk information so AI-powered underwriting workflows can operate with stronger grounding and traceability.

For carriers and MGAs exploring agentic underwriting, the priority should be more than giving AI greater autonomy. It should be giving AI the right commercial insurance context before that autonomy expands.

Explore Convr to see how its AI-powered underwriting platform can support more intelligent, traceable, and context-aware underwriting workflows.

‍

Commercial insurance underwriting is entering a period of fundamental change.

Between 2026 and 2031, underwriting teams will move beyond using technology primarily to store documents, calculate rates, and manage policies. The next generation of underwriting systems will actively organize submission data, identify relevant risk signals, recommend next steps, automate routine decisions, and give underwriters a continuously updated view of each account.

This transformation will be driven by a practical business need.

Commercial submissions continue to arrive through emails, applications, spreadsheets, loss runs, statements of values, inspection reports, financial documents, and broker-created forms. Underwriters often have the information they need, but it is fragmented across documents and systems that do not communicate effectively.

Before evaluating the risk, the underwriter must locate the correct files, identify missing information, interpret inconsistent descriptions, reenter data, compare external sources, and determine whether the submission fits the carrier’s appetite.

That operating model is becoming increasingly difficult to sustain.

Brokers expect faster responses. Carriers want better risk selection. Underwriting leaders need greater consistency. Operations teams need to manage rising submission volumes without increasing administrative headcount at the same rate.

The future of underwriting will therefore be defined by how effectively insurers convert fragmented data into decision-ready intelligence.

AI will play a central role, but the goal will not be to remove underwriters from the process. The goal will be to give them better information, reduce repetitive work, and enable more consistent decisions across the underwriting lifecycle.

1. AI-Assisted Decisioning Will Become Part of Daily Underwriting

The first major change will be the expansion of AI-assisted decisioning.

Many underwriting technologies currently help users find documents, extract fields, or summarize submissions. Over the next five years, AI will move further into the decision workflow.

An underwriter reviewing a commercial account will increasingly be able to ask questions such as:

• Does this risk fit our appetite?

• What information is missing?

• Which exposures require further review?

• How has the account changed since the previous policy period?

• Are the reported operations consistent with the business classification?

• Which losses are most relevant to the current coverage?

• What follow-up questions should be sent to the broker?

The system will not simply retrieve isolated data points. It will interpret information within the context of the account, the carrier’s underwriting rules, historical records, and relevant external risk signals.

This is an important distinction.

A general-purpose AI tool may be able to summarize a document, but commercial underwriting requires an understanding of relationships. Locations must be connected to property values. Vehicles must be connected to drivers and operating territories. Losses must be associated with the correct coverage period. Business descriptions must be interpreted within the context of classification, appetite, and exposure.

Future underwriting systems will become more valuable as they become more capable of preserving these relationships.

AI-assisted decisioning will also improve consistency. Instead of relying on each underwriter to manually locate the same information and interpret it in a different way, teams will begin with a more standardized risk view. Underwriters will still exercise professional judgment, but they will work from a more complete and reliable foundation.

2. Automated Submission Intake Will Become the Default

Submission intake is likely to experience one of the most visible transformations.

Today, many commercial underwriting teams still receive submissions through shared inboxes. Employees open messages, download attachments, identify document types, create records, extract information, and route the account to the correct team.

Over the next five years, much of this process will become automated.

Intelligent intake systems will be expected to:

• Ingest submissions from email, portals, APIs, and other channels

• Separate combined document packages

• Classify applications, loss runs, schedules, and supporting files

• Extract relevant underwriting information

• Standardize data into a consistent schema

• Identify missing or conflicting information

• Check the submission against appetite rules

• Route the account to the appropriate workflow

• Create tasks or broker requests automatically

The result will be a significant change in the underwriter’s starting point.

Instead of opening an email containing a collection of raw attachments, the underwriter will open an account that has already been structured, summarized, enriched, and prioritized.

This does not mean every submission will move through without review. Commercial insurance documents are too varied, and many risks are too complex, for completely unattended processing in every situation.

The more realistic future is selective automation.

Straightforward, high-confidence tasks will be completed automatically. Ambiguous information, conflicting values, and unusual exposures will be routed to the appropriate person for review. Human attention will be directed toward exceptions rather than routine data entry.

3. Embedded Risk Intelligence Will Replace Manual Research

Underwriters frequently rely on information that does not appear in the original submission.

They may need to verify business operations, review location characteristics, investigate ownership, examine financial indicators, identify regulatory issues, compare industry classifications, or understand the risk environment surrounding a property.

This research is often completed through separate websites, third-party databases, internal systems, and manual searches.

The future underwriting workflow will bring that intelligence directly into the account.

Relevant external information will be embedded alongside the submission rather than presented as a disconnected data feed. The system will connect external signals to the appropriate business, location, exposure, or policy period so the underwriter can understand why the information matters.

For example, property intelligence should not simply provide a collection of location attributes. It should identify which characteristics may affect the relevant coverage and present those insights in the context of the submission.

The same principle applies to business data.

An external classification, revenue estimate, ownership record, or operational description becomes more useful when it is compared with the applicant’s information and used to identify a potential inconsistency.

Embedded risk intelligence will reduce the amount of time underwriters spend moving between systems. More importantly, it will make external data easier to interpret and apply consistently.

4. Real-Time Enrichment Will Create a Living View of Risk

Traditional underwriting often relies on a snapshot of the applicant at a particular moment.

The submission describes the organization when the application was completed, but commercial risks can change throughout the policy period. Businesses open new locations, change operations, purchase equipment, experience losses, adjust staffing, expand into new territories, or encounter new financial pressures.

Over the next five years, risk profiles will become more dynamic.

Underwriting platforms will increasingly enrich account data throughout the lifecycle rather than only during initial submission review. New information will be compared with historical data to identify material changes before renewal or when additional review is required.

This will give carriers a more continuous view of risk.

Instead of reconstructing the account from the beginning at each renewal, underwriters will be able to see what has changed, why the change matters, and which areas deserve attention.

Real-time enrichment will also improve prioritization. Accounts with meaningful changes can be routed for deeper review, while stable renewals may move through a more streamlined workflow.

The future of underwriting will therefore be less dependent on isolated annual evaluations and more focused on maintaining an evolving, contextual understanding of the insured risk.

5. Underwriting Workbenches Will Become the Operational Layer

Most insurers are unlikely to replace every core system within the next five years.

Policy administration platforms, rating engines, document repositories, data providers, CRM systems, and broker portals will continue to play important roles. The challenge will be connecting those technologies into a usable underwriting experience.

This is where the underwriting workbench will become increasingly important.

Rather than forcing underwriters to move between multiple applications, the workbench will act as an operational layer across the existing technology environment. It will bring together submissions, structured data, risk intelligence, tasks, appetite rules, communications, and decision support within a unified workflow.

The most effective workbenches will not attempt to become another isolated system. They will integrate with the insurer’s existing architecture and allow information to flow between intake, underwriting, rating, policy administration, and portfolio management.

For underwriters, the experience should become simpler even as the technology behind it becomes more sophisticated.

They will spend less time searching for information, reentering data, and tracking tasks manually. They will spend more time interpreting complex exposures, communicating with brokers, evaluating terms, and making decisions that require professional judgment.

That shift will form the foundation for the increasingly autonomous underwriting workflows discussed in the second half of this article.

6. Autonomous Workflows Will Handle More Routine Underwriting Tasks

The next stage of underwriting modernization will move beyond individual automation features toward increasingly autonomous workflows.

Today, many systems automate isolated tasks such as extracting fields from documents or routing submissions to the correct queue. Over the next five years, AI agents will begin coordinating several steps across the underwriting process.

For a straightforward submission, an autonomous workflow may be able to collect documents, classify the risk, identify missing information, enrich the account with external data, apply appetite rules, create a preliminary risk summary, and recommend the next action.

The system may then route the account based on confidence and complexity.

A high-confidence submission that falls clearly outside appetite could be declined or referred according to predefined rules. A complete, lower-complexity risk may move directly to rating or an accelerated review. An unusual account with conflicting information would be escalated to an experienced underwriter.

This approach will allow carriers to apply human expertise more deliberately.

Underwriters will not need to review every routine task with the same level of attention. Instead, they will focus on exceptions, complex exposures, large accounts, unusual coverage requests, and situations where professional judgment materially affects the outcome.

Autonomous workflows will require careful governance. Insurers will need clear authority limits, transparent decision logic, reliable audit records, and appropriate human review. The objective should not be automation without oversight. It should be controlled automation that improves speed while preserving underwriting discipline.

7. The Underwriter’s Role Will Become More Strategic

As technology handles more document processing and administrative work, the role of the underwriter will evolve.

Underwriters will spend less time locating data and more time interpreting it.

Their value will increasingly come from understanding complex exposures, identifying emerging risks, negotiating terms, managing broker relationships, and making decisions that cannot be reduced to a simple rule.

This shift will also change the skills insurers prioritize.

Future underwriters will need strong commercial judgment, but they will also need to understand how to work effectively with AI-generated insights. They must know when to trust an automated recommendation, when to question it, and when additional investigation is required.

Data literacy will become more important. Underwriters will need to interpret confidence levels, identify possible data quality problems, and understand how external information influences the risk assessment.

Communication skills will remain essential.

Even the most advanced underwriting platform cannot replace the relationship between carriers and brokers. Complex accounts often require discussion, negotiation, and an understanding of the insured’s broader business strategy.

Technology will strengthen the underwriter’s role by providing better preparation for those conversations.

8. Portfolio Intelligence Will Influence Individual Decisions

Underwriting has traditionally focused heavily on evaluating one submission at a time.

Over the next five years, individual account decisions will become more closely connected to portfolio-level intelligence.

Underwriters will be able to see how a proposed risk affects concentrations across industries, locations, property characteristics, coverage types, and emerging exposure categories. This information will help carriers understand not only whether a single account is acceptable, but also how it fits within the existing book of business.

For example, an account may appear attractive on its own but create additional concentration within a region exposed to severe weather. Another submission may support diversification by adding a well-managed risk in an industry where the carrier wants to grow.

AI-supported portfolio analysis will help underwriting teams identify these relationships earlier.

Leaders will also gain greater visibility into submission flow, appetite alignment, referral patterns, quote ratios, processing time, and the reasons accounts are accepted or declined.

This intelligence can improve capacity allocation, product strategy, distribution planning, and underwriting guidelines.

The result will be a closer connection between front-line decisions and broader portfolio objectives.

9. Explainability and Governance Will Become Essential

As AI becomes more involved in underwriting, insurers will need to understand how recommendations and decisions are produced.

A system that generates a risk score without showing the underlying information will have limited value in complex commercial underwriting.

Underwriters need to know which data points influenced a recommendation, where that information came from, whether it conflicts with the submission, and how confident the system is in its interpretation.

Explainability supports better decisions because it allows the underwriter to challenge or validate the output.

It is also important for governance.

Insurers will need documented controls governing data sources, model performance, user permissions, decision authority, referrals, and human oversight. They will need audit trails showing which information was reviewed, which recommendations were generated, and who made the final decision.

Governance should be designed into the workflow rather than added after implementation.

Organizations that establish strong controls early will be better positioned to expand automation confidently while maintaining regulatory compliance, underwriting consistency, and trust among employees and distribution partners.

10. Modernization Will Become a Business Strategy, Not an IT Project

The insurers that gain the most value from underwriting technology will treat modernization as an operating model change rather than a software installation.

Automating an inefficient process without redesigning it often produces limited improvement.

Carriers must first identify where underwriters lose time, which decisions require professional judgment, which routine tasks can be standardized, and how information should move between teams and systems.

Technology can then support the redesigned workflow.

Executive sponsorship will be critical. Underwriting, operations, technology, data, compliance, and distribution teams will need shared objectives and a clear understanding of how success will be measured.

Useful performance measures may include:

• Submission processing time

• Time to first underwriter review

• Quote turnaround time

• Percentage of submissions within appetite

• Manual data entry reduction

• Referral frequency

• Quote and bind ratios

• Underwriter capacity

• Data completeness and accuracy

Successful modernization will also require adoption from the people who use the technology every day.

Underwriters should understand how new tools improve their work, where human judgment remains central, and how feedback will be used to refine the system.

The future of underwriting will not be created by technology alone. It will be created by insurers that combine capable platforms with redesigned workflows, experienced professionals, and clear strategic priorities.

Frequently Asked Questions

What will commercial insurance underwriting look like in five years?

Commercial underwriting will become more automated, connected, and data-driven. AI will organize submissions, extract and validate information, enrich accounts with external intelligence, and recommend next steps. Underwriters will remain responsible for complex decisions, negotiations, and professional judgment.

Will autonomous underwriting replace human underwriters?

Autonomous workflows will handle more routine tasks and lower-complexity submissions, but they are unlikely to replace experienced commercial underwriters. Complex risks require interpretation, negotiation, market knowledge, and an understanding of circumstances that automated rules may not fully capture.

What is AI-assisted underwriting?

AI-assisted underwriting uses artificial intelligence to support activities such as document classification, data extraction, risk enrichment, appetite screening, submission summarization, and decision support. The technology prepares and organizes information so underwriters can make faster and more informed decisions.

How will real-time data change underwriting?

Real-time enrichment will give carriers a more current view of an insured’s operations, locations, exposures, and financial condition. It can help identify material changes during the policy lifecycle and allow underwriting teams to prioritize accounts that require closer review.

What should insurers modernize first?

Many insurers begin with submission intake because it contains large amounts of manual, repetitive work. Automating document classification, data extraction, validation, and routing can create immediate efficiency while establishing the structured data needed for more advanced decision support.

Build the Underwriting Operation of the Future

Over the next five years, commercial underwriting will move from fragmented, document-heavy processes toward connected workflows built around decision-ready intelligence.

AI-assisted decisioning, automated submission intake, embedded risk data, real-time enrichment, and autonomous workflows will help carriers respond faster while applying underwriting expertise more effectively.

The competitive advantage will not come from automation alone. It will come from combining technology with experienced underwriters, clear governance, connected systems, and a well-designed operating model.

Convr helps commercial insurers create that foundation through an AI-powered underwriting workbench that transforms unstructured submissions into organized, enriched, and actionable risk intelligence. By automating intake and connecting critical underwriting information within a unified workflow, Convr enables teams to increase capacity, improve consistency, and make confident decisions faster.

Explore how Convr can support your underwriting modernization strategy and help your organization build a more intelligent, efficient, and connected commercial insurance operation.

‍

Commercial insurance underwriting is built on one objective: understanding risk well enough to make informed, profitable decisions. Before an underwriter can determine whether to offer coverage, set pricing, or request additional information, they must first evaluate the quality and completeness of the submission in front of them.

The challenge is that modern commercial insurance submissions rarely arrive in a standardized format.

Applications often include ACORD forms, loss runs, schedules of values, supplemental questionnaires, broker emails, financial documents, inspection reports, and numerous supporting attachments. Important information may be spread across dozens or even hundreds of pages, requiring underwriters to spend valuable time locating, validating, and organizing key details before they can begin evaluating the actual risk.

This is why experienced underwriters focus on a handful of critical data points first.

These core pieces of information help determine whether a submission fits the carrier's appetite, whether additional review is required, and how the account should be prioritized within the underwriting workflow. They also provide the foundation for every subsequent underwriting decision, from pricing and coverage terms to referrals and risk selection.

As commercial insurance continues to become more data-driven, insurers are investing in technology that structures fragmented submission data into decision-ready intelligence. Rather than manually searching through multiple documents, underwriters increasingly rely on AI-powered underwriting workbenches to surface the most important information upfront, allowing them to spend less time gathering data and more time evaluating risk. Convr

Understanding which data points matter most helps explain not only how underwriting decisions are made, but also why clean, structured, and complete submission data has become such a competitive advantage for commercial insurers.

1. Business Classification Sets the Foundation

One of the first pieces of information an underwriter reviews is the applicant's business classification.

Understanding exactly what a company does provides immediate context for nearly every aspect of risk evaluation. A contractor, manufacturer, transportation company, retail business, and technology firm each present very different exposure profiles, even if they generate similar annual revenue.

Business classification influences underwriting guidelines, expected loss patterns, regulatory considerations, pricing models, inspection requirements, and available coverage options.

Unfortunately, this information is not always straightforward.

Applicants may describe their operations differently across applications, websites, broker submissions, and supplemental documentation. Some businesses perform multiple operations that introduce additional exposures, while others have evolved significantly since previous policy periods.

Accurately classifying a business early in the underwriting process allows carriers to quickly determine whether the submission aligns with their appetite and whether additional review is necessary before moving forward.

2. Loss History Provides Immediate Risk Context

Past claims remain one of the strongest indicators underwriters evaluate when assessing commercial risks.

Loss history helps answer several important questions.

Has the business experienced frequent claims? Were losses isolated incidents or part of an ongoing pattern? Have corrective actions been implemented? Are claim severities increasing over time? Do previous losses suggest operational issues that could affect future performance?

Loss runs also help underwriters distinguish between organizations with similar operations but very different risk characteristics.

Two construction companies may perform identical work, yet one consistently demonstrates strong risk management while the other experiences repeated workers' compensation or liability claims. Reviewing historical loss information helps identify those differences early in the evaluation process.

Because loss data often arrives in multiple formats from different carriers, structuring and normalizing this information is essential for efficient underwriting. Modern underwriting platforms increasingly automate this process, allowing underwriters to analyze trends rather than manually extracting claim information from lengthy documents. Convr

3. Revenue Helps Measure Exposure

Annual revenue is another critical data point reviewed early in the underwriting process.

Revenue often serves as a proxy for business size and operational complexity while influencing premium calculations across many commercial insurance products.

A business generating $2 million in annual revenue generally presents different exposure characteristics than one generating $200 million. Larger organizations may have more employees, additional locations, broader operations, larger customer bases, and more complex contractual relationships.

Revenue also helps underwriters identify inconsistencies elsewhere in the submission.

For example, reported payroll, employee counts, sales volumes, or operational descriptions that appear inconsistent with stated revenue may warrant additional questions before underwriting continues.

Accurate financial information supports more consistent pricing while helping carriers evaluate risk within the proper business context.

4. Exposure Details Shape the Underwriting Decision

After establishing the basic profile of the applicant, underwriters turn their attention to the specific exposures presented by the business.

These details vary by industry but often include information such as:

• Number and location of facilities

• Employee count

• Property values

• Vehicle fleets

• Equipment schedules

• Products manufactured or distributed

• Geographic operations

• Contractual relationships

• Safety programs

• Cyber exposures

• Hazardous operations

These exposure details determine not only whether coverage is appropriate but also how policies should be structured and priced.

Incomplete or inconsistent exposure information frequently leads to follow-up questions that delay quoting and increase manual work for underwriting teams.

This is one reason insurers increasingly rely on AI-powered submission intake technology to extract, organize, and validate exposure information before underwriters begin their review. Convr's underwriting workbench, for example, structures fragmented submission data and enriches it with contextual risk intelligence so underwriters can evaluate exposures more quickly and consistently. Convr

5. Prior Coverage Helps Identify Gaps and Trends

Another important area underwriters review early is the applicant's insurance history.

Previous coverage provides valuable insight into how the business has managed its risk over time. Underwriters look for information such as current carriers, policy limits, deductibles, renewal dates, and any recent changes in coverage.

This information helps answer several important questions. Has the business maintained continuous insurance coverage? Have coverage limits changed significantly from one policy period to the next? Has the applicant moved between multiple insurers in a short period of time? Were there any coverage restrictions or cancellations that require further investigation?

Prior coverage also helps underwriters identify potential gaps that could affect both pricing and eligibility. For example, a business that has operated without certain types of coverage may present different underwriting considerations than one with a long history of comprehensive commercial insurance.

When this information is scattered across applications, declarations pages, broker correspondence, and policy documents, manually piecing it together can consume valuable underwriting time. Automated document intelligence helps organize this information into structured data, allowing underwriters to review coverage history much more efficiently.

Why Data Quality Matters as Much as the Data Itself

Even the most experienced underwriter can only make decisions based on the information available.

Incomplete applications, inconsistent documents, missing schedules, and conflicting data create unnecessary delays throughout the underwriting process. Instead of evaluating risk, underwriters spend time requesting clarification, searching through attachments, or following up with brokers for information that should have been readily available.

Poor data quality affects more than productivity.

Incomplete information can increase quote turnaround times, create inconsistent underwriting decisions, reduce broker satisfaction, and ultimately affect an insurer's ability to compete in today's commercial insurance market.

High-quality submissions, by contrast, allow underwriters to begin evaluating the account immediately. Structured, validated data improves consistency while reducing manual effort across the submission intake process.

As commercial insurance organizations continue investing in digital transformation, improving submission quality has become one of the most effective ways to increase underwriting efficiency without compromising decision quality.

How AI Is Changing the Way Underwriters Review Data

Artificial intelligence is not replacing underwriters. Instead, it is helping them spend more time applying their expertise where it creates the greatest value.

Historically, much of an underwriter's day involved administrative work. Reading lengthy submissions, locating missing information, manually entering data into underwriting systems, comparing documents, and identifying inconsistencies often consumed hours before actual risk evaluation could begin.

AI-powered underwriting platforms are changing that workflow.

Rather than expecting underwriters to search through dozens of documents, modern solutions automatically ingest submissions, classify documents, extract key data points, validate information across multiple sources, and present structured summaries that support faster decision making.

This allows underwriters to focus on evaluating complex risks, exercising professional judgment, collaborating with brokers, and making informed underwriting decisions instead of spending valuable time on repetitive manual tasks.

Convr's AI-powered underwriting platform is designed specifically to support this transformation by automating submission intake, extracting critical underwriting information, enriching data with external intelligence, and delivering structured insights that improve speed, consistency, and underwriting accuracy. By reducing administrative work, insurers can improve operational efficiency while creating a better experience for both underwriters and distribution partners.

Best Practices for Improving Underwriting Efficiency

Whether reviewing submissions manually or with AI support, several best practices consistently improve underwriting performance.

Start by ensuring submissions contain complete and consistent information before they enter the underwriting queue. Early validation reduces delays later in the process.

Standardize data wherever possible. Structured information allows underwriters to compare risks more consistently while reducing unnecessary interpretation between different document formats.

Prioritize the data points that have the greatest influence on underwriting decisions. Business classification, loss history, revenue, exposure information, and prior coverage provide the foundation for evaluating most commercial submissions.

Leverage technology to automate repetitive administrative tasks rather than replacing professional judgment. AI performs best when supporting experienced underwriters by delivering cleaner, better-organized information.

Finally, continue refining workflows as new technologies emerge. Commercial underwriting continues to evolve rapidly, and organizations that combine experienced underwriting professionals with intelligent automation are well positioned to improve both operational efficiency and decision quality.

Frequently Asked Questions

What information do underwriters review first?

Most commercial underwriters begin by reviewing the applicant's business classification, historical loss experience, annual revenue, operational exposures, and prior insurance coverage. These core data points provide the foundation for evaluating whether a risk fits the carrier's underwriting appetite and what additional review may be required.

Why is loss history so important in underwriting?

Loss history helps underwriters understand how a business has managed risk over time. Reviewing previous claims allows insurers to identify trends, evaluate claim frequency and severity, and determine whether past losses suggest operational issues that may affect future risk.

How does AI help commercial underwriters?

AI helps automate many of the manual tasks that traditionally consume underwriting time. Modern underwriting platforms can classify submission documents, extract structured data, validate information across multiple sources, identify inconsistencies, and present organized summaries that allow underwriters to focus on evaluating risk rather than gathering information.

What happens if submission data is incomplete?

Incomplete submissions often lead to additional questions, slower quote turnaround times, inconsistent underwriting decisions, and increased administrative work. Improving submission quality allows underwriters to begin evaluating risk more quickly while creating a better experience for brokers and policyholders.

Can AI replace commercial underwriters?

No. AI is designed to support underwriters rather than replace them. Experienced underwriters continue to make complex risk decisions, apply professional judgment, and evaluate unique business circumstances. AI improves efficiency by automating repetitive data collection and document processing, allowing underwriters to spend more time on higher-value decision making.

Transform Underwriting Data Into Faster Decisions

Every commercial insurance submission contains the information underwriters need to evaluate risk, but finding, organizing, and validating that information has traditionally required significant manual effort. As submission volumes increase and customer expectations continue to rise, insurers need better ways to surface critical underwriting data quickly without sacrificing accuracy.

Convr helps commercial insurers modernize underwriting by using AI to automate submission intake, extract structured data from complex documents, enrich underwriting intelligence, and deliver decision-ready information to underwriting teams. The result is faster turnaround times, greater consistency, improved operational efficiency, and more time for underwriters to focus on what matters most: making confident underwriting decisions.

If your organization is looking to streamline submission intake and empower underwriters with AI-driven data extraction and risk intelligence, explore how Convr can help transform your underwriting workflow.

‍

Summary

MSIG USA modernized their underwriting ecosystem to address fragmented legacy processes, enabling the insurer to scale specialty product offerings and improve risk evaluation through data integration and AI-driven automation. 

The insurer implemented Convr, an AI-enabled underwriting workbench, to systematize and streamline underwriting intake, clearance, and risk assessment workflows. This transformation reduced submission processing time to one hour, supported additional submission volume without increasing headcount, and enabled increases in revenue while fostering a more consistent, data-driven underwriting culture. 

MSIG USA's initiative illustrates what’s become a significant trend over the past several years, as insurers seeking to improve their underwriting processes and outcomes have shown increasing interest in modern underwriting workbench platforms. They have demonstrated how AI and automation can be leveraged not merely to digitize workflows but to fundamentally enhance underwriting quality, speed, and scalability.

Hiscox Partners with Convr AI to Drive Underwriting Excellence Through Data Accuracy

Serving more than 500,000 small business customers, Hiscox USA delivers insurance policies with a focus on the small business market.

Hiscox USA is part of the Hiscox Group, which has more than 3,000 employees across 14 countries worldwide.

The organization continually embraces new technologies, strategies and processes that best support the business and its customers.

Hiscox USA puts technical excellence at the heart of its strategy, helping to move the business forward and keep it competitive as the landscape changes.

Accurate data is key to that technical excellence.

Jim Cadieux, Head of Product and Portfolio Management at Hiscox, is leading the charge as he ensures that the company is growing efficiently and that all the different areas of the business are working together towards this goal.

Today, one of his primary areas of focus is ensuring that the data Hiscox uses for underwriting is as accurate as possible so that Hiscox can deliver a stellar customer experience while reducing risk.

"At Hiscox, we are constantly shaping an exceptional end-to-end experience for our customers and partners. Accurate data enables us to better understand our customers and help them to achieve their goals as well as our own."

Challenge: Accurate Data Necessary for Technical Excellence

Cadieux and the Hiscox team partnered with Convr AI to gain a better and more accurate understanding of the small businesses they insure.

By understanding more about these businesses, they can make better decisions as they assess risk and loss.

Accurate data is also essential for underwriting, as misleading data can lead to risky business decisions down the line.

The more accurate the data, the more protected the policyholder and insurer.

For small business owners across the United States, there is a pervasive lack of understanding of insurance.

According to the Hiscox Underinsurance Study, 83% of U.S. small business owners do not understand what a General Liability policy covers.

This lack of understanding can lead to policyholders not providing accurate data or updating their insurance when they need to.

In fact, 75% of small business owners in the United States are underinsured.

It is crucial for policyholders to provide accurate and up-to-date data to their insurance provider to ensure their business is fully protected.

If they do not, they could leave their business exposed and be financially and legally liable for any claims.

"We were looking to improve technical excellence when it came to digital underwriting – we wanted to know more about the risks and more efficiently rate policies."

Hiscox partnered with Convr AI to make the process of gaining accurate data more efficient.

Convr’s Risk 360 AI and Answers AI products, along with its promised return rate of 93%, helped Hiscox advance its goal of technical excellence and ensure that the policies they write are based on the best data possible.

Solution: Partnering with Convr AI

Using Convr, Hiscox is able to review tranches of renewals or new policies and understand whether self-reported data is accurate.

Having an accurate picture of individual business functions allows the company to improve rating accuracy, which is critically important when writing and renewing policies.

The Hiscox and Convr teams meet regularly to discuss data, insights and establish new goals and priorities.

Together, they have developed a set of key performance indicators to measure progress and are meeting and exceeding those goals.

Partnering with Convr has allowed Hiscox to gain a more detailed picture of the small businesses they insure.

Leveraging Risk 360 AI and Answers AI

Hiscox USA leverages two modules within Convr’s Underwriting Workbench:

• Risk 360 AI
• Answers AI

Risk 360 AI unleashes detailed insights from the intersection of tens of thousands of data elements.

Answers AI provides access to available information about an applicant’s business while answering underwriting questions directly through insurance-trained AI models.

"Those data sources are just going to get better and better over time."

Creating a Better Customer Experience

Hiscox strives to create a frictionless path for customers while simultaneously improving underwriting accuracy.

Rather than requiring customers to provide increasing amounts of information, Convr helps move more of the intelligence gathering process behind the scenes.

This enables a more efficient customer journey while helping underwriters make better decisions.

"Hiscox strives to be America’s leading small business insurer. To do that, we need to have a frictionless path for customers to find us and for us to address their needs. Convr plays a role in that as we’re able to do more on the back end rather than putting it all on the customer."

The Impact of Accurate Data

For Hiscox, underwriting excellence begins with data accuracy.

Better data enables better understanding of risk.

Better understanding of risk enables more accurate pricing, improved policy decisions and stronger protection for both policyholders and insurers.

By leveraging Convr’s AI-powered underwriting tools, Hiscox has strengthened its ability to evaluate risk while continuing to improve the customer experience.

The partnership has also established a framework for continuous improvement as new data sources, insights and capabilities become available.

Underwriting Excellence Through Data Accuracy

Technical excellence is not simply about improving operational efficiency.

It is about ensuring that every underwriting decision is supported by the most complete and accurate information available.

Through its partnership with Convr AI, Hiscox has enhanced its ability to understand small businesses, improve rating accuracy and support a customer-first approach to underwriting.

As data quality continues to improve, the value delivered by AI-powered underwriting solutions will continue to grow.

Convr AI Underwriting Workbench

Convr AI delivers a full suite of AI-infused commercial insurance tools that support underwriting analysis and decisions.

Intake AI

Eliminates manual submission paperwork by ingesting, preparing and analyzing submissions for a more effective digital process.

Answers AI

Applies decision science to correctly answer complex underwriting questions.

Risk 360 AI

Provides underwriters a unified view of a submission’s digital footprint to correctly classify and respond to underwriting questions.

Risk Score AI

Applies decision science to risk selection, relativity and lead scoring.

Convr is an AI underwriting and intelligent document processing workbench that drives world-class customer experiences.

It delivers premium growth, insights and efficiency for commercial P&C insurance organizations of all sizes, including many of the top 20 carriers, MGAs, brokers and reinsurers.

Convr is revolutionizing the industry through data, discovery and decisioning intelligence.

Crum & Forster Partners with Convr to Digitally Transform Submission Intake and Unleash Human Potential

You don’t get to be 200 years old without doing something right. Crum & Forster is a commercial P&C carrier with a long history of offering innovative solutions to overcome challenges. The company’s Surplus and Specialty Lines (S&S) Division provides bespoke solutions for hard-to-place risks.

As one of the country’s largest Excess and Surplus (E&S) carriers, Crum & Forster works with select wholesale brokers to provide the customized service the company is known for.

"I had a vision to streamline the submission intake process."

In 2021, the S&S Division kicked off a five-year plan to double its top-line underwriting performance. Lauren Dieterich, Senior Vice President, Head of Operations and Digital, Surplus & Specialty, recognized that to achieve that goal, her team needed to streamline a manual, labor-intensive submission intake process.

Specifically, Dieterich envisioned using intelligent document processing (IDP) to automatically pull data elements out of submission materials.

The Challenge

The S&S submission process requires more flexibility than most vendors can offer.

For example, the division deals mostly with wholesale brokers, which are typically not listed in an ACORD 125 form. Their contact information is more often buried in a long email thread featuring multiple parties.

In addition, submissions often include other documents, such as supplemental applications, driver lists or location schedules.

"I was looking for a vendor who could do more than just ACORDs."

"And I wanted a vendor who could grow with us as we could consume and leverage more and more data."

Convr Brings Crum & Forster's Vision to Life

Dieterich found exactly what she was looking for in Convr’s AI-infused commercial underwriting platform. The S&S Division selected Convr’s d3 Intake™ to enable a more efficient process for new business submission intake.

With d3 Intake, Crum & Forster’s S&S Division can:

• Quote faster
• Streamline its submission intake process
• Leverage data for future insights

d3 Intake eliminates most of the data entry required to clear and prepare an underwriting file, which transforms both the underwriting and customer experience.

By using d3 Intake’s IDP capabilities, the S&S Division can automatically ingest and organize information from nearly any structured or unstructured document.

d3 Intake enables the team to collect, analyze and retain the information from the application process. These insights can inform future pricing models, underwriting decisions or claims handling.

The flexibility of Convr’s solutions is essential for Crum & Forster. Convr took time to truly understand what Crum & Forster needed, whether being able to pull specific data points from long email threads, working with a variety of structured and unstructured documents or determining source priority when presented with multiple documents.

"We achieved our vision of a more efficient submission intake process with Convr’s d3 Intake on the front end."

We Saw Results Within Weeks of Turning It On

"We saw results within weeks of turning it on."

Streamline Submission Intake Process

Before d3 Intake, a team of contractors was responsible for clearing submissions, a process that required manual data entry into multiple legacy systems.

First, a submission would have to pass a clearance call, which meant combing through emails and attachments to manually enter data into a legacy system.

Next, if the submission passed clearance, then it was assigned to an underwriter. That meant navigating business rules spread across multiple tabs in a Microsoft Excel spreadsheet.

Finally, the account was triaged in a separate Excel sheet with additional required inputs.

After d3 Intake, the S&S Division could automatically ingest submission data from structured and unstructured sources. In turn, that allowed team members to automate business rules.

Finally, those two critical capabilities made it possible for Crum & Forster to develop a new submission intake platform that virtually eliminates manual data entry.

Cut Submission Processing Time by 50%

Before d3 Intake, the inefficient and labor-intensive submission intake process resulted in a one- to two-day backlog for submissions.

After d3 Intake, the S&S Division has cut its submission processing time in half. Typically, it sees same-day turnaround on submissions.

With automatic data ingestion and a new submission intake platform, the clearance team can clear, triage and prepare underwriting files faster than before.

Redeploy Team Members to Higher-Value Roles

Before d3 Intake, Crum & Forster’s S&S Division kept extra capacity on the clearance team to manage the backlog of submissions.

After a file had cleared submission, members of the Operations team would assemble the underwriting file.

After d3 Intake, there was no submissions backlog even at peak activity, and no need for overtime or excess capacity.

Within a month of implementing d3 Intake, Crum & Forster’s S&S Division was able to more strategically allocate its most important resources: its people.

Approximately 40% of the clearance team members moved into file preparation roles. In turn, 20% of the Operations team was redeployed into revenue-generating production and underwriting positions.

"The bulk of the savings came from being able to redeploy part of my Operations team into underwriting roles. Now our human resources are aligned with what’s really going to drive growth, and I could achieve those additional goals with no extra spend."

Digital Technology That Enables True Change

Crum & Forster’s S&S Division knew what it needed: a more efficient submission intake process.

It also knew how to make it happen: by leveraging IDP to automate and streamline how it was ingesting and capturing data.

"Convr provided exactly what I was looking for."

Convr’s IDP capabilities made it possible for the S&S team to automate business rules and, in turn, to develop a proprietary submission intake platform.

That platform has enabled a more streamlined intake process that reduces submission intake time by half.

Building the Foundation for Future Growth

But true digital transformation comes from using technology not just to reduce costs, but to do things differently.

Crum & Forster did just that, by offering advancement opportunities to contractors and redeploying Operations employees into critical and revenue-generating underwriting roles.

"Now we have other questions to answer."

"How do we extend the Convr relationship to use more of the data that d3 Intake can pull out of documents?"

By leveraging Convr’s d3 Intake and its IDP capabilities, Crum & Forster’s S&S Division has the foundation it needs to achieve its goal of doubling its top line within five years.

It has also planted the seeds for the next phase of its growth strategy.

"Convr has been instrumental in enabling our five-year growth plan."

Transform Your Organization Today

• Grow premiums
• Avoid losses
• Improve underwriting efficiency
• Quote faster
• Drive accurate pricing
• Enhance customer experience
• Augment underwriting productivity

Convr Product Suite

d3 Intake™

Eliminates manual submission paperwork by ingesting, preparing and analyzing submissions for a more effective, digital process.

d3 Risk 360™

Provides underwriters a unified view of a submission’s digital footprint to correctly classify and respond to underwriting questions.

d3 Answers™

Applies decision science to correctly answer complex underwriting questions.

d3 Score™

Applies decision science to risk selection, relativity and lead scoring.

Executive Summary

Insights from Insurance Management on the Shifts Driving Underwriting Performance and Retention

The commercial property and casualty underwriting function is undergoing rapid transformation. As digital tools, automation, and AI reshape traditional processes, commercial property and casualty (P&C) insurance leaders are racing to modernize their teams and technology.

The recent 2025 Convr Insurance Talent and Tech Trends Survey reveals that more than 90% of insurance managers and above are actively up-training their underwriting teams in data analytics, automation, and digital underwriting. Yet despite these efforts, organizations still face significant talent and technology challenges that threaten efficiency, accuracy, and employee retention.

Key findings include:

• Employee retention risk is highest among underwriters aged 21-40 - the very demographic positioned to lead the industry forward.

• 45% of new underwriting hires request better access to technology and tools, and 42% want training on the latest systems.

• 82% of managers believe their underwriting teams struggle more than other departments to attract quality talent.

• 95% of leaders expect more underwriting tasks to be automated in the coming years, yet manual data entry remains the top barrier to speed and accuracy.

The message is clear: the next era of underwriting depends on smarter tools, simpler processes, and strategic investment in talent.

The Talent Challenge: Retaining and Reskilling the Next Generation

Insurance leaders overwhelmingly agree that underwriting talent can be challenging to find - and even harder to keep.​

The takeaway: attracting and retaining the next generation of underwriters requires a dual focus on career growth and technology empowerment.​

Technology Gaps Undermine Efficiency and Accuracy​

Understaffing and outdated technology are having measurable downstream effects on underwriting accuracy and customer experience.​

• 70% of managers believe that understaffing leads to inaccurate information in quotes.​
• 82% believe understaffing directly harms customer experience.​
• 56% cite manual data entry and collection as the number one issue slowing down underwriting operations.

In fact, managers ranked the top 10 causes of underwriting slowdowns as follows:​

The Automation Imperative

Nearly 95% of insurance leaders expect a higher percentage of underwriting tasks to be automated over the coming years. In fact, more than 80% believe that at least 25% of today's manual underwriting work could be automated.​

The potential gains are substantial. One Convr customer reported reducing quote turnaround time from 1-2 days to just nine minutes after implementing automated underwriting workflows - a testament to the power of automation and intelligent data ingestion.

For an industry still battling staffing shortages and data bottlenecks, automation represents not just efficiency - but sustainability.

Technology as a Retention Strategy

Better technology doesn't just improve productivity - it improves retention. 84% percent of insurance managers believe that upgraded tools and automation will probably or definitely reduce employee attrition.​ ​As one senior underwriting leader noted, "When we remove the repetitive, manual work underwriters can focus on what they actually trained for - risk assessment and decision-making."

Technology investments are already accelerating. 73% of companies delivered new underwriting tools to their teams in 2024, and 83% plan to deliver more in 2025.​

When asked which tools have the most impact, managers ranked the top five as:​

This hierarchy highlights a clear emphasis on data visibility, compliance, and automation - all key to modernizing underwriting at scale.

What Underwriters Need Most

Respondents indicated that their underwriting teams would benefit most from simplified access to critical resources. In rank order, they cited:

Simplifying access to this information - and integrating it into daily workflows - is essential to improving accuracy, speed, and employee satisfaction.​

Top Skills for the Modern Underwriter

Even as automation grows, the human element of underwriting remains central. Commercial P&C insurance managers identified communication, detail orientation, and decision-making as the top three skills they seek in underwriting team hires.​ ​Even as automation grows, the human element of underwriting remains central. Commercial P&C insurance managers identified communication, detail orientation, and decision-making as the top three skills they seek in underwriting team hires.​ ​These "power skills" complement automation by ensuring underwriters can interpret, validate, and communicate insights from digital tools effectively.

A Vision for a Smarter, Faster Underwriting Future​

Nearly 95% of underwriting management agrees that their company's performance could improve through greater efficiency in underwriting processes. This consensus underscores a critical opportunity: to unite people, process, and technology in a cohesive digital strategy.

The path forward involves:

Automating routine work such as data collection, entry, and validation.​ Modernizing workflows through integrated data sources and workflow management systems.​ Training underwriters on AI tools and analytics to support faster, more accurate risk assessment.​ Improving data quality and accessibility to eliminate guess work and manual searches.​ ​Investing in experience - ensuring underwriters have tools that make their jobs easier, faster, and more rewarding.

Conclusion

The commercial P&C insurance underwriting profession stands at a turning point.​ ​While challenges in talent, staffing, and technology persist, the industry's direction is unmistakable: digital transformation is no longer optional - it's a competitive necessity.​ ​As automation expands and data becomes more central to decision-making, insurers that prioritize technology, training, and employee experience will not only operate more efficiently but also build the kind of workplaces that attract and retain top underwriting talent.​ ​The future of underwriting isn't about replacing human expertise -it's about amplifying it through technology.

Convr surveyed 200 commercial property and casualty (P&C) insurance decision-makers across the U.S. to dig into the role talent and technology play in driving results.

Modernizing Underwriting:

Turning to Scores

An Age-Old Problem

How do you select the right risk and price it appropriately? That's the goal of insurance underwriting. There is a delicate balance to charging acceptable rates and maintaining profitability. This is the domain of insurance underwriters who rely on historical data and actuarial analyses to evaluate and analyze the risks.

While the science behind it is valid, little has changed over the years in the way underwriting is performed by commercial insurance underwriters. Every day, thousands of these workers clock into their jobs with the intent to manage risk. They trudge through the mire of imperfect data, old policies, predictive analytics, online information and more to get to a place where they can comfortably accept, avoid or reduce the risk to their company. And why is it so hard? Because no single source is reliable, transparent, or comprehensive for assessing current or future risk.

The very essence of the underwriter's job is about making the best decision possible for their company, and they don't want to get it wrong. An inaccurate assessment of the risks associated with writing a policy or from insufficient premium could result in negative impact to loss and combined ratios. But, needless to say, sometimes they make mistakes.

As if this pressure is not enough, the sky-high pile of submissions and staffing shortages are among the many challenges these professionals face. Plus, there are dozens of cumbersome tasks and weeding through voluminous data sets and sources. Old underwriting tools require them to manually key in submission information from incoming documents. And then, the required quality checks contribute to longer lead times and added stress to maintain their high underwriting standards. The pace of work for today's underwriting professionals is accelerating and the pressure is only getting greater.

Now more than ever, the demand for faster submission processing and improved customer experience has carriers looking for ways to speed submission to quote. Insurance providers want straight through processing (STP) and their customers want real-time answers, quotes, and binders.

Happily, there are new solutions. Convr's Scores is one way underwriters are expediting their workflow, improving speed-to-quote and feeling assured their decisioning is sound.

Learn More

Machine Learning (ML) Modeling for Scoring Risks

Since 2019, Dr. John Henry, a consultant for Convr and the data science team have been forecasting risk related outcomes one year into the future. This might not seem like a big deal but since most commercial policies have a one-year duration or less, this is enough to provide underwriters with greatly increased confidence throughout the policy term. Examples of the events ML models are trained to forecast include injuries and fatalities.

The team trains the models on recurring schedules to include most recent data, consider new data sources, and improve performance over time. And the findings are presented in an easy-to-understand format - on a scale of zero to 100 called a risk score.

Convr's patented AI technology leverages ML models that are specifically trained for the commercial insurance industry. These models navigate structured and unstructured data from thousands of data sources and more than four billion data points to verify, cross-reference and deliver critical underwriting insights in real time.

Why Scoring Risks Works

Convr's risk scoring capability is driven by the need for accuracy and efficiency. Scores upgrade underwriter capabilities by providing the advanced data they need to make better and faster decisions. Convr's Scores deliver a single number measure of risk for businesses that an insurer can look to and quickly assess the relative risk of insuring a business and prioritize submissions. Companies that return a higher score would be more risky to insure while those with lower scores would likely present less risk.

Risk scoring brings more science and speed to the art of underwriting

For example, an underwriter can quickly see that a score of 90 means only 10% of businesses are more risky, while a score of 30 means 30% of businesses are less risky. The higher the score, the higher the risk. For an underwriter, it is as simple as filling in the name and address of a business and seeing real results that can affirm decisioning.

Scoring Simplified

Scores tell the underwriter where a business is on the risk distribution. A business with a score of 100 means it is in the riskiest 1% of businesses. A business with a score of 1 means that it is in the 1% of least risky businesses.

View Risk Score Sample

Convr's Data Science team found that underwriting profit in commercial auto had been trending down for several years at the time they began working on commercial auto models. His initial research looked at commercial auto loss experience at the industry level, and preliminary loss models were functions of (mostly) many geotemporal demographic and economic variables. Additional models were trained for commercial auto litigation verdict amounts, and large individual losses.

"Ultimately, we found that modeling accidents, injuries, and fatalities at the business level in a forward-looking way resulted in the most valuable predictive model(s) for underwriters. In the years since, these models have evolved and improved through collaborating with underwriters, actuaries, and claims professionals, and using more sophisticated methodologies."

Dr. John Henry

Consultant, Convr

Source: Best's Market Segment Report; March 28, 2019

US Commercial Auto

Net Underwriting Performance

Today, Convr's commercial auto risk score modeling framework incorporates all these learnings, leverages Convr's massive data-lake that includes thousands of data sources - updated on a recurring schedule - always forecasting risk one year into the future. In 2022, Convr performed a retrospective study to validate how well our commercial auto risk scoring model was forecasting risk.

• Accidents
• Injuries
• Fatalities

Accidents

Injuries

Fatalities

The Results

The results showed a convincing (and expected) relationship between Convr's Scores and injuries and fatalities per power unit. Businesses with higher scores experienced more of these events, on average, and businesses with lower scores experienced fewer of these events, on average. The study shows clearly that insurers with access to Convr's Scores in early 2021 would have been able to make decisions about current and potential insureds that would have resulted in better loss experience in the year ahead.

In the area of commercial auto for example, customers who were writing these policies have been avoiding the most risky insureds or those with the highest scores. They have been able to prioritize best risks (businesses with lowest scores). And they have been able to charge more (less) premium for insureds with higher (lower) scores.

See Real Results with

Scores and Risk 360 AI

Increase underwriting productivity

Prioritizing and reviewing submissions is often very manual and cumbersome. With d3 Risk Score, underwriters can rapidly narrow risks within their appetite and deep dive on selected risks via d3 Risk 360 (vs. Google search and DOT/Safer reports).

Reduce underwriting operating costs

Convr's implementations have seen a material reduction in operational cost across clearance, underwriting file preparation. Automation of these steps have helped our customers lower operational costs (FTE or BPO).

Increase speed to quote

A systematic approach, with d3 Score and d3 Risk 360 reduces administrative burden on Underwriters, reduces time to quote.

See growth of premiums

Increased underwriting productivity and speed-to-quote is expected to drive increased quote ratios, resulting in increased binds/new business.

Calibrate risk selection

Utilizing d3 Risk Score and d3 Risk 360, Underwriters can leverage relevant and timely information on insureds from Convr's data-lake of 2000+ data sources; high performing d3 Risk Score ML models further inform risk selection - this typically translates to better calibration of risk and greater consistency across the underwriting team.

Pricing adequacy

By monitoring loss performance with d3 Risk Scores, customers can identify segments of their book of business where they have an opportunity to adjust pricing to better reach their target loss ratio.

"The real opportunity is to look at your current book of business and incoming submissions and make better decisions today, tomorrow and going forward."

Dr. Addison Putnam

Consultant, Convr

Dive Deeper with Risk Relativity

Through risk relativity, underwriters can learn how the risk of a business compares to the average of the population through a score. One such score is specifically focused on workplace safety. For this model, we have found that some of the significant predictor variables for risk are previous infractions committed, type of permits assigned to a company and the number of years a company has been in business.

Why Scores, Why Convr?

To recap, achieving superior underwriting performance with Scores AI and Risk 360 AI can mean a commercial insurance underwriter can make more informed decisions, faster. In this way, insurance providers can realize transformative business growth and success. But, it is important to recognize that true transformation requires more than new technology. You need to be prepared for a shift in organizational mindset and culture, as well as the skill sets and roles of underwriters themselves. This is the secret to true competitive advantage.

As technology continues to transform the insurance industry, you can lead the revolution in your organization by reaching out to Convr. Convr's AI-infused commercial underwriting platform turbo-charges underwriting with more accurate and efficient decision-making and a greatly improved user experience.

At Convr, we are your partners in defining a new and better vision for commercial P&C insurance underwriting.

AM Best TV interviewed Convr CEO John Stammen at National Association of Mutual Insurance Companies (NAMIC) in September 2024. He shared insights on the value of AI underwriting and operations and how Convr AI can streamline submission to quote by reducing data entry, research and aggregation tasks to provide a better customer experience. Take a listen and hear how agents and others are winning new business with Convr AI.

\n

With a rich underlying data lake, time-tested data pipeline with data orchestration, and data currency with pre-plumbed, continuous updates, Convr AI sits on a rock-solid foundation that is unrivaled in the commercial insurance space. AI is integrated into everything we do. It informs our customers' submission selection and prioritization, risk quantification, and relativity assessments leading to improved decision-making. Explore even more at convr.com.

\n