Skip to content

For MGAs

AI underwriting for specialty MGAs.

Launch with a small senior team, and give your capacity providers an underwriting file they can check on every risk. Lexcel reads every submission, applies your guidelines and your lead underwriter’s precedent, and drafts the overview and indication with every finding cited to the page. Your underwriters make every call.

Submission overviewTollwick Robotics
Lexcel agentTollwick Robotics
Submission Overview

Run it on Tollwick’s submission.

Workflows

Submission Overview

5 steps · Deliversdoc

Summarizes a new submission for the underwriter: the risk, the terms requested, and what’s still missing.

StepsReady to run

  1. 1Read the submission materials
  2. 2Pull the verified record
  3. 3Check the underwriting guidelines
  4. 4List what’s still missing
  5. 5Write the overview

Template

docMarrowdene Submission Overview.docx

Every submission prepared on your guidelines,
and every call left to your underwriters.

Every submission reaches the workbench

Brokers keep sending to the address they use today. Agents read every email and attachment and put each new risk on the workbench.

Explore intake
WorkbenchSubmissions
Illustrative workbench: submissions on the desk with stage, verified fields, owner, and materials.
NameStage
Tollwick RoboticsNew submission
Vellowmere AnalyticsNew submission
Oakline PackagingUnderwriting
Ossendale ClinicsQuoting
Dornacre LogisticsBound
Selvenridge BiologicsNew submission
Prairie Grid EnergyUnderwriting
Wexholt DesignQuoting
Halvern MarineUnderwriting
Brightwater ClinicsNew submission

Built into a cited record

Agents fill each record from the package and cite every value to its source page. A value the documents don’t support is withheld or corrected, not guessed.

Explore the workbench

Drafted for your underwriter

Your workflows check each submission against your guidelines, compare similar bound policies, and draft the overview and indication on your templates, each term cited. Your underwriter reviews the draft and sets the terms.

Explore workflows
HomeDocumentsWorkstreamsWorkflows
Draft IndicationPublishedHistoryExport

Drafts an indication from the submission materials by Marrowdene's decision framework, guidelines, and referral authority.

Steps

1Read the submission
2Check the guidelines
3Compare bound policies
4Draft the indication
Add step

Linked resources

  • Decision frameworkThe positions your desk takes, drawn from its own work.
  • pdfMarrowdene Underwriting Guidelines.pdfAppetite, limits, and retentions by class.
  • docReferral Authority.docxWhich risks go to a senior underwriter.
  • xlsxBound Policies 2021 to 2025.xlsxFive years of the desk’s bound professional liability.
docDraft Indication.docxjust now

Indication

Tollwick Robotics LLC · Professional Liability

Limit
$5,000,000 each claim and aggregateSupplemental p. 2
Retention
$50,000Decision framework
Retroactive date
Aug 1, 2019Expiring Declarations
Exclusions
Contractual liability, as expiringEndorsement 4
Subjectivities
Copy of the hospital services contractCover Note

Your lead underwriter’s positions, applied

Lexcel reads your policies, quotes, and claims and drafts the positions your desk takes. Your lead underwriter confirms which govern, and every workflow applies them on each new risk.

How the decision framework works
Your firm’s work
Bound policies
1,284
Quotes
3,912
Claims
184
Endorsements
2,050
  • pdfWexholt Design, Policy 2025.pdf
  • pdfHollis Regional, Endorsement 7.pdf
  • docOakline, Quote 2024.docx
  • pdfOssendale, Claim 21-0418.pdf
  • pdfBrayford Systems, Policy 2023.pdf
Decision framework
  • Exclusion

    Contractual liability excluded where the insured indemnifies its clients

    Drawn from 31 bound policies
  • Retention

    $100,000 minimum where hospital or clinical work is over 15% of revenue

    Drawn from 18 bound policies
  • Referral

    Limits above $10M go to a senior underwriter

    Drawn from 46 quotes
  • Prior acts

    Retroactive date carried over from the expiring policy

    Drawn from 112 bound policies

Used in

Workbench · SubmissionsDraft IndicationSubmission Overview

A record of every submission,
yours to share with your capacity providers.

Every submission that reaches your inbox gets a record on the workbench, quoted or declined: each value cited to its source page, the drafts your workflows produced, and what your underwriters confirmed or corrected.

Capacity providers see what you bind and what becomes a claim. Your record shows every risk you saw and how your team handled it. It belongs to you: ask for any view of it, sync it to Salesforce, and share what you choose, when you choose.

Start with one line

Pick the line you write most. We set Lexcel up with your team on your own submissions, guidelines, and templates, and it writes into Salesforce, SharePoint, Box, and the other systems you already run.

Lexcel is built deepest in transactional liability and works across specialty lines where underwriting runs on documents. Add the next line when your team is ready.

Transactional liability on Lexcel

Who is Lexcel built for?

Specialty insurance teams: brokers, MGAs, underwriters, and carriers across specialty lines, including transactional liability: R&W, transactional tax, contingent liability, and secondary transaction insurance. Lexcel supports work across the lifecycle, from submission and underwriting through binding and claims, integrated with your systems and data sources.

Contact Lexcel to explore a pilot.

Can Lexcel write an underwriting summary from a submission?

Yes. A workflow reads every document in the submission package, checks it against your guidelines, and drafts the summary on your own template as a Word, Excel, or PowerPoint file, with each finding cited to the page it came from. Your underwriter reviews the draft and decides.

More: Specialty underwriting workflows .

What happens to a field the submission documents do not support?

Independent verifying agents confirm or refute each field against the cited source materials, and an unsupported value is withheld or corrected instead of written into the record. The underwriter can also confirm or correct a value directly on the workbench.

Can we see what the AI did before we rely on it?

Two different needs sit behind this question. Reviewers want each value to point back to a specific place, the page and the document, so they can confirm it themselves. They also want an inspectable work trace showing what materials were read, what was checked, and how an output was assembled, rather than a polished conclusion from a black box.

Separately, teams want the right record to land in the deal file for carrier file audits and claims, while retaining control over what becomes part of that file. What persists is the team's decision, not the platform's, because underwriters are deliberate about what belongs in a file.

Who owns the structured underwriting history?

The organization that produced the work product owns it. Agentic AI runs on that organization's materials, under its control. Claims history and internal analysis are among the categories of data that require the highest care.

Which specialty lines does this work for?

Specialty lines where the work runs on documents rather than a rating engine, which is most of the specialty market: submissions arrive as email with attachments, someone pulls the fields out by hand, and the judgment that follows comes from reading rather than scoring. Transactional liability is where the deepest work sits today, and it is a demanding proving ground precisely because the terms move deal to deal.

What does not travel between lines is the criteria, so workflows are built to the desk in question rather than ported from somewhere else. Teams that own several lines usually start with whichever one repeats most often, which is also the fastest way to learn whether the rest of the book is worth doing.

What does getting started actually involve for our team?

Most teams start with a pilot rather than a switch. The first stretch is setup and learning: standing up the workbench around the team's own fields and criteria, wiring the integrations into the systems already in use, building the orchestrations and workflows for the work that repeats, and spending enough time with the desk to learn how it actually quotes, reviews, and decides.

Then it runs on live deals, which is where the remaining gaps surface and get closed. A first draft of a workflow comes together quickly; what takes longer is the judgment, and the teams that get the most out of it put their own underwriters in the room while it is being built.

What does our IT team need to do to set up Lexcel?

Lexcel runs in the browser and is hosted by Lexcel on AWS, so there is nothing to install or maintain. For single sign-on, your IT team adds Lexcel as a SAML app in your identity provider, using the details Lexcel sends, and Lexcel sets up its side. Lexcel turns on the integrations you need, and an administrator connects each one from Lexcel. SharePoint and Outlook connect by signing in. Microsoft Teams may need your Microsoft administrator to approve the app first, and Salesforce needs your own Connected App's Consumer Key and Secret. Your own systems can also send submissions and bordereaux to Lexcel through its API, instead of by email.

Do we have to replace Salesforce or SharePoint to start an agentic underwriting workbench?

No. The workbench builds the record from your submission materials and syncs verified values into the system of record and document management system you already run.

More: How to Start an Agentic Underwriting Workbench Without Replacing Your System of Record .

Connects everywhere you work,
and to your own systems through our API.

  • Salesforce
  • Origami Risk
  • Applied Epic
  • Outlook
  • SharePoint
  • Box
  • Google Drive
  • OneDrive

Security and compliance

Built for enterprise security.

AICPA SOC for Service Organizations

SOC 2 Type II

Start with one process.
We’ll run it on Lexcel with you.

Bring a line of business or a review your team wants to move faster, and we’ll walk through it on the workbench, from the first email to your systems.