Question 1

What is an agentic underwriting workbench?

Accepted Answer

It is the database of a team's submissions, binds, and claim notices in which each record is built from information extracted from the package materials and verified against them rather than keyed in by hand. Every value carries the document behind it, the team's own workflows key off the record, and the underwriter keeps the final say. Full explanation: https://www.lexcel.ai/journal/what-is-an-agentic-underwriting-workbench/

Question 2

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

Accepted Answer

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.

Question 3

Does an agentic underwriting workbench replace the underwriter's judgment?

Accepted Answer

No. It produces cited fields and drafts so the underwriter can decide faster. Nothing binds or goes outbound until the underwriter reviews and confirms.

Question 4

Can underwriting and claims run on the same workbench?

Accepted Answer

Yes. Each has its own records, fields, and workflows, and when an underwritten deal becomes a claim the handoff can be set up so nobody rebuilds on the claims side what underwriting already verified.

Question 5

Who is Lexcel built for?

Accepted Answer

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.

Question 6

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

Accepted Answer

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: https://www.lexcel.ai/journal/how-to-start-an-agentic-underwriting-workbench-without-replacing-your-system-of-record/

Question 7

Can a team start with just claim notices, or just submissions?

Accepted Answer

Yes. A team can start with whichever one repeats often and add the other later.

Question 8

What does the benchmark study show?

Accepted Answer

Same M&A deal, side by side: Lexcel (1 attorney, 1.6 hours) vs. a four-attorney BigLaw team (100+ hours). Lexcel's unreviewed first draft surfaced more material findings on the same commercial contracts scope than the firm's polished final. Methodology and full results: https://www.lexcel.ai/journal/lexcel-vs-biglaw-benchmark/

Question 9

How does Lexcel pricing work?

Accepted Answer

Subscription pricing scoped to your team size, submission volume, and the lines you write. Contact sales for a quote tailored to your book.

Question 10

What does an organization get from a year of submissions on an agentic underwriting workbench?

Accepted Answer

A year of records against the same fields, which it can sort, filter, and query, with every value traceable to the document behind it. An organization that ran the same year through disconnected tools has a year of documents and nothing to query.

Question 11

What does Lexcel do with our historical policy and claims data?

Accepted Answer

Lexcel ingests archived policies, claims files, and notices, structures them, and surfaces the patterns that drive loss, so pricing, exclusions, and reserves are informed by your own book instead of industry averages. Your data stays your data. Lexcel does not train shared models on it and does not share signal across customers.

Question 12

Is institutional memory just a better document management system?

Accepted Answer

No. A document management system stores files. Institutional memory structures policies, quotes, and claims so the team can retrieve comparable work product with citations on a live matter, then review before anyone relies on it. More: https://www.lexcel.ai/journal/leveraging-institutional-memory-with-agentic-ai-in-specialty-underwriting/

Question 13

How do we keep outdated underwriting positions from becoming the new default?

Accepted Answer

By treating each use of history as its own call. Historical positions inform the live file rather than setting it by default, and every application of prior work is weighed against whether appetite, market practice, or the risk itself has moved since. The underwriter still reviews before any historical position drives a live quote or claim file.

Question 14

Who owns the structured underwriting history?

Accepted Answer

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.

Question 15

How do we trust automated extraction on a live quote or claim file?

Accepted Answer

Material pulls point back to source pages a reviewer can open, and the reviewer accepts or rejects before anything binds or goes outbound. Lexcel also runs extractions through a verification pipeline that checks each pull against the underlying materials before it reaches a reviewer. Trust comes from that verification trail, not from a vendor's promise that the AI is usually right.

Question 16

Where does Lexcel store customer files?

Accepted Answer

AWS S3. Each organization has its own bucket so policy, submission, and claims data does not mix with other customers' data.

Question 17

Is Lexcel SOC 2 certified?

Accepted Answer

Yes. SOC 2 Type II. Lexcel does not train on customer documents or use them to improve models.

Question 18

What AI models power Lexcel?

Accepted Answer

Primarily Claude, with support for swapping in OpenAI and others per task. Quality comes from line-specific tooling and a prompting architecture built for specialty insurance workflows, alongside the models.

FAQs

The workbench

Getting started

History and data

Security and trust