---
title: "Insurance AI data layer vs investigation agent: where Verisk's Claude connectors stop"
description: "Verisk put two governed data connectors inside Claude on May 5, 2026. MCP's own architecture documentation calls that the data layer. What happens after the data arrives is a different layer entirely."
date: "2026-09-09"
lastModified: "2026-11-16"
author: "Nitish Badu"
tags: ["Vendor Comparison"]
canonical: "https://gethesperai.com/blog/verisk-mcp-data-layer-vs-investigation-layer/"
---

# Insurance AI data layer vs investigation agent: where Verisk's Claude connectors stop

> **TL;DR** On May 5, 2026 Verisk exposed two connectors inside Anthropic's Claude, Verisk Underwriting Intelligence (ISO Indications) and Verisk XactRestore, so insurance professionals can query governed data conversationally. The Model Context Protocol's own architecture documentation calls that layer the data layer. The layer above it, which decides what a flagged claim needs, reconciles sources that contradict each other and writes a defensible finding, is still a person's job at every carrier in the market.
>
> - Verisk's Claude launch surface is 2 connectors, neither of them fraud data
> - MCP's own docs name the inner layer the data layer, not Hesper marketing
> - New York logged 52,105 fraud reports in 2024 against 316 investigations opened

- **52,105 → 316** - Reports of suspected fraud received vs new investigations opened, New York Insurance Frauds Bureau, 2024 (NY DFS Consumer Protection and Financial Enforcement 2024 Annual Report)
- **2 connectors** - Verisk's launch surface inside Claude: Underwriting Intelligence and XactRestore (Verisk newsroom, May 5, 2026)
- **~60 platforms** - Online marketplaces Digital Asset Finder monitors, against 8 billion+ indexed data points (Verisk and Legentic, August 21, 2025)
- **~25% → 100%** - Flagged-claim coverage, manual SIU vs an autonomous investigation layer (Hesper internal benchmarks)

A data layer makes information reachable. An investigation agent decides what to do with it. That vocabulary is not ours: the Model Context Protocol's own [architecture documentation](https://modelcontextprotocol.io/docs/2026-07-28/learn/architecture) calls its inner layer the data layer. Verisk's two Claude connectors do exactly what that layer does.

If you already pay Verisk, the practical question is whether this closes the investigation line item on your roadmap. It does not, and Verisk has not said it does. This is not a takedown. The question is what still has to happen after the data arrives.

This post extends our [three-layer model of prevention, detection and investigation](/blog/insurance-fraud-prevention-vs-detection-vs-investigation/) into protocol territory. For the vendor-level version, see our [Hesper and Verisk comparison](/blog/hesper-vs-verisk/).

## What Verisk actually shipped into Claude

Verisk's May 2026 collaboration with Anthropic exposes Verisk data to Claude through Model Context Protocol connectors, launching with two: Verisk Underwriting Intelligence, carrying ISO Indications loss costs, and Verisk XactRestore, carrying restoration and repair pricing. Both are query surfaces over governed data. Neither is a fraud product, and neither was presented as one.

The [announcement](https://www.verisk.com/company/newsroom/verisk-brings-its-trusted-analytics-and-generative-ai-capabilities-directly-into-anthropics-claude/) describes the mechanism this way: "Through MCP connectors, insurance professionals can access Verisk's proprietary, regulatory-grade data and analytics through generative AI, governed by Verisk's established data governance framework to support customers' controlled access and compliance needs."

Trade summaries compress this into "Verisk brings its analytics into Claude," and a claims reader can walk away believing ClaimSearch went into a chat window. It did not. ClaimSearch, ClaimDirector scoring and Xactimate estimating were not part of the launch surface.

> Trust is the foundation of insurance, and that doesn't change as new technologies emerge. What is changing is how professionals expect to interact with information.
>
> - Lee Shavel, President and CEO, Verisk, May 5, 2026

How professionals interact with information changed. What a professional has to do with the information after they get it did not.

## What MCP is, in the protocol's own words

The Model Context Protocol is an open-source standard for connecting AI applications to external systems. Its documentation compares it to a USB-C port for AI applications. Verisk built two servers and Claude is the host. That is the entire topology of the May announcement.

> MCP focuses solely on the protocol for context exchange.
>
> - Model Context Protocol architecture documentation, protocol version 2026-07-28. The same sentence goes on to state that MCP does not dictate how AI applications use LLMs or manage the context they are given.

Where the deciding happens is stated without ambiguity. When the language model decides to use a tool, the AI application intercepts the tool call, routes it to the appropriate MCP server, executes it, and returns the results back to the LLM. The choosing sits in the model and the host application. MCP is the wire.

An MCP tool can be called by an agent, not only by a person in a chat window. But exposing a capability over a protocol does not supply the thing that decides which capabilities a particular claim needs, in what order, and what to do when two of them disagree.

## The jobs between a data connection and a finished investigation

Between a reachable data source and a resolved claim sit four distinct jobs: access, invocation, orchestration and judgement. A protocol handles the first two. Since the Verisk connectors run inside Claude, Anthropic's own definitions are the fairest yardstick for the rest.

[Building effective agents](https://www.anthropic.com/engineering/building-effective-agents) defines workflows as "systems where LLMs and tools are orchestrated through predefined code paths," and agents as "systems where LLMs dynamically direct their own processes and tool usage, maintaining control over how they accomplish tasks." Anthropic recommends MCP for integrating third-party tools, so MCP sits underneath workflows and agents alike. It is the augmentation channel, not the autonomy.

Anthropic also states when an agent is the right design: open-ended problems where you cannot predict the number of steps or hardcode a fixed path. A flagged claim is the textbook instance. A marketplace listing hit turns a total-loss file into a title-history file. The path is discovered, not scheduled.

Hesper runs [15+ investigation phases in parallel](/blog/parallel-processing-siu-investigation-phases/) on every flagged claim, then reconciles what those phases return into a single documented finding. The design behind it is in our breakdown of [AI agent architecture for claims investigation](/blog/ai-agent-architecture-claims-investigation/).

## Where Verisk does automate investigative work

Verisk automates specific investigative checks and runs them continuously. Its [August 21, 2025 launch](https://www.verisk.com/company/newsroom/verisk-unveils-new-claimsearch-tools-to-detect-digital-commerce-and-locate-assets-in-insurance-investigations/) of Digital Commerce Detector and Digital Asset Finder, through an alliance with Legentic, monitors nearly 60 online platforms against more than 8 billion indexed open-source data points. Neither tool waits for a human to commission a scan. That is the strongest counter-example to everything above.

Digital Commerce Detector compares claim details including VINs against current and archived online sale listings. As early as first notice of loss, total loss claims can be flagged for further investigation based on attempts to sell those vehicles or their parts. Digital Asset Finder works the other end of the lifecycle, locating assets after settlement for recovery and subrogation.

Concede the point plainly, because it is real. This is automated investigative work with no human commissioning each scan. Verisk's own phrasing also draws the boundary: the output is a claim flagged for further investigation. Our [auto claims use case](/use-cases/auto-claims/) covers the VIN, total-loss and staged-accident patterns these tools touch.

## One standing question is not an investigation

The line between a monitoring tool and an investigation is scope and arbitration, not automation. A monitoring tool answers one standing question against one evidence class, continuously and well. An investigation decides which questions a specific claim raises, runs them together, and resolves what happens when two of the answers contradict each other.

Take the case where the tool works perfectly. Digital Commerce Detector matches a VIN on a total-loss file against an archived marketplace listing. That hit is a lead, and a good one. Here is what has to happen next:

- Pull and timestamp the listing history before it disappears
- Establish whether the listing is the whole vehicle or a parts teardown
- Reconcile the posting date against the reported date of loss
- Compare it against the insured's recorded statement about where the vehicle was
- Check tow and salvage records, and whether the seller account ties to any party on the claim
- Decide whether the combination supports a referral, an examination under oath, or nothing at all
- Write it up so a state examiner reading the file in eighteen months can follow the conclusion

Verisk's own phrasing draws the boundary: the output is a claim flagged for further investigation. Detection is upstream; investigation is downstream.

**Figure 1 (After the hit) - The tool answered its question. Everything after the hit is the investigation.** What has to happen once Digital Commerce Detector matches a VIN on a total-loss file, before anyone can decide.

The hit: VIN match on an archived listing (Total_loss_file.pdf, Listing_archive.html, Recorded_statement.mp3)

**Agent legwork** (Logged, sourced, timestamped)

1. Capture and timestamp the listing history before it disappears
2. Establish whole vehicle or parts teardown
3. Reconcile the posting date against the reported date of loss
4. Cross-reference the recorded statement on where the vehicle was
5. Check tow and salvage records and seller-account ties to parties

15+ investigation phases in parallel

Hand-off: Evidence file

**SIU lead decides** (A named human, every decision)

- Referral
- Examination under oath
- No further action, documented

Agent recommends. SIU lead signs.

Source: Illustrative decision-rights map built from the steps listed in this post. The hit is the output Verisk describes as a claim flagged for further investigation; every step after it is currently a person's calendar entry.

(Illustrative example)

None of that is a criticism of the tool. The tool answered its question. The list above is the investigation, and every item on it is currently a person's calendar entry. That is where 14+ days per case comes from, and it is why an investigator carrying 200+ open cases completes roughly 10 investigations a month.

On [July 23, 2026](https://insurance-edge.net/2026/07/23/weightmans-teams-up-with-verisk-on-anti-fraud-data/), UK law firm Weightmans and Verisk launched Fraud Rely, joining Weightmans' proprietary fraud database and counter-fraud legal expertise to Verisk's detection, matching and intelligence capability. Fraud Rely widens the pool of things that can be matched. It does not change who resolves a match once one lands.

The strongest counter-argument comes from Carpe. Its [July 21, 2026 Carpe Claims launch](https://carpe.io/resources/press/carpe-launches-carpe-claims/) states that "a carrier's own AI systems can order an investigation, monitor a claimant, question the findings, and route the results without a human touching a screen." That is a real architectural step. It is also a procurement action.

But Carpe's own Investigative Reports page schedules fulfilment at one to four days with human analyst verification, as we documented in [Carpe Data alternatives: ordering an investigation is not running one](/blog/carpe-data-alternatives/).

*Figure: The data arrives in a second. What it means is still sitting in someone's queue.*

## Everyone is building the seat

Five insurance MCP moves shipped between February and July 2026: One Inc, Duck Creek, Verisk, ACORD Solutions Group and Carpe. All five expose data, transactions or service orders. Four of the five explicitly keep a human or the carrier's own orchestrator in the deciding seat. That is an observation about the market, not a claim about any one vendor.

| Vendor | Date | What went over the protocol | Who holds the deciding seat |
| --- | --- | --- | --- |
| One Inc | February 3, 2026 | PremiumPay and ClaimsPay, running inside the customer's own approved AI environment | The carrier's own AI environment and its people |
| Duck Creek | April 28, 2026 | AI Gateway supporting MCP and A2A, to register Duck Creek, partner and customer-built agents | Whichever agent the carrier deploys into the gateway |
| Verisk | May 5, 2026 | Underwriting Intelligence (ISO Indications) and XactRestore, into Claude | The professional asking, with accountability remaining with people |
| ACORD Solutions Group | May 28, 2026 | ADEPT and ACORD Transcriber, over an MCP-enabled architecture | Agents operating within defined compliance, validation and audit controls |
| Carpe | July 21, 2026 | Online Injury Alerts and Investigative Reports, headless and MCP-native | The carrier's agent orders; a human analyst fulfils |

[Duck Creek's Agentic AI Platform](https://www.prnewswire.com/news-releases/duck-creek-launches-insurance-native-agentic-ai-platform-and-unveils-new-applications-to-transform-underwriting-and-claims-302755119.html) is the most architecturally ambitious of the five. Its named claims application is Agentic FNOL: capture, validate and route at intake. Duck Creek is building the orchestration seat inside the core system, upstream of the flagged claim.

Put the five together: nobody has shipped an MCP-callable thing that reasons across contradictory evidence and writes a defensible finding on a flagged claim. We reached the same conclusion in [agentic AI for insurance claims, where eight of nine agents talk and one investigates](/blog/agentic-ai-insurance-claims-beyond-fnol/), and mapped the gap in our [claims automation guide](/blog/claims-automation-pillar/).

Duck Creek and ACORD are a tailwind rather than a threat. A governed agent gateway is the deployment surface for an investigation agent. Building the seat is genuinely useful work. It is just not the same work as supplying the investigator who sits in it.

## What the gap costs while the plumbing improves

Better access to data does not change how many flagged claims get worked. The clearest public illustration is New York's Insurance Frauds Bureau, where reports received rose from 30,113 in 2020 to 52,105 in 2024, a 73% increase, while new investigations opened moved from 324 to 316, a 2.5% decline. Input scaled. Investigative capacity did not.

| New York Insurance Frauds Bureau, 2020-2024: bar length is reports of suspected fraud received; the label carries new investigations opened that year | Value | Share |
| --- | --- | --- |
| 2020 - 324 new investigations opened | 30,113 reports | 58% |
| 2021 - 283 new investigations opened | 34,201 reports | 66% |
| 2022 - 279 new investigations opened | 38,554 reports | 74% |
| 2023 - 341 new investigations opened | 44,998 reports | 86% |
| 2024 - 316 new investigations opened | 52,105 reports | 100% |

Those figures come from Appendix 1 of the [New York Department of Financial Services Consumer Protection and Financial Enforcement Division 2024 Annual Report](https://www.dfs.ny.gov/system/files/documents/2025/03/nysdfs-2024-cpfed-annual-rpt-20250315.pdf). One caveat: the 52,105 are reports insurers sent to the state, and the 316 are cases the state opened. This is not carrier SIU coverage. It illustrates the same pattern that shows up inside a carrier.

| Jurisdiction and unit | Period | Referrals received | Cases opened or assigned | Arrests |
| --- | --- | --- | --- | --- |
| New York Insurance Frauds Bureau, all units | 2024 | 52,105 | 316 | 227 |
| New York Medical and No-Fault Unit | 2024 | 41,686 | 71 | Not reported separately |
| New York Auto Unit | 2024 | 5,451 | 97 | Not reported separately |
| California Fraud Division, automobile program | FY2023-24 | 12,559 | 602 | 272, plus 354 cases referred to prosecutors |

The Medical and No-Fault row is the most extreme: 41,686 reports received in 2024 against 71 investigations opened. California tells the same story. In fiscal year 2023-24 the [California Department of Insurance Fraud Division](https://www.insurance.ca.gov/0300-fraud/0100-fraud-division-overview/10-anti-fraud-prog/Automobile.cfm) received 12,559 suspected fraudulent claims in its automobile program and assigned 602 new cases.

**Figure 2 (Input vs capacity) - Reports to New York's fraud bureau rose 73%. Investigations opened fell 2.5%.** Better detection, matching and monitoring raise what arrives at the investigation layer; they do not raise what gets worked.

**Investigations opened: down**

- New investigations opened, 2020 to 2024: -2.5% (324 in 2020, 316 in 2024)
- Medical and No-Fault Unit: 41,686 reports received in 2024 against 71 investigations opened

**Reports received: up**

- Reports of suspected fraud received, 2020 to 2024: +73% (30,113 in 2020, 52,105 in 2024)
- Worth the work: Insurers reported $3.5 billion in SIU savings in 2023, plus $40.3 million in recoveries

**Takeaway:** Adding a connector changes how fast a person can look something up, not how many flagged claims get worked.

Source: NY DFS Consumer Protection and Financial Enforcement Division 2024 Annual Report, Appendix 1 (published March 15, 2025), 2020 vs 2024. State bureau figures: reports insurers sent to the state and cases the state opened, not carrier SIU coverage.

None of this says the work is not worth doing. The same New York report states that insurers reported $3.5 billion in savings resulting from SIU investigations in 2023, the most recent year available, plus $40.3 million in recoveries. Investigation returns money. There is simply a hard ceiling on how much of it any staffed unit can do.

For a claims VP: adding a connector changes how quickly a person can look something up, not how many flagged claims get worked. Manual SIU runs 14+ days per case, which is why carriers fully investigate about 25% of flagged claims. Compress the cycle to minutes rather than weeks and coverage goes to 100%. Those are Hesper internal benchmarks; the model is on our [coverage and cost calculator](/roi/).

> **Where Hesper sits, stated plainly**
>
> Hesper AI takes a flagged claim, runs 15+ investigation phases in parallel, reconciles what they return, and produces an audit-ready finding in minutes instead of 14+ days. Hesper is complementary to FRISS, Shift Technology, and Verisk - not a replacement. It has built-in fraud detection and works standalone. The SIU lead still signs the finding.

## How to tell which layer a vendor is selling

Seven layers sit between a record in a database and a documented investigative conclusion. Most vendor confusion comes from comparing products that occupy different rows as though they were competing for the same one.

| Layer | What it does | Who acts | What it outputs | Where it stops |
| --- | --- | --- | --- | --- |
| System of record and data utility (ISO ClaimSearch, Xactimate, ISO Indications, Legentic listings index) | Holds records, prices, matches and scores | The carrier's system, on a schedule or on submission | A record, a match, a score, a price | It knows what is in the data. It does not know what this claim needs |
| Access protocol (MCP) | Standardizes how an AI application discovers and calls tools and reads resources over JSON-RPC 2.0 | Nobody. It is a wire format | A tool result, returned to whoever asked | It moves context. It does not decide anything |
| Assistant with connectors (Verisk data inside Claude) | Lets a professional query governed data in natural language, in one window | A human, asking | An answer in a conversation | The human sets the goal, judges the answer and carries it into the file |
| Continuous monitoring tool (Digital Commerce Detector, Digital Asset Finder, Online Injury Alerts) | Runs one standing query against one evidence class, continuously | The tool, autonomously, within its scope | A flag, an alert, a hit, flagged for further investigation | One question, one evidence class. It does not reconcile its hit against contradicting evidence |
| Agent-callable service (Carpe Claims over MCP) | Lets a carrier's own AI order a service without a screen | The carrier's agent orders; a human analyst fulfils | A commissioned report, delivered later | Ordering is not running. Someone still fulfils, reconciles and concludes |
| Orchestration platform (Duck Creek AI Gateway, ACORD ADEPT) | Registers, routes and governs agents across the lifecycle | Whichever agent the carrier deploys into it | A governed execution path | It provides the seat. It does not supply the investigator who sits in it |
| Investigation agent (Hesper) | Decides which checks a flagged claim needs, runs 15+ phases in parallel, resolves contradictions, writes the finding | The agent, end to end, with a human SIU lead reviewing | An audit-ready investigative report with sources, reasoning and timestamps | Adjudication. The SIU lead and the adjuster make the call |

Four questions tell you which row a vendor occupies, and all four can be asked in a demo. They interrogate the artefact at the end, which is what a state examiner eventually reads.

1. Who decides which checks this claim needs, your system or my staff? If the answer is your staff, you are buying a data layer. That is a legitimate purchase, just not investigative capacity.
2. What happens when two of your sources disagree with each other? Ask to see it on a real file, not on a slide.
3. What is the artefact at the end: a result, a report, or a documented decision with its reasoning attached? Only the third one closes anything.
4. If a state examiner pulls this file in eighteen months, what does the record show about how the conclusion was reached?

The fourth question is where most stacks come apart, because the chain usually reconstructs from a completion date and a disposition code typed in after the fact. That is the standard we wrote up in [the defensibility standard for fraud investigation AI](/blog/fraud-investigation-ai-defensibility-standard/). Logging is a design decision made before the first phase runs, not a report generated afterward.

**Figure 3 (Procurement test) - Four demo questions separate a data connection from an investigation agent.** Each question interrogates the artefact at the end, which is what a state examiner eventually reads.

|  | Who decides the checks | Two sources disagree | The artefact at the end | An examiner pulls the file |
| --- | --- | --- | --- | --- |
| Data layer (Utility, connector, monitor) | Your staff | Your staff arbitrates | A result or a report | A completion date and a disposition code |
| Investigation agent (SIU lead reviews) | The agent, claim by claim | Resolved, both sources cited | A documented finding with its reasoning | Sources, order, returns and conclusion |

**Takeaway:** Logging is a design decision made before the first phase runs, not a report generated afterward.

Source: Questions as set out in this post. Answers describe the layer, not any one vendor: data layers are a legitimate purchase, they just do not add investigative capacity.

Nothing here argues that a carrier should buy fewer data layers. They are worth what they cost. They just do not add investigative capacity, so do not score them against that line in a procurement memo. For that memo, our [rundown of Verisk alternatives](/blog/verisk-alternatives/) covers the detection shortlist and the [2026 AI fraud platforms buyer's guide](/blog/ai-fraud-platforms-compared-2026-pillar/) maps prevention, detection and investigation vendor by vendor.

The honest read is that Verisk shipped a useful thing and described it accurately, with accountability remaining with people. Take that clause literally. Every hour of investigative work behind that accountability is still a person's hour, and the queue those hours are drawn from keeps getting longer.

## Key takeaways

- Verisk's May 5, 2026 launch put two MCP connectors inside Claude: Verisk Underwriting Intelligence (ISO Indications) and Verisk XactRestore. Neither is fraud-facing.
- The data layer framing is the protocol's own vocabulary. MCP's architecture documentation states that it focuses solely on the protocol for context exchange.
- Verisk does automate investigative work through Digital Commerce Detector and Digital Asset Finder, and its own description of the output is a claim flagged for further investigation.
- New York's Insurance Frauds Bureau received 52,105 reports of suspected fraud in 2024 and opened 316 new investigations. Referral volume scales with automation; investigative capacity does not.

## Frequently asked questions

### What is the difference between an AI data layer and an AI investigation agent in insurance?

A data layer makes information reachable. An investigation agent decides what to do with it. Verisk's May 2026 MCP connectors are a data layer. An investigation agent sits above that. It decides which checks a flagged claim needs, runs them in parallel, reconciles sources that contradict each other, and produces an audit-ready finding a human reviews.

### If our carrier already uses Verisk, do we still need an investigation layer?

Yes, because they solve different problems. Verisk supplies data, matching, scoring, pricing and targeted monitoring. None of that changes how many flagged claims a Special Investigations Unit can work in a month. Detection is upstream; investigation is downstream. Hesper is complementary to Verisk, not a replacement.

### How do you tell whether a vendor sells a data layer or an investigation layer?

Ask four questions in the demo. Who decides which checks this claim needs, your system or my staff? What happens when two of your sources disagree? What is the artefact at the end: a result, a report, or a documented decision with its reasoning attached? If a state examiner pulls this file in eighteen months, what does the record show about how the conclusion was reached?

### What does an AI investigation agent do that a data connector does not?

It takes a flagged claim and runs the SIU playbook end to end. Hesper runs 15+ investigation phases in parallel, reconciles what those phases return and produces an audit-ready report with sources, reasoning and timestamps attached. Manual SIU investigation runs 14+ days per case; the agent works in minutes, not weeks. The human SIU lead still reviews the finding and makes the adjudication call.
