Sixfold Content
Product Update
Sixfold Expands Underwriting Brain: AI to Research, Reason & Document
Over the past 2+ years, we've built an AI underwriting brain that evaluates risk based on each insurer's specific risk appetite. Now we're expanding its capabilities with agentic research that provides better insights, case notes that connects patterns, and documentation that's actionable and audit-ready.
Explore all Resources
Stay informed, gain insights, and elevate your understanding of AI's role in the insurance industry with our comprehensive collection of articles, guides, and more.
Research Agent: From Hours of Digging to Seconds of Insights
Meet Research Agent, underwriters’ new research partner. It spots the gaps in a submission, finds the missing details, and delivers the insights that matter most for the decision.
In commercial underwriting, submissions rarely contain everything underwriters need to properly assess risks. Critical information such as SEC filings, cyber incidents, litigation history, or executive misconduct aren't in the application, and finding that data falls on the underwriter.
The stakes are high: miss one key detail, and underwriters are suddenly pricing a completely different risk. The research to uncover this information means hours going through public sources such as news archives and databases.
All while brokers demand quotes fast in an increasingly competitive market.
Why We Built it
With Research Agent, underwriters have a research partner who finds the gaps in the submission, locates the missing pieces, and brings back the insights that matter for the decision.
The agent does the external research work on the underwriter’s behalf. By filling critical information gaps and applying research from the public web and connected third-party data sources into Sixfold’s overall risk assessment, underwriters are given a complete risk picture for more precise appraisal. Underwriters can view the exact origin of any piece of information, with clickable links that take them directly to the original source for verification or further detail.
The result? Quotes go out faster, underwriters make more consistent calls, and decisions get made without wondering what might have been missed.
“Research Agent has been one of our most anticipated features, especially for customers in specialty lines with complex cases where extensive research is needed to get a complete picture of the risk.
We expect the agent to save them at least two hours per submission.”
- Alex Schmelkin, Founder & CEO at Sixfold
When Research Makes Or Breaks The Quote
.png)
Sixfold’s Research Agent is designed to support commercial lines of business where external data is essential in risk evaluation and quoting. Lines of business we’re seeing the highest demand for include:
General Liability - Public web research to capture OSHA violations, litigation history, and negative press coverage
Cyber - 3rd party cyber threat intelligence plus broader public web research for cyber breach disclosures and corporate litigation involving cybersecurity lapses
E&S Property - Public and/or 3rd party data on location and climate based risks (flood, wildfire, crime, etc.), permit history, and company mentions in the news
Directors & Officers (D&O) - News on executive misconduct, class-action lawsuits, SEC filings, and shareholder news
Healthcare & Life Sciences - Public records of malpractice lawsuits, regulatory actions, patient safety concerns, and news coverage related to clinical trials or product safety
While Competitors Prep, You Price
Research Agent delivers wins across the board, immediate time savings for underwriters and competitive advantages insurers.
“We’re seeing growing demand for research-heavy underwriting. With this launch, we accelerate the time to quote while elevating decision-making with richer context.”
- Lana Jovanovic, Head of Product at Sixfold
Focus on what matters: Those hours gained back per case? That's time underwriters can spend on what they do best: making smart risk decisions, strengthening broker relationships, and building customer connections instead of drowning in research tasks.
Speed wins deals: Reduced manual research burden means underwriters can respond faster to brokers, increase their quote volume, and capture more bound premiums. For carriers competing on both responsiveness and quality, this means winning more of the right business.
Same quality, every time: Every underwriter now has access to the same thorough research process. No more inconsistency based on who's handling the case or how much time they have to dig. Better decisions, whether it's one case or a thousand.
Improved portfolio performance: Sixfold’s comprehensive risk assessment, now with the added capability of public web research and connected third-party data, equips underwriters with a deeper understanding of each risk.
Contact Sixfold to see the Research Agent in action.
Sixfold's Approach to AI Fairness & Bias Testing
As AI becomes more embedded in insurance underwriting, ensuring fairness is a shared responsibility across carriers, vendors, and regulators. Sixfold's commitment to responsible AI means continuously exploring new ways to evaluate bias.
As AI becomes more embedded in the insurance underwriting process, carriers, vendors, and regulators share a growing responsibility to ensure these systems remain fair and unbiased.
At Sixfold, our dedication to building responsible AI means regularly exploring new and thoughtful ways to evaluate fairness.1
We sat down with Elly Millican, Responsible AI & Regulatory Research Expert, and Noah Grosshandler, Product Lead on Sixfold's Life & Health team, to discuss how Sixfold is approaching fairness testing in a new way.
Fairness As AI Systems Advance
Fairness in insurance underwriting isn’t a new concern, but testing for it in AI systems that don’t make binary decisions is.
At Sixfold, our Underwriting AI for life and health insurers don’t approve or deny applicants. Instead, it analyzes complex medical records and surface relevant information based on each insurer's unique risk appetite. This allows underwriters to work much more efficiently and focus their time on risk assessment, not document review.
“We needed to develop new methodologies for fairness testing that reflect how Sixfold works.”
— Elly Millican, Responsible AI & Regulatory Research Expert
While that’s a win for underwriters, it complicates fairness testing. When your AI produces qualitative outputs such as facts and summaries, rather than scores and decisions, most traditional fairness metrics won’t work. Testing for fairness in this context requires an alternative approach.
“The academic work around fairness testing is very focused on traditional predictive models, however Sixfold is doing document analysis,” explains Millican. “We needed to develop new methodologies for fairness testing that reflect how Sixfold works.”
“The academic work around fairness testing is very focused on traditional predictive models, however Sixfold is doing document analysis,” explains Millican. “We needed to develop new methodologies for fairness testing that reflect how Sixfold works.”
“Even selecting which facts to pull and highlight from medical records in the first place comes with the opportunity to introduce bias. We believe it’s our responsibility to test for and mitigate that,” Grosshandler adds.
While regulations prohibit discrimination in underwriting, they rarely spell out how to measure fairness in systems like Sixfold’s. That ambiguity has opened the door for innovation, and for Sixfold to take initiative on shaping best practices and contributing to the regulatory conversation.
A New Testing Methodology
To address the challenge of fairness testing in a system with no binary outcomes, Sixfold is developing a methodology rooted in counterfactual fairness testing. The idea is simple: hold everything constant except for a single demographic attribute and see if and how the AI’s output changes.2
“Ultimately we want to validate that medically similar cases are treated the same when their demographic attributes differ,”
— Noah Grosshandler, Product Manager @Sixfold
“We start with an ‘anchor’ case and create a ‘counterfactual twin’ who is identical in every way except for one detail, like race or gender. Then we run both through our pipeline to see if the medical information that’s presented in Sixfold varies in a notable or concerning way” Millican explains.
“Ultimately we want to validate that medically similar cases are treated the same when their demographic attributes differ,” Grosshandler states.
Proof-of-Concept
For the initial proof-of-concept, the team is focused on two key dimensions of Sixfold’s Life & Health pipeline.
1. Fact Extraction Consistency
Does Sixfold extract the same facts from medically identical underwriting case records that differ only in one protected attribute?
2. Summary Framing and Content Consistency
Does Sixfold produce diagnosis summaries with equivalent clinical content and emphasis for medically identical underwriting cases?
“It’s not just about missing or added facts, sometimes it’s a shift in tone or emphasis that could change how a case is perceived,” Millican explains. “We want to be sure that if demographic details are influencing outputs, it’s only when clinically appropriate. Otherwise, we risk surfacing irrelevant information that could skew decisions.”
Expanding the Scope
While the team’s current focus is on foundational fairness markers (race and gender), the methodology is designed to evolve. Future testing will likely explore proxy variables such as ZIP codes, names, and socioeconomic indicators, which might implicitly shape model behavior.
“We want to get into cases where the demographic signal isn’t explicit, but the model might still infer something. Names, locations, insurance types, all of these could serve as proxies that unintentionally influence outcomes,” Millican elaborates.
The team is also thinking ahead to version control for prompts and model updates, ensuring fairness testing keeps pace with an evolving AI stack.
“We’re trying to define what fairness means for a new kind of AI system,” explains Millican. “One that doesn’t give a single output, but shapes what people see, read, and decide.”
Sixfold isn’t just testing for fairness in isolation, it’s aiming to contribute to a broader conversation on how LLMs should be evaluated in high-stakes contexts like insurance, healthcare, finance, and more.
That’s why Sixfold is proactively bringing this work to the attention of regulatory bodies. By doing so, we hope to support ongoing standards development in the industry and help others build responsible and transparent AI systems.
“This work isn’t just about evaluating Sixfold, it’s about setting new standards for a new category of AI." Grosshandler concludes.
“This work isn’t just about evaluating Sixfold, it’s about setting new standards for a new category of AI. Regulators are still figuring this out, so we’re taking the opportunity to contribute to the conversation and help shape how fairness is monitored in systems like ours,” Grosshandler concludes.
Positive Regulatory Feedback
When we recently walked through our testing methodology and results with a group of regulators focused on AI and data, the feedback was both thoughtful and encouraging. They didn’t shy away from the complexity, but they clearly saw the value in what we’re doing.
“The fact that it’s hard shouldn’t be a reason not to try. What you’re doing makes sense... You’re scrutinizing something that matters.” said one senior policy advisor.
“The fact that it’s hard shouldn’t be a reason not to try. What you’re doing makes sense... You’re scrutinizing something that matters.”
— Senior Policy Advisor
One of the key themes that came up during the meeting was the unique nature of generative AI, and why it demands a different kind of oversight. As one senior actuary and behavioral data scientist put it: “Large language models are more qualitative than quantitative... A lot of technical folks don’t really get qualitative. They’re used to numbers. The more you can explain how you test the language for accuracy, the more attention it will get.”
That comment really resonated. It reflects the heart of our approach, we’re not just tracking metrics. We’re evaluating how language evolves, how facts can shift, and how risk is framed and communicated depending on the inputs.
The Road Ahead
Fairness in AI isn’t a fixed destination, it’s an ongoing commitment. Sixfold’s work in developing and refining fairness and bias testing methodologies reflects that mindset.
As more organizations turn to LLMs to analyze and interpret sensitive information, the need for thoughtful, domain-specific fairness methods will only grow. At Sixfold, we’re proud to be at the forefront of that work.
Footnotes
1While internal reviews have not surfaced evidence of systemic bias, Sixfold is committed to continuous testing and transparency to ensure that remains the case as we expand and refine our AI systems.
2To ensure accuracy, cases involving medically relevant demographic traits, like pregnancy in a gender-flipped case, are filtered out. The methodology is designed to isolate unfair influence, not obscure legitimate medical distinctions.
Meet Narrative: Your Shortcut to Risk Documentation
Sixfold’s latest launch introduces Narrative, a feature that helps underwriters document risk faster and more consistently. First rolled out with Zurich’s North America Middle Market team, Narrative is already helping standardize how risk is communicated across the organization.
No one became an underwriter because they love writing case documentation. But that’s where a huge amount of time goes today. Referral notes, peer review memos, audit documentation, written and rewritten, case after case.
- A single case can take an hour, often several hours, to document.
- Multiply that across a typical team handling hundreds of submissions each week. The result is thousands of hours spent each year on documentation alone.
- Underwriters are doing this work while balancing dozens of other tasks: reviewing new submissions, responding to brokers, preparing quotes, and managing existing accounts.
80% Automation, 20% Judgment
Sixfold’s Narrative feature automates and standardizes how risk is communicated across the organization. It automatically generates a risk narrative that matches each insurer’s appetite, tone and format, while giving underwriters the flexibility to apply their own judgment where it matters.
See below for a quick product walkthrough from Shirley Shen, Senior Product Manager @Sixfold:
The Narrative feature is built to:
1. Align with the insurer’s unique risk appetite
2. Surface key facts and risk insights that matter most
3. Adhere to required documentation standards and formats
“Think of all the documents underwriters have to create for administrative purposes. Anything that requires them to synthesize the risk overall. Sixfold is doing 80% of that now: bringing together all the facts. Then the underwriter just adds the last 20%, the judgment call.”
- Laurence Brouillette, Head of Customers and Partnerships @Sixfold
Proven with Zurich’s North America Team
The Narrative feature was developed and validated through the 2024 Zurich Innovation Championship (ZIC).
Over a 6-week sprint with Zurich’s North America Middle Market team, Sixfold:
- Partnered with 16 underwriters and was used in 80%+ of their live submissions
- Processed nearly 4,000 pages of submission and web data
- Achieved an average of 60 minutes time savings per submission
Following this success, Narrative is now rolling out across Zurich’s U.S. offices.
"We launched with four Zurich Middle Market offices in January 2025 and are now expanding Sixfold to dozens more offices countrywide.”
- Amy Nelsen, Head of Underwriting Operations, U.S. Middle Market @Zurich North America
How Zurich gives underwriters time back with Sixfold — featured in The Insurer.
AI That Actually Gets Used
Narrative is a great starting point for insurers looking to bring AI into underwriting workflows today. It takes the repetitive parts of the job off underwriters’ hands without requiring them to change how they already work.
“Sixfold streamlines the way underwriters receive information on new submissions, offering a holistic and simplified overview of a business’s operations and exposures right from the point of entry into our workflow.”
- Madison Chapman, Senior Middle Market Underwriter @Zurich North America
How Sixfold is transforming underwriting for Zurich’s U.S. Middle Market team.
When underwriters experience that impact immediately, with fewer hours spent writing up cases and fewer rounds of revisions, adoption happens easily. AI becomes part of the flow of work because it genuinely makes the day-to-day tasks so much easier.
Get in touch to see how Sixfold fits your underwriting workflow.
Sixfold Partners with Mphasis to Simplify Integration
Sixfold and Mphasis are teaming up to make AI in insurance underwriting faster to deploy and easier to use, helping insurers grow without delays.
Implementing new AI technology in your underwriting workflow can be a challenge. Between IT team bandwidth and integration complexities, getting a new workflow up and running smoothly takes time.
At Sixfold, we’re all about making underwriters’ lives easier and speeding up the quote process. So, of course, we want to make implementing our platform just as smooth and just as fast. One way to do that? Partner with experts who know operations & technology inside and out. That’s where Mphasis comes in.
Meet Mphasis
If you haven’t heard of them, think of Mphasis as a company that helps insurance carriers streamline operations, integrate technology, and make their day-to-day workflows simpler. Basically, they’re the experts at making complex systems work together, which makes this partnership a win-win for everyone involved.
Mphasis will integrate Sixfold’s platform to help carriers deliver faster, more confident quotes by giving underwriters contextual risk insights tailored to each insurer’s unique appetite.
“Mphasis is excited to partner with Sixfold to accelerate AI adoption in the insurance industry. By leveraging Sixfold’s AI expertise, Mphasis enhances its insurance technology capabilities to deliver advanced, data-driven automation solutions for global insurers, driving efficiency, accuracy, and innovation across the insurance value chain.”
- Nitin Rakesh, Chief Executive Officer and Managing Director, Mphasis
When it comes to new tech, speed to value matters and no one wants a slow start. With Mphasis, we’re making sure insurers can start seeing value from their Sixfold integration faster.
This partnership is about improving insurance underwriting and speeding up implementation, enabling insurers to scale quicker and stay ahead of the challenges in today’s market.
Read more about the partnership on Yahoo Finance, Life Insurance International and Fintech Finance.
.png)
New in Life & Disability: Track Sources & New Changes
Sixfold’s latest launch introduces two new features for Life & Disability underwriters: with In-line Citations and New Case Facts, underwriters can easily trace where each fact came from and quickly spot what’s new in a case, making reviews faster, clearer, and more efficient.
Check Sources Instantly
Trust and transparency are essential when underwriters use AI in their daily work. Underwriters need to know that the information they rely on is accurate; otherwise, a policy decision could result in incorrect coverage, claims issues, or unnecessary risk for the carrier.
One of the best ways to build that confidence is by clearly showing the source of each piece of information. That’s why we’re excited to introduce a new In-line Citations feature for our Life & Disability customers. This feature makes it easy to check the source behind any insight Sixfold surfaces.
So, how does it work?
When reviewing a case in Sixfold, underwriters can now see exactly where each fact came from, including the document and page number. Here’s what you’ll see when clicking into a fact card:
- Document category listed for each file.
- Page number shown on hover
- One-click access to the exact source page
- All of the documents where the fact was found
Our goal? To increase underwriter confidence and efficiency by clearly showing the source of medical and lifestyle facts within the insurance application analysis.
New Info? Now Flagged for You
In Life and Disability underwriting, it’s common for some cases to take time, sometimes weeks, to gather all the documents needed for final analysis. The result? A lot of new information is coming in, and it’s not always clear what’s actually new facts.
That’s where our new capability, New Case Facts comes in.
Now, when new facts are surfaced within a case, you’ll see a bell icon next to the relevant fact card, a simple way to flag which facts came from the latest documents added. You can click into the fact to see more context, including which document category it came from.
This makes it easier to understand what’s been added, without having to reread the whole submission. It’s especially useful when multiple underwriters are collaborating on a case; one might start the analysis, while a colleague might actually finish it.
With new facts clearly marked, everyone can stay aligned and quickly assess what’s different and what it means for the overall risk profile of the applicant.
What is MCP - and Why It Matters for Underwriting
At Sixfold, we always integrate the latest AI advancements, but only when they truly help make underwriting faster, easier, and more accurate. One of the most promising technologies we’re exploring right now is Model Context Protocol, or MCP.
At Sixfold, we always integrate the latest AI advancements, but only when they truly help make underwriting faster, easier, and more accurate. One of the most promising technologies we’re exploring right now is Model Context Protocol, or MCP. Curious why? Read on.
What Is MCP?
MCP is a way for different AI models, and the agents (read about agents here) that use them, to talk to each other.
Think of it like this: instead of manually connecting different systems when you want to share data, MCP lets one AI model pull context from another in real time, seamlessly and instantly.
Basically, instead of teaching every AI everything, you teach each one what it’s best at, and they learn to ask each other for help.
Who’s Behind It?
Since its introduction, MCP has gained traction among major AI providers:
Anthropic: The creator of MCP in November 2024, Anthropic has integrated the protocol into its Claude family of language models, enabling them to interact seamlessly with external systems.
OpenAI: In March 2025, OpenAI announced support for MCP across its Agents SDK and ChatGPT desktop applications, facilitating broader adoption of the protocol.
Google DeepMind: Shortly after OpenAI's announcement, Google DeepMind confirmed MCP support in its upcoming Gemini models and related infrastructure, highlighting the protocol's growing industry acceptance.
...and many more! It’s not just the AI giants. Tools like Linear, Zapier and Atlassian are jumping on board. Signaling that MCP is becoming foundational infrastructure, not just something for the leading LLMs, but for the everyday tools teams use to get work done.
MCP + Underwriting AI?
Why is MCP relevant for AI underwriting technologies? Today, many insurers have their own internal AI tools. MCP basically turns all these isolated AI models into a connected ecosystem.
Here’s an example:
1. Let’s say a carrier has its own internal ChatGPT-like app as well as Sixfold's AI risk assessment solution.
2. With MCP, an underwriter using an internal chat tool, for example, can simply ask a question “What’s the risk appetite score for this customer named Gamehendge Widgets?”
3. Their AI doesn’t need to know everything itself, it just knows who to ask, in this case - Sixfold. It reaches out to Sixfold’s models, gets the answer, and serves it up directly to the underwriter.
No complex integration projects. No heavy lift for IT. MCP would act as a seamless bridge between Sixfold’s risk assessment expertise and the additional AI tools underwriters are using.
Why Sixfold Cares (a Lot)
Right now, almost everyone is talking about "agentic" behavior, how AI agents plan and reason independently. But the thing is that MCP is the quieter, more practical sibling: it’s about getting the right data in the right place, way faster than before.
The impact MCP can bring:
- It can meet underwriters where they are today - inside the tools they already use every day
- Enables flexible adoption where carriers can pull in just the capabilities they want, without a massive rollout
- It’s a leap forward in making underwriting AI more accessible and useful
At Sixfold, we’ve made MCP connections between our models and other systems, We’ve, and also exposed internal tools where AI chat assistants can query Sixfold’s underwriting insights.
What to Watch Out For
Like any new tech, MCP isn’t perfect. There are a few important risks to keep in mind:
Security:
- MCP is pretty quiet on the security mechanisms with which connected systems lock down their data. Existing enterprise-grade methods that companies like Sixfold use to protect sensitive customer data will need to be considered and implemented.
- Malicious tools could hide bad instructions if care is not taken on how different models talk to each other.
Accuracy:
- Incorrect or messy data leads to bad decisions. AI pulling data quickly doesn’t mean it’s always right, double-checking and validation are key.
What’s Next with MCP?
MCP done right (e.g. secure, validated and tested over and over) could be a kind of quiet but transformative technology that will make AI in insurance not just smarter, but more practical.
From many steps to one: MCP collapses complex processes into simple interactions.
From heavy integrations to light connections: Carriers can plug into any AI expertise easily.
From standalone tools to connected ecosystems: Underwriters get the best of all worlds, without even noticing the heavy lifting happening in the background.
Emerging protocol: Agent-to-Agent (A2A). A2A was launched by Google in April 2025 and has already gained support from Microsoft. The protocol addresses the need for AI agents, often developed on disparate platforms, to communicate and collaborate. Even with certain similarities, MCP and A2A work well together instead of competing. Google says that A2A is meant to go alongside Anthropic’s MCP.
As more organizations roll out MCP and A2A, AI assistants and agents are getting way better, more up-to-date, more capable, and way more useful in the flow of work.
The future of AI in underwriting isn’t just about smarter models, it’s about models that collaborate and talk to each other.