AI agents for insurance claims
Give your adjusters agents that only see the claims they handle
Three agents for claim intake, file summaries and fraud screening. The ones adjusters call act as that adjuster and read only the claims assigned to them. Every call lands in one audit record.
Governing Insurance Agents
Any tool, any model, any use case
Our example demonstrates three agents for your claims work, pulled from our template library. Our team can work with yours to build, govern, and operate your agents as you deliver on your IT strategy.
Examples for Insurance
More from the library · Insurance
Also in the library
Triage new claims
Reads each first notice of loss, sets severity and line of business, and routes it to the right adjuster queue. It flags. It never settles.
Tools
Model
Runs
Limits
Tuned for your team
- Your severity bands and routing rules
- Lines of business as ClaimCenter defines them
Applying Controls to Agents
Enforce claim access, privacy and payment authority in one place
Dome sits between the agents and your systems. Every call is checked against rules your team writes before it reaches ClaimCenter, OnBase or a model.
Acting as
- Agentclaim-summarizer is registered and active
- Callerr.whitaker verified through Entra ID
- Toolget_document is granted on claims-tools
- RuleCLM-20814 is assigned to r.whitaker
Comprehensive Audit
Show regulators exactly which claim files an agent opened
One record for every call: the agent, the adjuster it acted for, the system, and the decision. Enable investigations, increase confidence and reduce risk in agentic operations.
- fnol-triage08:12:40
| Timestamp | Type | Agent | Acting as | Resource | Outcome | Latency |
|---|---|---|---|---|---|---|
| 08:12:40.318 | ||||||
Regulation
Give examiners evidence, not just a policy
State regulators now ask how insurers govern AI. These are the rules claims agents reach, and what the controls above give you for each.
NAIC Model Bulletin on AI Systems
What it asks
Adopted by more than 20 states: a written AI program, controls over third-party AI, and documentation regulators can review.
What Dome gives you
One inventory of agents and the models they reach, rules on what each may do, and an audit record of every call.
Unfair claims settlement practices laws
What it asks
Claims must be investigated and decided fairly and promptly, and regulators expect a person accountable for adverse decisions.
What Dome gives you
Agents triage, summarize and flag. Paying or closing a claim is refused to every agent, so adjusters decide.
Insurance data security laws
What it asks
State laws based on the NAIC Insurance Data Security Model Law require protecting nonpublic information, including the health and financial data in claim files.
What Dome gives you
A guard strips identifiers from claim documents before a model call, and agents reach only approved models.
FAQ
Common questions
What does the NAIC AI model bulletin require?
Insurers using AI need a written program covering governance, risk controls and third-party AI, with documentation regulators can review. More than 20 states have adopted it.
How do insurers document AI governance for a market conduct exam?
Show the inventory, the rules and the record. Dome keeps all three in one place: every agent, what it may call, and every call it made, allowed or refused.
Can AI deny an insurance claim?
Regulators expect a person to own adverse decisions. On this setup agents triage, summarize and flag, and payment and closing calls are refused, so adjusters decide.
How are AI agents used in insurance claims?
First notice of loss triage, claim file summaries and fraud screening are common first agents. Each reads only the claims its adjuster is assigned.
How do you keep a human in the loop on agentic claims?
Draw the line in rules. Agents can write triage fields and notes, money and claim status stay with the adjuster, and every attempt to cross the line is recorded.
Forward deployed engineering
Spend 30 minutes with our FDE team to understand the platform, and how it fits to your needs.
Our FDE team can get your first agent under management and work with your platform team to deliver results for your AI program.
Key topics to discuss:
- Review your AI plans, progress to date, and timeline for agentic projects in production.
- Planning a specific agent, or agentic app, to bring under governance.
- Learning more about our platform capabilities, from gateways to routing.
- Defining agentic operations as repeatable golden pathways for Platform and AppDev teams.
Explore
Other industries
AI agents for financial services
KYC reviews, client servicing and SAR narratives. Approvals, money movement and filings stay with your people.
Agentic use cases
- Review onboarding documentsChecks identity and entity documents against your CDD requirements, runs sanctions screening and writes the KYC summary. An analyst approves.
- Answer client requestsReads the client's accounts and open cases and drafts the reply to a servicing request. It never moves money or changes an account.
- Draft SAR narrativesPulls the alert history and transactions for a case and drafts the SAR narrative. An investigator edits it and files.
Answers to
- GLBA Safeguards Rule
- BSA/AML and the FinCEN CDD Rule
- NYDFS Part 500
- Regulation E (EFTA)
- CFPB UDAAP
- Interagency third-party risk guidance
- ECOA and Regulation B
- FCRA
- SR 11-7 model risk management
- PCI DSS v4.0.1
- Regulation E (EFTA) error resolution
- BSA/AML and OFAC sanctions screening
- SEC Regulation S-P (2024 amendments)
- SEC Marketing Rule and FINRA Rule 2210
- Books and records (Rule 204-2 and Rule 17a-4)
- FINRA Rule 3110 and Regulatory Notice 24-09
- SEC Rule 17a-4 recordkeeping
- Exchange Act Section 15(g) information barriers
AI agents for gaming and sports betting
Player support, responsible gaming review and bonus setup. Self-exclusions and limits stay out of an agent's reach.
Agentic use cases
- Answer player questionsLooks up a player's account, bets and withdrawal status so a specialist can answer fast. It reads. Balances and limits stay with people.
- Review responsible gaming signalsReviews players flagged for risky play and drafts case notes for the responsible gaming team. It never changes a limit.
- Configure bonusesSets up deposit matches and free bets from a campaign brief, up to the cap you set. Self-excluded players are never targeted.
Answers to
- State gaming regulations
- Bank Secrecy Act (FinCEN casino rules)
- Age, identity and location checks
AI agents in healthcare
Prior authorizations, visit notes and eligibility checks. Agents read only the charts their clinician can read.
Agentic use cases
- Assemble prior authorizationsPulls the notes, orders and imaging a payer asks for into one authorization packet. A clinician reviews it and submits.
- Draft visit notesDrafts a visit note from the encounter and the chart, in the department's template. The clinician edits it and signs it.
- Verify eligibility before the visitChecks coverage for the next day's appointments overnight. Anything that needs a call before the visit goes to the patient access channel.
Answers to
- HIPAA minimum necessary
- Business associate agreements
- HIPAA Security Rule audit controls
- CMS prior authorization rule (CMS-0057-F)
AI agents for law firms
Conflicts checks, clause extraction and redlines. Every agent acts as the lawyer who asked.
Agentic use cases
- Check new matters for conflictsSearches Intapp and past matters in iManage for parties that conflict with a proposed engagement. It reports. It never clears a conflict.
- Extract clauses from contractsPulls parties, dates, renewal and change-of-control terms from the contracts in a matter workspace. Only in matters the requester is staffed on.
- Draft redlines against the playbookMarks up a counterparty draft against your playbook and saves it as a new version. Counsel reviews it and sends it.
Answers to
- ABA Formal Opinion 512
- Privilege after United States v. Heppner
- Ethical walls (Model Rules 1.7, 1.9, 1.10)
AI agents for professional services firms
Proposals, staffing and engagement status. Each agent sees only the engagements its consultant works on.
Agentic use cases
- Draft proposalsReads an RFP and drafts a response from the firm's reuse library. Client names in past work are stripped before the model sees them.
- Match staff to engagementsMatches skills and availability to a new engagement's roles and proposes a team. Resource managers make the assignments.
- Report engagement statusReads the project plan and engagement files and drafts the weekly status report. It sees only engagements its consultant is on.
Answers to
- Client confidentiality terms
- AICPA Confidential Client Information Rule
- SOC 2
- GDPR and state privacy laws
AI agents for retail
Order lookups, replenishment and product copy. Refunds, orders and publishing stay with your people.
Agentic use cases
- Answer order questionsLooks up orders, shipments and returns so an associate can answer a customer fast. It reads. Refunds stay with the associate.
- Plan replenishmentForecasts demand by store and drafts purchase orders against par levels. Buyers review them and send them.
- Write product copyWrites product titles and descriptions from supplier data, in your voice, and saves them as drafts. Merchandisers publish.
Answers to
- PCI DSS v4.0.1
- State privacy laws (CCPA/CPRA)
- SOX internal controls
- FTC Act, Section 5
- Antitrust and algorithmic pricing
- Predictive scheduling laws
- Routing guides and carrier contracts
AI agents for software companies
Escalation triage, incident summaries and release notes. Agents read code and incidents. Shipping stays with engineers.
Agentic use cases
- Triage engineering escalationsReads an escalated ticket and the code it points to, drafts a diagnosis and sets priority. Fixes stay with the engineer.
- Summarize incidentsFollows an incident's timeline and recent deploys, drafts status updates and a first postmortem. It never acknowledges, pages or resolves.
- Draft release notesReads the pull requests merged since the last release and drafts customer-facing notes. The release stays a draft until an engineer publishes it.
Answers to
- SOC 2
- ISO/IEC 42001
- EU AI Act
- State privacy laws (CCPA/CPRA)
Enabling agent operations
Governance at the agent‑action boundary.
However an agent was built and wherever it runs, the same three boundaries are available to control it: the code it ships as, the tools it calls, and the model it reasons through.
Code
Agent Registry
Make every agent known and manageable. Credentials issued, capabilities declared, lifecycle owned.
See more
Tool
MCP Gateway
Evaluate every call against policy with full context. Allow, deny, or escalate. Filter what comes back.
See more
Model
Model Broker
Constrain how the agent reasons. Selection by policy, routing across providers, evals against real traffic.
See more