"RaftLabs has been an exceptional partner. From the start, they became more than just a service provider, they embraced our vision with their expertise and dedication. We're proud of the result."
Jennyfer Ngueno
CoFounder & CEO, Sekou
AI Agent Development Services for Insurance
AI agents that act, not just answer
A chatbot tells a policyholder how to file a claim. An AI agent collects the FNOL data, validates it against the policy record, creates the claim in your system, assigns it to the right adjuster, and sends the first status message, all from a single inbound contact. The difference matters in insurance because half-finished workflows create the cost: when a FNOL lands by email and a handler has to open three systems and re-key the data, that's a workflow problem, not a training problem. We build insurance AI agents with a defined scope per workflow, explicit escalation rules, and compliance-aware data handling.
FNOL intake agents that collect, validate, and route first notice of loss from any channel
Underwriting data agents that query CLUE, MVR, credit bureaus, and property databases and return structured output for review
Claims status agents that give policyholders real-time updates without advisor involvement
Compliance-aware architecture with full audit trails and configurable human-in-the-loop checkpoints
Bring the problem, the current workflow, or the existing code. We reply with a practical next step within one business day.
Trusted by
The brief
Start with what is not working.
Good software decisions begin with the constraint, not a list of features or a preferred technology.
01
Your claims team re-keying the same FNOL data from emails, portals, and phone notes into your system of record, every single intake?
02
Underwriting data collection from CLUE, MVR, and third-party sources taking days and pulling attention away from actual risk assessment?
Plain answer
RaftLabs builds AI agents for insurance workflows: FNOL intake, underwriting data extraction, claims status, renewal reminders, and fraud-signal flagging. Unlike rule-based RPA, these agents act end-to-end across systems, apply configurable decision logic, and escalate to human reviewers at defined checkpoints.
What to remember
- FNOL intake agents accept input from email, web portal, and phone transcripts, producing a consistent structured claim file regardless of inbound channel.
- Underwriting data agents run parallel bureau retrieval (CLUE, MVR, credit, property databases) and assemble a structured package the moment all sources return.
- Fraud signal flagging agents surface transparent, explainable risk signals rather than a black-box score, so SIU reviewers know exactly what to investigate.
- Every agent action is logged, and any output that can decline, delay, or price a policyholder surfaces its reasons and routes to a human for review.
- Buy the system of record and build the process layer, since custom fits intake, triage, document chaos, legacy handoffs, and work between systems.
Proof
- shipping production software across industries
- Since 2015
- RaftLabs delivery record
- average client rating across delivered projects
- 4.9/5
- Clutch, verified reviews
- scope and cost agreed in writing before any build starts
- Fixed price
- Every RaftLabs engagement
What an insurance AI agent actually does
An agent fixes the half-finished-workflow problem by owning it end-to-end. It escalates the exceptions that genuinely need a human. Each agent runs one insurance workflow well. We scope the integration with your policy administration system and claims platform during discovery, where most projects find their real complexity.
Agents sit on top of insurance software as the system of record, use document processing for ACORD forms and loss runs, start as AI chatbots for status enquiries, and graduate from insurance automation when rules stop being enough.
McKinsey puts 30 to 40% of an underwriter's time on administrative work like rekeying data and running manual analyses ("Insurance productivity 2030"). That is the work an agent should take off your team.
We are direct about proof. RaftLabs has shipped AI agents and document data-extraction systems, not yet a live insurance claims or underwriting agent. The engineering is the same one domain over. The adjacent work below shows it.
Capabilities
What we build
FNOL intake agent
Extracts structured FNOL data from email, portal, or phone transcript, validates against the policy record, creates the claim, and routes it to the right adjuster queue.
Underwriting data extraction agent
Runs parallel CLUE, MVR, credit, and property database retrieval, assembling a structured underwriting package the moment all sources return.
Claims status agent
Answers policyholder status enquiries in plain language from live claims data, and sends proactive updates at defined workflow trigger events.
Policy renewal reminder agent
Drives personalised, compliance-checked renewal outreach across the pre-renewal window, escalating coverage questions to a human.
Fraud signal flagging agent
Aggregates configurable fraud indicators into a transparent risk score, routing high-risk claims to SIU with the specific signals that triggered the flag.
Subrogation identification agent
Reviews claim narratives at defined lifecycle points to flag recovery-worthy cases for professional review, never determining liability itself.
The first decision is not what to build.
It is whether software is the right answer at all. We use four possible recommendations before discussing a development scope.
- 01
Buy
Choose a maintained product when it handles the core claims and underwriting operations workflow and the remaining gaps can be solved with configuration, a connector, or a small process change. Paying for software you do not have to maintain is often the better trade.
- 02
Repair
Keep the existing product when users still get value from it and the code can be understood safely. Start with evidence: where the code lives, how the data is organized, what is tested, which outside services it depends on, who can access what, and how updates go live.
- 03
Build
Own the system when claims and underwriting operations shape margin, customer experience, speed, or a product customers pay for. Start with one complete path and the system connections that path cannot work without.
- 04
Wait
Do not turn a changing policy into permanent software. Stabilise the rules, name the workflow owner, and measure the cost of the current process before paying for a product.
Not sure which path is yours? Bring it to a 30-minute call. Leave with the answer in writing.
How we work
From scope to live insurance agent
- Phase 101
Workflow and system scoping
We map your target workflow, systems, and where your team is losing time. You leave the first phase with a written scope document and a fixed-price quote.
- Phase 202
Integration and escalation design
System integrations, decision logic, and human-in-the-loop checkpoints designed against your compliance requirements.
- Phase 303
Build and integrate
The agent workflow built as a directed graph with explicit state transitions, tested against real claim and submission scenarios.
- Phase 404
Launch v1 and team training
Claims and underwriting teams trained on the escalation workflow before the v1 goes live. We extend to more workflows from there.
Proof
How we work with insurers and MGAs
- 01
Fixed price before development starts
We scope the work, calculate the cost, and lock it in writing before any development starts.
- 02
Shipping production software since 2015
We have built AI agents and document data-extraction systems across fintech, healthcare, logistics, and retail.
- 03
We don't start a build we haven't scoped
The scoping document defines the workflow state machine, integration points, and escalation logic before any code is written.
- 04
Compliance documentation ships with the software
A data flow diagram, controls inventory, and audit trail specification are delivered alongside the working system.
Proof
Adjacent AI-automation work
- 01
Document data extraction
AI-OCR platform extracts and syncs document data across 40+ US locations
An offline-first AI-OCR pipeline that reads receipts and POS documents, then syncs structured records across sites. This is the FNOL-neighbouring problem: turn messy inbound documents into clean, structured data. - 02
AI agent build
Multi-step conversational AI agent that runs research interviews end-to-end
An AI agent that conducts interviews and returns structured output, built on Anthropic Claude via AWS Bedrock. Same agent-engineering pattern behind an insurance workflow agent.- concept to launch
- 12 weeks
- 03
EventRaft reaches 50,000 users in 6 months by replacing scattered event tools with one platform
EventRaft replaces the three to five tools most event organizers juggle with one native iOS and Android platform. 50,000 users in six months, 95% satisfaction, and 25% faster event management (client-reported).- in 6 months
- 50k+ users
- satisfied users
- 95%
- faster event management
- 25%
What it costs
Every project starts at $10000.
A focused v1 covers one insurance workflow end to end, with escalation to human reviewers at defined checkpoints.
Starting investment
Starts at $10000
The first agent is scoped around one workflow and its integration with your policy admin and claims platforms. After a 30-minute call, you get a written build, buy, repair, or wait recommendation plus first-phase direction. Free, whether or not you build with us.
Custom fits in the process layer, on top of the system of record.
Buy the system of record; evaluate platforms when the pain is in policy admin or rating.
A fit
Pain in intake, triage, document chaos, legacy handoffs, or work between systems
An agent must handle unstructured variation across systems, with defined escalation and human routing for any output that can decline, delay, or price a policyholder
Not a fit
Pain in policy admin or rating, which means evaluating platforms
A system-of-record purchase, where traditional underwriting software is the working layer
RPA or workflow automation or AI agent
| RPA or workflow automation | AI agent | |
|---|---|---|
| Input | Fixed rules on structured data, and breaks when formats change | Unstructured variation, because the LLM reads intent and content, not just field positions |
| Action | Fixed, rule-based steps | Multi-step actions across systems: validates a policy number, creates a claim record, routes it to the right adjuster, and sends acknowledgement |
| When to graduate | Rules are enough for the workflow | Rules stop being enough, and the workflow needs judgment across systems |
Proof
What clients say about working with RaftLabs
Three-year average engagement. Founders and operators describing the work in their own words. No marketing varnish.
Work with us
Have an insurance AI agent project?
Tell us the workflow you want to automate, the systems you run on, and where your team is losing time to work an agent should handle. We'll scope what it takes and give you a fixed cost.
- Scope and cost agreed before work starts. No surprises. No obligation.
- Working prototype within 3 weeks of kickoff.
- Pay by milestone. You see progress before each invoice.
- 60-day post-launch warranty. Bug fixes, UI tweaks, and deployment support. No retainer.
- All conversations are NDA-protected.
Common questions
RPA follows fixed rules on structured data and breaks when formats change. AI agents handle unstructured variation because the LLM reads intent and content, not just field positions. Agents can also take multi-step actions across systems: validate a policy number, create a claim record, route it to the right adjuster, and send acknowledgement as one end-to-end workflow with the full state tracked and auditable.
Every agent action is logged: the data it retrieved, the decision it made, what it wrote to the system of record, and when. We confirm data processing agreements are in place before any policyholder data reaches an LLM. For any output that can decline, delay, or price a policyholder, the agent surfaces the specific reasons and routes to a human for review.
We integrate with systems that expose REST APIs or SOAP web services, including Guidewire PolicyCenter and ClaimCenter, Duck Creek Policy and Claims, and Applied Epic. Bureau data including CLUE and MVR is accessed via LexisNexis, ISO, or state-specific aggregators. Integration complexity is the single biggest variable in project scope, so we confirm API access and sandbox environments during discovery.
Cost follows scope: a focused insurance AI agent covering one workflow, one system integration, defined escalation logic, and compliance-aware architecture is a different build than a multi-agent build covering FNOL intake, underwriting data extraction, and claims status with integrations to a policy admin system and claims platform. After scoping the workflow and integrations, you get a fixed written quote.
Buy the system of record, build the process layer. Pain in policy admin or rating means evaluating platforms. Pain in intake, triage, document chaos, legacy handoffs, or work between systems means custom fits better. Traditional underwriting software is a system of record; agentic AI is the working layer on top that handles broker emails, ACORD forms, loss runs, and manual handoffs the platforms leave to people. Most insurers need both. Start with a core platform for the main workflow, and add specialized point tools as gaps appear.
What should stay human: complex coverage decisions with real financial consequences, sensitive claims conversations after a loss, final underwriting judgment calls, any interaction where trust-based advising matters more than speed. Support the advisory role, do not replace it. Low-complexity, high-volume policies: straight-through within thresholds. Complex commercial and specialty: agents support, underwriter decides. Extract, enrich, appetite-screen, risk-score, prepare the file, then the human makes the call. The real implementation work is defining escalation rules and success metrics with underwriting and claims leadership, not the model.
Yes. For email, the agent monitors a designated inbox and runs extraction against the email body and attachments. For web portal submissions, it receives a webhook or polls the portal API. For phone transcripts, it extracts FNOL fields from unstructured conversational text. Each channel feeds the same downstream validation and routing workflow, producing a consistent structured claim file.
Go deeper