Skip to content
SSyntalith
Book a free process review (30 min)

Blog · Published · Updated

AI Workflow for Insurer Case Processing: Intake, Evidence and Review

Short answer

An AI agent in claims processing takes in the claim, checks that the documents are complete against the team's list, reads the policy data, prepares a summary with sources and hands exceptions to the claims handler. The decision on liability, the amount or a refusal stays with a person. At Syntalith the agent costs from €3,000 net, and with 800 claims a month it pays back in 1.3 months.

How we workDetails ↓

  1. 01Call30 minutes with an engineer, free
  2. 02PrototypeA working system on your process and data, free
  3. 03ImplementationTarget and fixed price in the contract; 50% at signing
  4. 04Acceptance50% once the agreed target is met
net per agent for one process, build paid once
from €3,000
from signing the contract to acceptance
6–16 weeks
free prototype on your cases
€0
Book a free process review (30 min)

We belong to the OpenAI and Anthropic partner programmes and learn through their official courses. What this means ↓

Author: Syntalith · 3 min read

Example: the morning request inbox
Agent · ready

Statistics

Insurance and AI: statistics 2026

1.3 mo.

payback of a €3,000 agent at 800 claims a month: €2,792 of case preparation today, €425 with checking and the model. Scenario.

Figures checked: 22 October 2026

Claims triage and the limits of decisions

Three layers of work in a claim

  • Intake and sorting

    agent: policy, documents, description, history

    pilot scope

  • Operational qualification

    agent: type of loss, gaps, priority, queue

    pilot scope

  • Decision on the merits

    claims handler: liability, amount, refusal

    the agent prepares the material

Time disappears in many small delays: a claim in the wrong queue, documents with ambiguous names, photos and invoices in different channels, a manual policy check and a general request to „complete the documents”. The agent helps with each of these steps, and the claims handler's time stays for assessment and difficult conversations.

Completeness against the team's list

The claims team defines which materials it checks for each type of case, and the model does not create a binding list from general knowledge. In one exercise an invoice arrived, then a resent copy of it, then a photo labelled with the number of another case: three files do not mean three correctly delivered documents.

Working statusWhat the claims handler sees
File receivedWhere the original is and what it was assigned to
Uncertain readingWhich field to compare with the image
Missing informationWhich requirement is not met
Conflicting materialsWhich versions the discrepancy concerns
Ready for reviewWhat was checked and what needs a decision

The status „ready for review” describes the preparation of the material. Accepting a claim needs a separate decision and status, and sending an attachment to a queue does not confirm that anyone has taken over the case.

What an insurance claims agent costs and when it pays back

Scenario: 800 claims a month
Today
800 claims × 6 min = 80 h (€2,792)
With the system, a person checks the output in 15% of the time
€419
Model, 1 call per case, Claude Sonnet 5.5
€6
Cost of one case
€3.49 today, €0.53 with the system
Saving
€2,367 a month

Payback of €3,000

1.3 months

The volume, the time and the checking share are the scenario's assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat. Model: 2,500 input tokens and 300 output tokens per call at Anthropic's rates, converted at the ECB rate of 1.1205 USD per euro on 22 October 2026.

According to Brynjolfsson, Li and Raymond (2025), support agents working with AI resolved 15% more issues an hour on average. In claims, the biggest difference comes from a complete case at the start, with no hunting for attachments.

Control, data and the AI Act

Approval by a person lets you check the sources, change the result and stop the run. Automation tools describe such stops: n8n requires approval before a tool is called, and LangGraph pauses the run until a decision. Annex III of the AI Act lists systems for risk assessment and pricing in relation to natural persons in life and health insurance, and Article 14 describes human oversight. EIOPA describes AI governance in proportion to the risk. You limit the data to what each stage needs, in line with the principle of data minimisation.

The first scope

A pilot on one type of claim
  • Glass claims, assistance or simple cost refunds based on an invoice
  • A document list approved by the claims team
  • A draft request for missing items, approved before it is sent
  • Similar numbers, a corrected document and a resent file in the test sample
  • Cases the system marked ready too early, counted separately

The scope in insurance is described on AI in insurance.

Worked example · Scenario

How we count the payback: preparing claim files

We run the same count for your claims in the free process review.

€2,792

a month for handling 800 case documents by hand

Payback: 1.3 mo.

6 minutes to receive and check a document and checking in 15% of the old time are our assumptions. €34.90 an hour is the EU average hourly labour cost for 2025 according to Eurostat, for companies with 10 or more employees. Model cost: reading a document in our case file system (about €0.0002) plus a description of what is missing (Claude Sonnet 5.5, about 2,000 + 300 tokens), at the ECB rate of 1.1205 USD per euro on 22 October 2026.

See the full calculation →

This is how we implement it in companies

All case studies →

Client results.

All projects →
foap.comcustomer service

foap.com customer service: 95% of replies are sent automatically.

Users from several countries write to foap.com, in several languages. The system reads the entire conversation and the terms of that person, and then sends a response in that person's language. Questions about money and exceptions go to the team with a ready draft, so they have to check and send them.

the system sends the answers itself, without human typing
95%
time from the arrival of the e-mail to the ready response (median)
30 s
e-mails that require a response receive a ready-made draft
100%
less work for every 1000 answers (estimate)
47 h

Data from foap.com production, October 20-21, 2026. Estimate: 3 minutes for handwritten response.

How foap.com customer service works →
Sample messages. Money matters always come to the person.

Other implementations

jaktako.design

studio projektowe

−87%

Time to look for new customers, every day

4 hours → 30 min

approx. 73 hours less per month (21 days of work)

according to the studio

How the agent loop works →
Signature Estates

real estate

approx. −90%

Operator time spent browsing portals, per day

2–3 hours → 20 min

approx. 45 hours less per month (21 days of work)

respect · contact the seller 5 minutes after the announcement

How the agent finds property listings →
Kuba Koziej, CEO and co-founder of MoreGrowth and board member at Natu.Care

Kuba Koziej

CEO and co-founder, MoreGrowth

„We started with my own AI agent. During the training that followed, I learned to build new applications myself. Today I am bringing this way of working with AI into my business. Working with Syntalith gave me exactly the skills and tools I needed.”

View the original training review on LinkedIn ↗

See the agent on your own cases before you commit.Book a free process review (30 min) →

How we build automation and agents

From a conversation to a working system in four steps.

  1. 01 · 30 min

    Free process review

    €0

    You're talking to an engineer. You receive the written plan within 2 business days.

  2. 02 · 5 days

    Free prototype

    €0

    The system works on 20-100 cases that your team has already handled. You see every result.

  3. 03 · 2–16 weeks

    Build

    50%

    Fixed price and goal written in the contract. First installment upon signing.

  4. 04 · after reaching the goal

    Reception

    50%

    You pay the second installment when the system reaches its target on your cases.

How a free prototype is created

Mon.

We set a goal

What result do you consider good?

Tue–Wed

The system is working

It goes through your affairs, one by one.

Thu

We compare

We check every difference with the team's work.

Fri

Result and price

List of errors and fixed implementation price.

You choose the matters. We anonymize them upon request, they stay in the EU and we delete them after the test.

On the market, such a test usually costs from PLN 3,000 to PLN 8,000.

Book a free process review (30 min)

We establish a prototype during a free analysis.

Data checked on October 25, 2026.

„Is my data safe?”

Yes. You choose where they go: from your company account to the model on your server.

  1. 00Employee's private account

    Customer and company data ends up in an account that the company cannot see or control. There is no data processing agreement, so it is a violation of the GDPR. When an employee leaves, the chat history goes with them.

  2. 01ChatGPT or Claude corporate account

    The provider does not use your data to train models. A copy of the queries remains in his logs for up to 30 days.

  3. 02API with zero retention (ZDR)

    The provider processes the request and does not save anything. It requires his consent, we prepare the application together.

  4. 03Processing in the EU

    Queries are counted and stored in Europe: OpenAI in the EU region, Claude via clouds with the EU region.

  5. 04Model at your place

    The open model runs on your server or in your cloud in the EU. The data does not go outside the company.

What we do with every implementation

  • Confidentiality agreement and data processing agreement before we receive any data.
  • You choose the cases for the prototype and we anonymize them upon request.
  • The data stays in the EU and we delete it after the test.
  • Corporate accounts with an administrator on your side.

When data cannot leave the company

The open model runs on your server or in your cloud in the EU. To choose from:

White-tailed eagle
Polish model, SpeakLeash and ACK Cyfronet AGH
PLLUM
Polish model, HIVE consortium commissioned by the Ministry of Digitization
Qwen
Alibaba
GLM
Zhipu AI
DeepSeek
DeepSeek

We select a model for the task and check it on your cases. We run it, tune it and maintain it.

Source: Bielik and PLLuM, ACK Cyfronet AGH ↗ · PLLuM, Ministry of Digitization ↗

Do you have a lot of your own data? We will fine-tune the small model.

  1. 1 Your examples
  2. 2 tuning
  3. 3 test on new cases
  4. 4 model at your place

When you have thousands of similar emails, documents or reports, we teach a small open model based on your examples. It works for you, responds quickly and costs less to maintain than a large model. We measure quality on issues that the model has not seen while learning.

Przemysław and Piotr did it in large programming and consulting companies. Artem did it before and does it today at Syntalith. It's about models on your own infrastructure, tuning and quality measurement.

Private AI models →

Source: OpenAI, training on data from private accounts ↗ · OpenAI, who sees conversations ↗ · Anthropic, changes for private accounts (August 2025) ↗ · OpenAI, data in API ↗ · AWS Bedrock, EU profile ↗

You choose the protection level during the interview. We sign the data processing agreement before we see any data.Schedule a free analysis →

AI agents

See the agent on your own cases before you commit.

The agent takes the case through the next steps in your systems, and the actions take effect until the consent of the indicated person is obtained. A prototype for 20-100 cases that your team has already handled costs €0. We write down the purpose and test set in the contract.

See AI agents →
net per agent for one process, build paid once
from €3,000
from signing the contract to acceptance
6–16 weeks
free prototype on your cases
€0
Book a free process review (30 min)

or call+48 888 78 48 78WhatsAppMon–Fri 9:00–17:00 CET

Questions

  • What does an AI agent do in claims processing?

    It takes in the claim, collects the policy and incident data, checks that the documents are complete against an approved list, prepares a summary with sources and a draft request for missing items, and routes the case to the right queue.

  • Does the agent decide on paying the claim?

    No. Liability, the scope of cover, the amount, a refusal and a settlement stay with the claims handler. The agent prepares the material, and the handler opens the basis of each point.

  • How much does a claims agent cost?

    At Syntalith from €3,000 net. With 800 claims a month at 6 minutes of preparation each, the payback is 1.3 months. We agree connections, permissions and maintenance before the quote.

  • Is a claims agent a high-risk system?

    The classification depends on the intended purpose. Annex III of the AI Act lists, among others, systems for risk assessment and pricing in relation to natural persons in life and health insurance. Preparing documents for review is assessed separately.

  • Which cases always go to a person?

    Bodily injury claims, a refusal or reduction of a benefit, disputes about the scope of cover, suspected fraud, recourse, appeals, clients in a difficult situation and conflicting data.

Let's talk

Just write, call or choose a date.

We work fast because we hate corporate cotton wool. We don't have salespeople or managers to keep an eye on managers. You talk immediately to engineers who then build your system. We respect each other's time and yours too.

We will accept 3 more companies by the end of the year.

Write
contact@syntalith.ai
Call
+48 888 78 48 78
WhatsApp
write on WhatsApp

Mon–Fri 9:00–17:00 CET

What our OpenAI and Anthropic partnerships mean for you.

OpenAI makes ChatGPT and Anthropic makes Claude. We belong to the partnership programs of both companies, so we work with their tools every day and learn from the creators themselves.

OpenAI Select PartnerClaude Partner Network
01We will select a tool for the task
We implement both ChatGPT and Claude. We check both on your documents, and you choose the one that makes fewer corrections and saves more time.
02Knowledge straight from the creators
We learn from official OpenAI and Anthropic courses and materials. Your team learns about the features and settings that work today.
03Licenses without our margin
When we roll out ChatGPT, Claude or Copilot, you buy the licences directly from OpenAI, Anthropic or Microsoft and they invoice you. We add nothing to the licence.
04Certified engineers
On the team, we have an AWS certification in machine learning and an Anthropic certification in systems architecture on Claude.

Participation in programs does not mean that OpenAI or Anthropic endorses our services.