Accelerator 02 · Insurance
Claims intake & triage agent
Takes a first notice of loss, checks it against the policy wording, flags fraud indicators and routes it to the right next action.
The problem
- First notice of loss arrives by email, call-centre notes and portal forms in different shapes.
- Handlers spend the first touch on reading policy schedules and endorsements instead of deciding.
- Fraud indicators are caught late because nobody lines up dates, previous claims and policy terms on day one.
What it does
- Structures the claim into a standard intake record.
- Checks the loss against policy period, cover, waiting periods, sub-limits and endorsements.
- Lists fraud indicators with the evidence behind each, without accusing anyone.
- Recommends a next action (fast-track, survey, investigation, more documents) and drafts the customer message.
Pick a sample claim and see the coverage check, fraud flags and recommended next action.
Live demo: Claims intake & triage agent
Synthetic data only · nothing you type is stored
Output
Intake record, coverage check, fraud indicators and a recommended next action.
The demo first calls the Surge in-house AI server and falls back to a hosted open-source model if it is busy. The badge on the output shows which one answered. Limited to a few runs per visitor per day.
How it integrates
In your deployment the accelerator runs inside your environment, behind your single sign-on, and is connected to the systems below. You choose the hosting and the model.
Systems and APIs
- Claims management system (create / update claim via API)
- Policy administration system to fetch schedule and endorsements
- Email / WhatsApp intake channels
- Surveyor and investigator assignment queue
Data we need for a pilot
- Policy wordings and endorsement library
- 100+ closed claims with outcomes (anonymised)
- Existing fraud indicator checklist
Where it runs
- On-prem on the insurer's infrastructure
- Private cloud tenancy in an Indian region
Open-source models we start with
- Qwen3-class 14B–32B instruct model
- BGE-M3 embeddings over policy wordings
- OCR for scanned bills and estimates
Walkthrough
A short recorded walkthrough of the claims intake & triage agent: the input, the output and how a reviewer uses it.
Next accelerator: Clinical notes to structured summary →Walkthrough video coming soon
We are recording a short walkthrough of this accelerator. Meanwhile, run the live demo above or book a working session.
Run the insurance accelerator on your data
In a working session we map it to your process, systems and rules, and agree what a pilot must prove before it goes live.