Media & Evidence package

Insurance claim photo assessment

Motor claims with damage photos: AI damage assessment, decision-table triage and SLA, adjuster review, letters, and photos with faces and plates blurred for repairers.

Connects to Google Gemini

OfficialStarts from a formIntermediate~20 min setupv1.0.0
Download .utpkg 19 KBHow to install

About this package

What it does

Insurance claim photo assessment starts from a claim form page where the claimant enters their policy, what happened and uploads photos of the damage (the camera opens on phones).

Analyze Image describes the damage and returns a structured assessment: severity, damaged parts, a rough cost range, whether the vehicle looks drivable and whether the photo matches the story. The Damage triage decision table turns that and the cover into a band (fast track, standard, specialist or coverage check), an estimate band, a decision SLA and whether an inspection is suggested. Every photo is also copied with faces and licence plates blurred, because repairers do not need them.

The adjuster reviews the claim with the AI assessment clearly marked as a hint, picks a repairer from the Approved repairers table and approves the repair, asks for an inspection or declines. Approval and decline letters are generated as PDFs and emailed, and the chosen repairer gets the job with the blurred photos only. The adjuster always decides.

Starts from a form

Starts from a form page: share the Motor claim form (/f/<id>) in your app or website; each claim starts the workflow.

Someone fills in a form to start it: the workflow start form (Run dialog in the app, or your own portal posting to the API) or a standalone form page (/f/<id>) whose Form submitted trigger starts the workflow. People complete User Task forms along the way.

How forms work

The flow

Step by step

  1. 1

    Claim with photos

    The claimant fills in the themed claim form and uploads damage photos.

  2. 2

    AI damage assessment

    Analyze Image returns a description, labels and a structured answer: severity, damaged parts, cost range, drivable, consistency.

  3. 3

    Triage and SLA

    The Damage triage decision table sets the band, estimate band, inspection suggestion and the decision SLA.

  4. 4

    Blur for sharing

    Each photo is copied with faces and licence plates blurred for repairers.

  5. 5

    Adjuster review

    The adjuster sees the assessment as a hint, picks a repairer and approves, requests an inspection or declines.

  6. 6

    Letters and repairer job

    Approval or decline letters are emailed as PDFs; the repairer gets the blurred photos only.

Motor claim photo assessment — Damage photos from the claim form are analysed by AI, triaged by a decision table and reviewed by an adjuster, who approves the repair, asks for an inspection or declines; repairers only get copies with faces and plates blurred. The same canvas you get in the designer after installing.

Forms

The start form and the task forms

People start it from a form page (/f/<id>) with its own header, theme and buttons; submitting it starts the workflow. User Tasks show their fields and outcome buttons to the assignee.

Form page · /f/<id>

Motor claim: report damage

Report vehicle damage · 3-column grid · own header and theme · Its own page: share the link or open it on a tablet

Policy number * policy_number · text
Your name * claimant_name · text
Email * email · emailname@company.com
Phone phone · phone
Cover * cover · choice
ComprehensiveThird party, fire and theftThird party only
When did it happen? * incident_date · dateYYYY-MM-DD
Where? location · text
What happened? * description · textarea
Photos of the damage * damage_photos · attachments
Can the vehicle be driven? * drivable · choice
YesNoNot sure
The information I have given is true * declaration · boolean
Submit claim

User Task

Adjuster review

{{band}}: {{claim_ref}} ({{form.claimant_name}}) · 2-column grid · own header and theme

Approved amount approved_amount · currencyPrefilled: {{assessment.estimate_high}}
Repairer repairer · lookup
Repairer email repairer_email · emailname@company.com
Note to the claimant note · textarea
Approve repairRequest inspectionDecline

From your code

Start a run over the API

Every workflow can be started over REST, MCP or the CLI, whatever its trigger, with the sample input below. Runs start straight away on the published version; replace <workflow id> with the id the install created.

REST

shell
curl -X POST "$USERTASKS_URL/api/v1/workflows/start" \
  -H "Authorization: Bearer $USERTASKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"workflow_id":"<workflow id>","variables":{"policy_number":"POL-000123","claimant_name":"Riley Example","email":"riley.example@example.com","phone":"+1 555 0100","cover":"Comprehensive","incident_date":"2026-10-29","location":"Sample Street car park","description":"A trolley rolled into the driver door in the car park and dented it.","drivable":"Yes","declaration":true}}'

CLI

shell
usertasks workflows inputs <workflow id>          # the start form: keys, types, required
usertasks workflows run <workflow id> --input policy_number=POL-000123 --input claimant_name="Riley Example" --input email=riley.example@example.com --input phone="+1 555 0100" … --wait

What's included

11 assets, ready to adapt

TypeNameDetails
Email templateClaim approvedApproval letter to the claimant (PDF attached).
Email templateClaim declinedDecline letter to the claimant (PDF attached).
Email templateClaim receivedSent to the claimant when the photos arrive.
Email templateInspection neededSent when the adjuster asks for an inspection.
Email templateRepair job for repairerSent to the chosen repairer with the redacted photos (faces and plates blurred).
Data tableApproved repairersRepairers the adjuster can assign; redacted photos are sent to them.
Data tableMotor claimsClaims reported with damage photos: AI assessment, triage band, adjuster decision and repairer.
IntegrationGoogle Gemini (media AI)Media AI provider for transcription, image and video analysis and finding what to redact. Paste your Gemini API key on install (aistudio.google.com). To use OpenAI, Azure AI or AWS instead, point the media steps at that integration.
Decision tableDamage triage6 rules — Triage band, estimate band, SLA and whether an inspection is needed, from the AI damage assessment and the policy. Tune the bands to your book; the AI estimate is a hint for the adjuster, never a settlement.
formsMotor claim: report damageClaimants report vehicle damage with photos; the claim is assessed, triaged and sent to an adjuster.
WorkflowMotor claim photo assessment28 steps — Damage photos from the claim form are analysed by AI, triaged by a decision table and reviewed by an adjuster, who approves the repair, asks for an inspection or declines; repairers only get copies with faces and plates blurred.

Approved repairers · 3 sample rows

NameEmailRegionSpecialtyActive

Motor claims · 1 sample rows

ClaimPolicyClaimantEmailIncidentSeverity (AI)Damaged parts (AI)BandEstimate bandApprovedRepairerStatusDecided by

Requirements

What you connect it to

Credentials never travel in a package. The install wizard asks for what your environment must provide, or installs it incomplete until you finish setup.

Needs

  • Media AI provider — An API key for a media AI provider (Google Gemini by default; OpenAI, Azure AI, AWS and others can be swapped in) that transcribes, analyses and finds what to redact.
  • Assignees — People in your workspace to receive the User Tasks (picked on install).
  • Email — Email delivery configured for the instance (EMAIL_PROVIDER), used for notifications.

After installing

  1. Google Gemini (media AI): paste your Gemini API key. It analyses the damage and finds faces and plates to blur.
  2. Assignees: pick the adjuster who reviews claims (escalates to their manager after 48 hours).
  3. Tune the Damage triage bands and replace the sample Approved repairers.
  4. Set EMAIL_PROVIDER so claimants and repairers receive their emails.

Asked for on install

  • Integration “Google Gemini (media AI)”Required

    • Key valueconfig.auth_config.key_value
    • Base urlconfig.base_urldefault https://generativelanguage.googleapis.com· optional

  • Workflow “Motor claim photo assessment” assigneesRequired

    • User for step “Adjuster review”nodes.13.config.assignee_id

Install

Install it in your workspace

Works on UserTasks cloud and on any self-hosted instance. Installing creates the assets above; nothing runs until you complete setup and start it.

In the app

  1. Download insurance-claim-photo-assessment-1.0.0.utpkg.
  2. Open Automations → Packages and drag the file onto the page (or choose Import package). Browse gallery there lists every gallery package without downloading by hand.
  3. Pick the file. The wizard verifies the checksum, every file hash and the signature, and shows the readme.
  4. Review the changes (what is created) and the data rows.
  5. Fill in the requirements, or tick Keep incomplete and finish later with Complete setup.
  6. Done: the workflow is published and active once setup is complete.

With the CLI

shell
curl -fLO https://usertasks.com/gallery/insurance-claim-photo-assessment-1.0.0.utpkg
usertasks packages inspect insurance-claim-photo-assessment-1.0.0.utpkg       # offline: checksum, hashes, signature
usertasks packages install insurance-claim-photo-assessment-1.0.0.utpkg --dry-run
usertasks packages install insurance-claim-photo-assessment-1.0.0.utpkg       # prompts for each requirement
usertasks packages install insurance-claim-photo-assessment-1.0.0.utpkg --keep-incomplete --yes   # in CI; finish with:
usertasks packages complete insurance-claim-photo-assessment -f values.yaml

Verify the download

File SHA-256
234dce9c257e83e978b8549a26bed40ac29e19bf9ee3dd6d2d2c8073a298cad2
Package checksum (what is signed)
sha256:6dccd44e18915ba3f3b2ff5b9dc338dceb742503a3873bca1f40ad5139f7c235
Signer
UserTasks Gallery · 49:f3:04:90:47:02:4d:07:28:61:3d:dc:bb:aa:db:11

shasum -a 256 insurance-claim-photo-assessment-1.0.0.utpkg should print the file SHA-256. How gallery packages are signed.

Versions

Version 1.0.0

  1. v1.0.02026-10-30First release.

Installing a newer version upgrades in place: local credentials and requirement values are kept, and changes you made are flagged first. How packages work

More packages

Related

Browse the whole gallery