Routespring Logo
Request Demo

Removes work · Pilot-ready

Passenger compensation claims

Decide EU261, UK261, APPR and US refund claims under your written policy, and pay within limits.

For airline customer relations and legal.

The work the agent does
  1. 1Takes in claims from forms, email and claims firms, and matches each to the flight and ticket.
  2. 2Pulls the delay cause and duration from operations data and the delay codes.
  3. 3Decides eligibility and the amount under the regulation and your written policy.
  4. 4Drafts the decision letter with the reasoning, and pays within the limit you set.
  5. 5Prepares the file for claims the airline will defend.
The flow

Five steps, one branch to a person.

  1. 1

    Claim intake

  2. 2

    Pull flight data

  3. 3

    Decide under policy

  4. 4

    Draft and pay

  5. 5

    Defend the rest

Branch to a person: Denials on extraordinary circumstances. Payments above the limit you set. Anything heading to a regulator or a court.

Inside the workflow

What it reads, who signs off, what we count.

What the agent reads
  • Claim forms and correspondence
  • Flight operations data and delay codes
  • Fare and ticket records
  • Regulation text and your policy
Where a person signs off
  • Denials on extraordinary circumstances.
  • Payments above the limit you set.
  • Anything heading to a regulator or a court.
What gets measured
  • Cost per claim
  • Days from claim to decision
  • Decisions overturned on appeal

Time to shadow mode

6 to 8 weeks

From the day the 50 files arrive to the agent running beside your team.

Production, processing workflows

$2 to $6 per document

Reconciliation, schedule changes and claims. Priced per file handled, with a monthly minimum of $3,000. No platform fee. Full pricing

For your integration team

The API behind this workflow

Claims run outside the Crew Travel API. Passenger iROPS can carry the intake; the agent reads flight data and policy from your own sources.

Method

How passenger compensation claims goes live

  1. 1

    Week 1

    Pick the workflow and the owner

    One workflow your team already runs, with its documents, systems and written rules, one owner on your side, and one number that decides whether it worked.

  2. 2

    Weeks 1 to 2

    The 50-file test

    Fifty closed files with known outcomes, graded blind by two of your people. We write the agent without looking at them, run it, and report false positives and false negatives against the human baseline.

  3. 3

    Weeks 3 to 8

    Shadow mode

    About 100 new files run beside your team with no answers given. Your team compares weekly. The test set stays closed while we tune, so the agent is never fitted to it.

  4. 4

    Weeks 9 to 10

    Run alone on the cases it has earned

    The agent finishes the routine cases alone. Every batch is stamped with the policy version and can be undone. Exceptions go to a person with the facts gathered.

  5. 5

    After go-live

    Eight-week error watch

    Every finished case is checked for eight weeks, then a sample. Every correction joins the test set. The error rate is reported to the owner weekly.

W1W3W5W7W9Go-livePick workflow and owner50-file testShadow modeRun alone on earned casesError watchEight weeks of full checks, then a sample
Start here

Send us 50 closed files.

Fifty closed passenger compensation claims cases under NDA. Within two weeks you get the agent’s error rate against your own team and, for recovery workflows, the dollars it would have found. No charge.

  • NDA first
  • Two weeks
  • The report is yours