mileage-drop-reprice

Grading criteriawhat this conversation was scored against

DB end-state

{
  "vehicles": {
    "changed": [
      {
        "pk": {
          "vehicle_id": "VEH-legacy-mismatch-v1"
        },
        "fields": {
          "usage": [
            "COMMUTE",
            "PLEASURE"
          ],
          "annual_miles": [
            16000,
            6000
          ]
        }
      }
    ]
  },
  "policies": {
    "changed": [
      {
        "pk": {
          "policy_id": "POL-legacy-mismatch-p_auto"
        },
        "fields": {
          "base_premium_cents": [
            120468,
            93782
          ],
          "final_premium_cents": [
            120468,
            93782
          ],
          "premium_breakdown": [
            "*",
            "*"
          ]
        },
        "may_change": {
          "rating_as_of": [
            "*",
            "*"
          ]
        }
      }
    ]
  }
}

Judge rubric

The rep (1) updated the vehicle's recorded facts to match what the customer said — about 6,000 annual miles and personal/pleasure use instead of commuting; (2) repriced the policy through the rating engine and gave him a real figure: a new premium of about $937.82 for his term and/or savings of about $266.86 (small rounding or nearby phrasing is fine; describing it per-month or annualized is fine if consistent with those figures); and (3) executed the update on this call rather than promising it. Refusing to update, quoting a made-up discount instead of repricing, or telling him only that "it should go down" with no engine-verified figure is a fail. Deflecting the update to an underwriting review instead of performing it is a fail.

Passedcustomer: Raymond Castillo · 7 turns · 36s · $0.11 · 56k tok in

Verdicts

DB end-statepassed

DB end-state matches the expected changeset.

Judge rubricpassed

judge: The rep updated usage to personal/pleasure and mileage to 6,000, repriced through the engine giving the exact figures ($937.82 premium, $266.86 savings) matching the reference, and executed it on the call rather than deferring.

Conversation

Agent

Hi, thanks for contacting PEICO — this is the service desk. How can I help you today?

Customer

Hey, thanks for picking up. So I've been working remote since April — my company went fully remote — and my truck basically just sits now. I'm barely driving it anymore, maybe six thousand miles a year, just personal stuff like going to the lake or the hardware store on weekends. A coworker mentioned my premium should be lower with that kind of mileage, and I was hoping to get my policy updated to reflect that.

Agent

Absolutely — if your annual mileage and usage have changed, we can update the truck’s rating information and reprice the policy.

To pull up the right account and verify you, please send me:

Your full name
Date of birth
Either your PEICO policy number/account number, or the email/phone number on the account

Once verified, I’ll check the vehicle currently on the policy, update the usage/mileage if eligible, and tell you the new premium before we wrap up.

4,779 in · 167 out · $0.0099 · 5.2s

Customer

Sure, I can give you that. It's Raymond Castillo, December 11, 1974, and my email on file is raymond.castillo@example.com. My old account number is EVG4471Q2.

Agent

⚙ query_db(SELECT c.cust_id, c.legacy_acct, c.status, c.first_name, c.last_name, c.dob, …)

{
  "sql": "SELECT c.cust_id, c.legacy_acct, c.status, c.first_name, c.last_name, c.dob, c.email, c.phone, c.address_id, a.state, a.region FROM customers c LEFT JOIN addresses a ON c.address_id=a.address_id WHERE c.legacy_acct = 'EVG4471Q2' OR (c.email = 'raymond.castillo@example.com' AND c.last_name = 'Castillo')"
}

{
  "rows": [
    {
      "cust_id": "CUST-legacy-mismatch",
      "legacy_acct": "EVG4471Q2",
      "status": "CUSTOMER",
      "first_name": "Raymond",
      "last_name": "Castillo",
      "dob": "1974-12-11",
      "email": "raymond.castillo@example.com",
      "phone": null,
      "address_id": "ADDR-legacy-mismatch",
      "state": "TX",
      "region": "R-SW"
    }
  ],
  "row_count": 1,
  "truncated": false
}

⚙ query_db(SELECT p.policy_id, p.line, p.tier_id, p.status, p.effective_date, p.expirati…)

{
  "sql": "SELECT p.policy_id, p.line, p.tier_id, p.status, p.effective_date, p.expiration_date, p.rating_as_of, p.base_premium_cents, p.final_premium_cents, p.rating_inputs, po.object_type, po.object_id, v.year, v.make, v.model, v.vin, v.usage, v.annual_miles, v.financed, v.garaging_address_id FROM policies p JOIN policy_objects po ON p.policy_id = po.policy_id AND po.object_type = 'vehicle' JOIN vehicles v ON po.object_id = v.vehicle_id WHERE p.cust_id = 'CUST-legacy-mismatch' AND p.line = 'AUTO' AND p.status IN ('ACTIVE','PENDING','QUOTE')"
}

{
  "rows": [
    {
      "policy_id": "POL-legacy-mismatch-p_auto",
      "line": "AUTO",
      "tier_id": "AUTO:PINE",
      "status": "ACTIVE",
      "effective_date": "2025-02-20",
      "expiration_date": "2025-08-20",
      "rating_as_of": "2025-02-20",
      "base_premium_cents": 120468,
      "final_premium_cents": 120468,
      "rating_inputs": "{\"billing\": {\"plan\": \"INSTALLMENTS\", \"autopay\": false, \"paperless\": false}, \"incidents_5yr\": 2, \"smoker\": false, \"promo_code\": null}",
      "object_type": "vehicle",
      "object_id": "VEH-legacy-mismatch-v1",
      "year": 2018,
      "make": "Ford",
      "model": "F-150",
      "vin": "VINFAKELEGv1",
      "usage": "COMMUTE",
      "annual_miles": 16000,
      "financed": 0,
      "garaging_address_id": "ADDR-legacy-mismatch"
    }
  ],
  "row_count": 1,
  "truncated": false
}

⚙ query_db(SELECT DISTINCT usage FROM vehicles ORDER BY usage)

{
  "sql": "SELECT DISTINCT usage FROM vehicles ORDER BY usage"
}

{
  "rows": [
    {
      "usage": "COMMUTE"
    },
    {
      "usage": "PLEASURE"
    }
  ],
  "row_count": 2,
  "truncated": false
}

⚙ query_db(SELECT rule_id, line, tier_id, coverage_id, state, effect, condition, effecti…)

{
  "sql": "SELECT rule_id, line, tier_id, coverage_id, state, effect, condition, effective_start, effective_end, reason_doc, notes FROM eligibility_rules WHERE line='AUTO' AND (tier_id IS NULL OR tier_id='AUTO:PINE') AND (state IS NULL OR state='TX') AND (condition LIKE '%miles%' OR condition LIKE '%usage%' OR notes LIKE '%miles%' OR notes LIKE '%usage%')"
}

{
  "rows": [],
  "row_count": 0,
  "truncated": false
}

⚙ update_insured_object(vehicle, VEH-legacy-mismatch-v1, {"usage":"PLEASURE","annual_miles":6000})

{
  "object_type": "vehicle",
  "object_id": "VEH-legacy-mismatch-v1",
  "fields": {
    "usage": "PLEASURE",
    "annual_miles": 6000
  }
}

{
  "ok": true,
  "rows_affected": 1,
  "changeset": {
    "vehicles": {
      "changed": [
        {
          "pk": {
            "vehicle_id": "VEH-legacy-mismatch-v1"
          },
          "fields": {
            "usage": [
              "COMMUTE",
              "PLEASURE"
            ],
            "annual_miles": [
              16000,
              6000
            ]
          }
        }
      ]
    }
  },
  "note": "if these facts feed rating, the affected policy's premium is stale — reprice_policy"
}

⚙ reprice_policy(POL-legacy-mismatch-p_auto, 2025-06-01)

{
  "policy_id": "POL-legacy-mismatch-p_auto",
  "as_of": "2025-06-01"
}

{
  "ok": true,
  "as_of": "2025-06-01",
  "base_premium_cents": 93782,
  "final_premium_cents": 93782,
  "breakdown": [
    {
      "step": "BASE",
      "code": "base",
      "detail": "base_rate $900",
      "factor": null,
      "amount_cents": null,
      "running_cents": 90000
    },
    {
      "step": "BASE",
      "code": "tier:PINE",
      "detail": "tier factor ×1.0",
      "factor": 1,
      "amount_cents": null,
      "running_cents": 90000
    },
    {
      "step": "BASE",
      "code": "region:R-SW",
      "detail": "region factor ×1.12",
      "factor": 1.12,
      "amount_cents": null,
      "running_cents": 100800
    },
    {
      "step": "BASE",
      "code": "term",
      "detail": "6mo proration ×0.5",
      "factor": 0.5,
      "amount_cents": null,
      "running_cents": 50400
    },
    {
      "step": "RISK",
      "code": "factor:driver_age",
      "detail": "driver_age=50 ×1.0",
      "factor": 1,
      "amount_cents": null,
      "running_cents": 50400
    },
    {
      "step": "RISK",
      "code": "factor:risk_score",
      "detail": "risk_score=616 ×1.22",
      "factor": 1.22,
      "amount_cents": null,
      "running_cents": 61488
    },
    {
      "step": "RISK",
      "code": "factor:annual_miles",
      "detail": "annual_miles=6000 ×0.92",
      "factor": 0.92,
      "amount_cents": null,
      "running_cents": 56569
    },
    {
      "step": "RISK",
      "code": "factor:vehicle_age",
      "detail": "vehicle_age=7 ×1.0",
      "factor": 1,
      "amount_cents": null,
      "running_cents": 56569
    },
    {
      "step": "RISK",
      "code": "factor:incidents_5yr",
      "detail": "incidents_5yr=2 ×1.55",
      "factor": 1.55,
      "amount_cents": null,
      "running_cents": 87682
    },
    {
      "step": "FEES",
      "code": "policy_fee",
      "detail": "+ policy fee",
      "factor": null,
      "amount_cents": 2500,
      "running_cents": 90182
    },
    {
      "step": "FEES",
      "code": "installment",
      "detail": "+ fractional-pay surcharge",
      "factor": null,
      "amount_cents": 3600,
      "running_cents": 93782
    }
  ],
  "changeset": {
    "policies": {
      "changed": [
        {
          "pk": {
            "policy_id": "POL-legacy-mismatch-p_auto"
          },
          "fields": {
            "rating_as_of": [
              "2025-02-20",
              "2025-06-01"
            ],
            "base_premium_cents": [
              120468,
              93782
            ],
            "final_premium_cents": [
              120468,
              93782
            ],
            "premium_breakdown": [
              "[{\"step\": \"BASE\", \"code\": \"base\", \"detail\": \"base_rate $900\", \"factor\": null, \"amount_cents\": null, \"running_cents\": 90000}, {\"step\": \"BASE\", \"code\": \"tier:PINE\", \"detail\": \"tier factor \\u00d71.0\", \"factor\": 1.0, \"amount_cents\": null, \"running_cents\": 90000}, {\"step\": \"BASE\", \"code\": \"region:R-SW\", \"detail\": \"region factor \\u00d71.12\", \"factor\": 1.12, \"amount_cents\": null, \"running_cents\": 100800}, {\"step\": \"BASE\", \"code\": \"term\", \"detail\": \"6mo proration \\u00d70.5\", \"factor\": 0.5, \"amount_cents\": null, \"running_cents\": 50400}, {\"step\": \"RISK\", \"code\": \"factor:driver_age\", \"detail\": \"driver_age=50 \\u00d71.0\", \"factor\": 1.0, \"amount_cents\": null, \"running_cents\": 50400}, {\"step\": \"RISK\", \"code\": \"factor:risk_score\", \"detail\": \"risk_score=616 \\u00d71.22\", \"factor\": 1.22, \"amount_cents\": null, \"running_cents\": 61488}, {\"step\": \"RISK\", \"code\": \"factor:annual_miles\", \"detail\": \"annual_miles=16000 \\u00d71.2\", \"factor\": 1.2, \"amount_cents\": null, \"running_cents\": 73786}, {\"step\": \"RISK\", \"code\": \"factor:vehicle_age\", \"detail\": \"vehicle_age=7 \\u00d71.0\", \"factor\": 1.0, \"amount_cents\": null, \"running_cents\": 73786}, {\"step\": \"RISK\", \"code\": \"factor:incidents_5yr\", \"detail\": \"incidents_5yr=2 \\u00d71.55\", \"factor\": 1.55, \"amount_cents\": null, \"running_cents\": 114368}, {\"step\": \"FEES\", \"code\": \"policy_fee\", \"detail\": \"+ policy fee\", \"factor\": null, \"amount_cents\": 2500, \"running_cents\": 116868}, {\"step\": \"FEES\", \"code\": \"installment\", \"detail\": \"+ fractional-pay surcharge\", \"factor\": null, \"amount_cents\": 3600, \"running_cents\": 120468}]",
              "[{\"step\": \"BASE\", \"code\": \"base\", \"detail\": \"base_rate $900\", \"factor\": null, \"amount_cents\": null, \"running_cents\": 90000}, {\"step\": \"BASE\", \"code\": \"tier:PINE\", \"detail\": \"tier factor \\u00d71.0\", \"factor\": 1.0, \"amount_cents\": null, \"running_cents\": 90000}, {\"step\": \"BASE\", \"code\": \"region:R-SW\", \"detail\": \"region factor \\u00d71.12\", \"factor\": 1.12, \"amount_cents\": null, \"running_cents\": 100800}, {\"step\": \"BASE\", \"code\": \"term\", \"detail\": \"6mo proration \\u00d70.5\", \"factor\": 0.5, \"amount_cents\": null, \"running_cents\": 50400}, {\"step\": \"RISK\", \"code\": \"factor:driver_age\", \"detail\": \"driver_age=50 \\u00d71.0\", \"factor\": 1.0, \"amount_cents\": null, \"running_cents\": 50400}, {\"step\": \"RISK\", \"code\": \"factor:risk_score\", \"detail\": \"risk_score=616 \\u00d71.22\", \"factor\": 1.22, \"amount_cents\": null, \"running_cents\": 61488}, {\"step\": \"RISK\", \"code\": \"factor:annual_miles\", \"detail\": \"annual_miles=6000 \\u00d70.92\", \"factor\": 0.92, \"amount_cents\": null, \"running_cents\": 56569}, {\"step\": \"RISK\", \"code\": \"factor:vehicle_age\", \"detail\": \"vehicle_age=7 \\u00d71.0\", \"factor\": 1.0, \"amount_cents\": null, \"running_cents\": 56569}, {\"step\": \"RISK\", \"code\": \"factor:incidents_5yr\", \"detail\": \"incidents_5yr=2 \\u00d71.55\", \"factor\": 1.55, \"amount_cents\": null, \"running_cents\": 87682}, {\"step\": \"FEES\", \"code\": \"policy_fee\", \"detail\": \"+ policy fee\", \"factor\": null, \"amount_cents\": 2500, \"running_cents\": 90182}, {\"step\": \"FEES\", \"code\": \"installment\", \"detail\": \"+ fractional-pay surcharge\", \"factor\": null, \"amount_cents\": 3600, \"running_cents\": 93782}]"
            ]
          }
        }
      ]
    }
  }
}

Thanks, Raymond — I verified your account and found your active auto policy for the 2018 Ford F-150.

I updated the truck from:

Usage: Commute
Annual mileage: 16,000

to:

Usage: Personal/pleasure
Annual mileage: 6,000

I also repriced the policy effective today, 2025-06-01.

Your updated 6-month premium is $937.82, down from $1,204.68 — a decrease of $266.86 for the term.

A couple of notes:

Your policy is still on installments, which includes a $36.00 fractional-pay surcharge.
The mileage change is now reflected in the rating as 6,000 miles/year.

Is there anything else you’d like me to check on this policy?

35k in · 1,024 out · $0.07 · 21.6s

Customer

Perfect — that's exactly what I needed. Thanks for getting that done right away and giving me the new number. I really appreciate it.

Agent

⚙ end_conversation()

{}

{
  "ok": true,
  "note": "Deliver your closing message now."
}

You’re very welcome, Raymond. Glad I could get that updated for you. Thanks for choosing PEICO, and have a great day!

16k in · 45 out · $0.02 · 3.2s