Foresee

Docs

For AI agents: the site index is /llms.txt and the full text is /llms-full.txt.

Foresee enables AI assistants to compare home and auto insurance across every carrier and coverage option, by providing instant, accurate, detailed quote estimates.

Using Foresee

Foresee hosts two MCP servers:

Users who want a simple, low-friction quote estimate without giving up their PII use:

https://mcp.go-foresee.com/mcp

Users who also want to confirm quotes estimates directly with carriers can dispatch Foresee's computer use agents via:

https://agents.go-foresee.com/mcp

Neither server requires authentication.

Tools

Foresee publishes two tools on the MCP servers:

Tool	Purpose	agents.	mcp.
quote_insurance	Generate instant, accurate, detailed quote estimates	✅	✅
live_carrier_quotes	Confirm quote estimates with carriers	✅	❌

Tool 1: quote_insurance

Purpose: generate instant, itemized quote estimates from the carriers Foresee supports, across the lines and states Foresee currently serves, in one call.

Input Parameters

Parameter	Type	Required	Details
profile	object	yes	see Profile
lines	object	yes	Keys are the lines to price (auto, home, renters); values are that line's coverage options (see Coverage options)
carriers	string[]	no	Defaults to "all carriers"
include_failures	boolean	no	true

Profile

Core Profile

There is a core input profile, plus additional blocks for auto and home/renters insurance. The only required fields are age (or dob), ZIP, and (for auto insurance) vehicle details.

Omitted optional fields become declared assumptions: we choose a conservative stand-in, reported back as assumptions — e.g. auto.vehicles[].annual_mileage = 12000, with a tighten_by entry listing the assumptions which would move the price the most. prior_insurance means insurance for the same line; companion_policies means insurance for a different line

Field	Type	Required
zip_code	string	yes
age	integer	yes
dob	string, YYYY-MM-DD	accepted alternative to age
city	string	no
gender	string	no
marital_status	string	no
education	string	no
employment_status	string	no
occupation	string	no
credit_range	string	no
home_ownership_status	string	no
residence_type	string	no
military_affiliation	string	no
memberships	string[]	no
effective_date	string	no
prior_insurance	object	no
companion_policies	object[] — {line, carrier}	no

companion_policies lists policies the household already holds, each with the carrier that writes it — {"line": "home", "carrier": "State Farm"}. A carrier's multi-policy discount applies only to a policy it writes, so a held policy with no carrier earns none, and the quote asks for the carrier under tighten_by.

Auto Insurance Profile

Field	Type	Required
auto.vehicles[].year	integer	yes
auto.vehicles[].make	string	yes
auto.vehicles[].model	string	yes
auto.vehicles[].ownership	string	no
auto.vehicles[].annual_mileage	integer	no
auto.vehicles[].primary_use	string	no
auto.vehicles[].garaging_zip	string	no
auto.drivers[].relation	string	no (self for the first)
auto.drivers[].dob	string	no
auto.drivers[].years_licensed	integer	no
auto.drivers[].accidents	object[]	no
auto.drivers[].violations	object[]	no
auto.drivers[].sr22_required	boolean	no

accidents and violations are lists of dated entries — {"on": "2025-01", "kind": "speeding"}, {"on": "2023-06-15", "at_fault": true} — where an empty list is a clean record. An entry missing on (or a violation missing kind) is refused, naming its path.

Home & Renters Insurance Profile

Field	Type	Required
property.year_built	integer	no
property.construction_type	string	no
property.roof_type	string	no
property.square_feet	integer	no
property.protection_class	string	no
property.replacement_cost	integer	no
property.devices	string[]	no
property.losses	object[]	no

Coverage options

Each key in lines takes that line's coverage options. Nothing is priced at a server default: the options you pass are the ones priced.

Auto

Option	Type	Required	What it covers
bi	string	yes	Bodily injury liability: injuries you cause to other people. Per-person/per-accident limit in $000s, e.g. "100/300"
pd	integer	yes	Property damage liability: damage you cause to other people's cars and property. Limit in $000s, e.g. 100
coll_deductible	integer	yes	Collision: damage to your own car from a crash, whoever is at fault. The deductible you pay per claim, in dollars
comp_deductible	integer	yes	Comprehensive: damage to your own car from anything other than a crash — theft, fire, hail, vandalism, hitting an animal. The deductible you pay per claim, in dollars
um	string	no	Uninsured/underinsured motorist: your injuries when the at-fault driver has no or too little insurance. Per-person/per-accident limit in $000s, e.g. "100/300"
medpay	integer	no	Medical payments: medical bills for you and your passengers, whoever is at fault. Limit in dollars, e.g. 5000

Home

Option	Type	Required	What it covers
coverage_a	integer	yes	Dwelling: rebuilding the house itself. Limit in dollars, usually the replacement cost
coverage_e	integer	yes	Personal liability: injuries or damage you're legally responsible for, on or off the property. Limit in dollars
coverage_f	integer	yes	Medical payments to others: a guest's medical bills after an injury on your property, whoever is at fault. Limit in dollars
aop_deductible	integer	yes	All-other-perils deductible: what you pay per claim for everything except perils with their own deductible (such as earthquake). In dollars

Coverages B (other structures, such as a detached garage or fence), C (personal property — your belongings), and D (loss of use — living costs while the house can't be lived in) are not asked in dollars — they come back in sel as ratios of Coverage A that were priced.

Renters

Option	Type	Required	What it covers
coverage_c	integer	yes	Personal property: your belongings. Limit in dollars
coverage_e	integer	yes	Personal liability: injuries or damage you're legally responsible for. Limit in dollars
coverage_f	integer	yes	Medical payments to others: a guest's medical bills after an injury in your home, whoever is at fault. Limit in dollars
deductible	integer	yes	What you pay per claim before coverage starts. In dollars
coverage_d	integer	no	Loss of use: extra living costs if you have to move out while the place is repaired. Limit in dollars

Response format

A priced result arrives entirely in structuredContent; content is empty. The rating detail is the dense field: compact machine text, one section per line, shown in the response blocks below. Beside it sit the headline fields per line under by_line (carriers with monthly, confidence_interval, carrier_quote_url, warnings, rated_vs_asked; plus assumptions, tighten_by, failures), and presentation (how to present the prices), bundle and skipped at the top. Refusals (profile_required, coverage_required) are plain JSON with no dense.

Prefix	Frequency	Meaning
Q	once per line	What was priced: state, line of business, coverage selection
assumptions:	once per line	Assumptions made by Foresee; high_impact: true means that this field materially moves the quote estimate
tighten_by:	once per line	The profile paths of the missing facts that would most move the price
not_priced:	when applicable	Carriers excluded, with the reason
C	once per carrier	Carrier, writing entity, monthly premium (point estimate and confidence interval)
W	as needed	A note on the carrier above, e.g. no online quote page
L	once per carrier	Monthly cost per coverage, under codes that mean the same coverage at every carrier (BI, PD, UMBI, MEDPAY, COMP, COLL…); A+B is one premium covering both, FEE a flat fee
D	per carrier	Price ladders: for each coverage lever, every offered rung as ±$/mo against the quoted monthly, everything else held at the selection. +0.00 marks the selected rung; (asked X) = X isn't offered and the price sits at the nearest offered rung. Re-price from D; don't re-call

---

Example: auto

A 41-year-old in ZIP 90066 with a 2021 Honda Civic.

Mercury shows the plain carrier cell; Travelers rates through two possible writing entities, so its cell carries a ci segment (the placement span). USAA lands in not_priced with the carrier's own reason.

{
  "profile": {
    "zip_code": "90066",
    "age": 41,
    "auto": {"vehicles": [{"year": 2021, "make": "Honda", "model": "Civic"}]}
  },
  "lines": {"auto": {"bi": "100/300", "pd": 100, "coll_deductible": 500, "comp_deductible": 500}},
  "carriers": ["mercury", "travelers", "usaa"]
}

Every omitted profile field comes back as a declared assumption — the fat assumptions: block below is caused by the thin request above, and tighten_by: lists the nine answers that would most move the price. Mercury shows the plain carrier cell; Travelers rates through two possible writing entities, so its cell carries a ci segment (the placement span). USAA lands in not_priced with the carrier's own reason.

Q CA auto sel={"bi":"100/300","coll_deductible":500,"comp_deductible":500,"pd":100}
assumptions: [{"assumed":"Single","field":"marital_status","high_impact":false},{"assumed":12000,"field":"auto.vehicles[].annual_mileage","high_impact":true},{"assumed":"Commute","field":"auto.vehicles[].primary_use","high_impact":true},{"assumed":15,"field":"auto.vehicles[].one_way_miles","high_impact":true},{"assumed":5,"field":"auto.vehicles[].commute_days","high_impact":false},{"assumed":16,"field":"auto.drivers[].age_first_licensed","high_impact":true,"note":"CA Good Driver discount (at least 20% off every CA price here, INS §1861.025) is granted on this assumption: it rates the applicant as licensed 3+ years. If they were first licensed less than 3 years ago, these prices are understated — send auto.drivers[].age_first_licensed (or date_first_licensed / years_licensed on the same driver) and re-quote."},{"assumed":[],"field":"auto.drivers[].accidents","high_impact":true},{"assumed":[],"field":"auto.drivers[].violations","high_impact":true},{"assumed":false,"field":"prior_insurance.insured","high_impact":true},{"assumed":null,"field":"home_ownership_status","high_impact":false},{"assumed":null,"field":"occupation","high_impact":true},{"assumed":null,"field":"memberships","high_impact":true}]
tighten_by: auto.vehicles[].annual_mileage,auto.vehicles[].primary_use,auto.vehicles[].one_way_miles,auto.drivers[].age_first_licensed,auto.drivers[].accidents,auto.drivers[].violations,prior_insurance.insured,occupation,memberships
not_priced: usaa:USAA: military families only — set military_affiliation to quote.
C mercury|Mercury Insurance Company|235.11
L BI:56.33,PD:44.10,UMBI:16.85,MEDPAY:0.97,COMP:17.49,COLL:99.38
D bi 100/300=30/60:-9.70,50/100:-6.72,100/300:+0.00,250/500:+12.31,300/300:+12.68,500/500:+23.13
D pd 100=15:-7.99,25:-6.39,50:-2.88,100:+0.00,250:+2.56,300:+3.83
D coll_deductible 500=100:+19.87,200:+14.91,250:+12.42,500:+0.00,1000:-9.94,2000:-29.81,2500:-39.75
D comp_deductible 500=25:+25.74,50:+17.88,100:+11.00,200:+6.09,250:+2.75,500:+0.00,1000:-2.75,2000:-5.70,2500:-8.06
C travelers|Travelers Commercial Insurance Company|368.50|ci 327.21-415.00
L BI:149.00,PD:70.17,COMP:15.50,COLL:114.33,UMBI:19.50
D bi 100/300=15/30:-61.67,25/50:-39.33,30/60:-32.83,50/100:-13.50,100/300:+0.00,250/500:+12.50,500/500:+16.67,1000/1000:+52.67
D pd 100=5:-21.50,10:-10.50,15:-6.67,25:-2.83,50:-0.67,100:+0.00,250:+0.50,300:+0.83,500:+1.17
D coll_deductible 500=100:+22.17,250:+13.17,500:+0.00,1000:-19.33,1500:-34.50,2500:-56.50,5000:-86.00
D comp_deductible 500=0:+11.17,50:+9.67,100:+8.00,250:+2.17,500:+0.00,1000:-1.67,1500:-3.67,2500:-6.50,5000:-10.50

---

Example: home

The same 41-year-old as above, insuring a frame house built in 1998 with a replacement cost of $450,000:

{
  "profile": {
    "zip_code": "90066",
    "age": 41,
    "property": {"year_built": 1998, "construction_type": "frame", "replacement_cost": 450000}
  },
  "lines": {"home": {"coverage_a": 450000, "coverage_e": 300000, "coverage_f": 1000, "aop_deductible": 1000}},
  "carriers": ["mercury", "autoclub"]
}

sel echoes B/C/D as the ratios of Coverage A that were priced. Each carrier's L is its base premium (HO_BASE) plus fees. Dwelling facts are in assumptions:/tighten_by: — here roof type, protection class, and a clean loss history.

Q CA home sel={"aop_deductible":1000,"coverage_a":450000,"coverage_b_pct":0.1,"coverage_c_pct":0.5,"coverage_d_pct":0.2,"coverage_e":300000,"coverage_f":1000}
assumptions: [{"assumed":"Asphalt Shingle","field":"property.roof_type","high_impact":false},{"assumed":1,"field":"property.stories","high_impact":false},{"assumed":2,"field":"property.bathrooms","high_impact":false},{"assumed":1,"field":"property.units","high_impact":false},{"assumed":"owner occupied","field":"property.occupancy","high_impact":false},{"assumed":5,"field":"property.protection_class","high_impact":true},{"assumed":"Attached","field":"property.garage","high_impact":false},{"assumed":"Single","field":"marital_status","high_impact":false},{"assumed":[],"field":"property.losses","high_impact":true}]
tighten_by: property.protection_class,property.losses
C mercury|CALIFORNIA AUTOMOBILE INS CO|123.67
L HO_BASE:118.76,FEE:3.75,FEE:1.16,FEE:0.01
D aop_deductible 1000=500:+13.38,1000:+0.00,1500:-5.38,2500:-21.45,3500:-26.58,5000:-37.01,10000:-48.28,25000:-63.01,50000:-72.51
D coverage_a 450000=30000:-90.60,65000:-82.94,95000:-76.38,130000:-68.81,165000:-61.24,195000:-54.76,230000:-47.27,265000:-39.79,295000:-33.39,330000:-25.82,365000:-18.34,395000:-11.94,430000:-4.37,445000:-1.17,450000:+0.00,455000:+1.01,465000:+3.20,500000:+10.86,570000:+26.34,630000:+39.88,700000:+56.03,770000:+72.77,830000:+87.49,900000:+105.41,970000:+124.09,2500000:+523.01,6000000:+1464.79
D coverage_e 300000=100000:-1.34,200000:-0.58,300000:+0.00,500000:+0.68,1000000:+4.04
D coverage_f 1000=1000:+0.00,2000:+0.17,5000:+0.42
C autoclub|Interinsurance Exchange of the Automobile Club|146.10
L HO_BASE:144.50,FEE:1.60
D aop_deductible 1000=500:+20.98,750:+7.59,1000:+0.00,1500:-11.45,2000:-16.93,3000:-21.06,5000:-25.36,10000:-28.73,15000:-51.90,20000:-63.44,25000:-71.53,30000:-77.34,50000:-90.49
D coverage_a 450000=60000:-120.65,90000:-115.51,110000:-110.96,130000:-105.66,150000:-99.59,170000:-92.85,190000:-86.53,220000:-76.17,250000:-64.54,280000:-54.09,320000:-40.02,350000:-29.15,360000:-26.54,400000:-16.00,440000:-3.62,450000:+0.00,460000:+2.45,480000:+9.44,550000:+32.95,650000:+77.19,750000:+98.00,850000:+116.62,950000:+147.71,2000000:+475.47,4000000:+1099.41,10000000:+2982.24

---

Example: renters

A different household at the same ZIP: a 27-year-old renter:

{
  "profile": {"zip_code": "90066", "dob": "1998-11-11"},
  "lines": {"renters": {"coverage_c": 30000, "coverage_e": 100000, "coverage_f": 1000, "deductible": 500}},
  "carriers": ["farmers", "usaa"]
}

Q CA renters sel={"coverage_c":30000,"coverage_e":100000,"coverage_f":1000,"deductible":500}
assumptions: [{"assumed":2000,"field":"property.year_built","high_impact":false},{"assumed":5,"field":"property.protection_class","high_impact":false},{"assumed":"Single","field":"marital_status","high_impact":false},{"assumed":[],"field":"property.losses","high_impact":true}]
tighten_by: property.losses
not_priced: usaa:USAA: military families only — set military_affiliation to quote.
C farmers|Fire Insurance Exchange|29.88
L RENTERS_BASE:29.17,FEE:0.42,FEE:0.30
D deductible 500=100:+5.89,250:+1.85,500:+0.00,1000:-2.61,1500:-4.29,2500:-6.73
D coverage_c 30000=4000:-16.33,10000:-11.95,17000:-7.15,23000:-3.87,29000:-0.59,30000:+0.00,31000:+0.51,37000:+3.79,43000:+7.07,49000:+10.36,55000:+13.64,62000:+17.43,68000:+20.71,74000:+23.99,81000:+27.78,87000:+31.06,93000:+34.35,100000:+38.14,106000:+41.42,112000:+44.70,118000:+47.99,125000:+51.77,131000:+55.06,137000:+58.34,144000:+62.13,150000:+65.41
D coverage_e 100000=100000:+0.00,300000:+3.28,500000:+5.56,1000000:+10.69

---

Example: auto + renters

The same 27-year-old renter, now with a car. Empty violations and accidents lists mean a clean record, so the driving-record questions leave assumptions: entirely.

{
  "profile": {
    "zip_code": "90066",
    "age": 27,
    "prior_insurance": {"insured": true, "carrier": "GEICO", "since": "2019"},
    "auto": {"drivers": [{"violations": [], "accidents": []}],
             "vehicles": [{"year": 2021, "make": "Honda", "model": "Civic", "annual_mileage": 9000}]},
    "property": {"year_built": 1978, "square_feet": 850}
  },
  "lines": {
    "auto": {"bi": "100/300", "pd": 100, "coll_deductible": 500, "comp_deductible": 500},
    "renters": {"coverage_c": 30000, "coverage_e": 100000, "coverage_f": 1000, "deductible": 500}
  },
  "carriers": ["farmers", "mercury"]
}

Since we now provide record, mileage, and insurance history,the auto assumptions: shrink to eight entries and its tighten_by: to five. The renters section declares its own dwelling stand-ins. Mercury prices auto only; Farmers prices both lines.

Q CA auto sel={"bi":"100/300","coll_deductible":500,"comp_deductible":500,"pd":100}
assumptions: [{"assumed":"Single","field":"marital_status","high_impact":false},{"assumed":"Commute","field":"auto.vehicles[].primary_use","high_impact":true},{"assumed":15,"field":"auto.vehicles[].one_way_miles","high_impact":true},{"assumed":5,"field":"auto.vehicles[].commute_days","high_impact":false},{"assumed":16,"field":"auto.drivers[].age_first_licensed","high_impact":true,"note":"CA Good Driver discount (at least 20% off every CA price here, INS §1861.025) is granted on this assumption: it rates the applicant as licensed 3+ years. If they were first licensed less than 3 years ago, these prices are understated — send auto.drivers[].age_first_licensed (or date_first_licensed / years_licensed on the same driver) and re-quote."},{"assumed":null,"field":"home_ownership_status","high_impact":false},{"assumed":null,"field":"occupation","high_impact":true},{"assumed":null,"field":"memberships","high_impact":true}]
tighten_by: auto.vehicles[].primary_use,auto.vehicles[].one_way_miles,auto.drivers[].age_first_licensed,occupation,memberships
C mercury|Mercury Insurance Company|289.94
L BI:66.80,PD:52.55,UMBI:17.38,MEDPAY:1.05,COMP:23.50,COLL:128.67
D bi 100/300=30/60:-11.50,50/100:-7.96,100/300:+0.00,250/500:+14.60,300/300:+15.04,500/500:+27.43
D pd 100=15:-9.52,25:-7.61,50:-3.43,100:+0.00,250:+3.05,300:+4.57
D coll_deductible 500=100:+25.74,200:+19.30,250:+16.09,500:+0.00,1000:-12.87,2000:-38.60,2500:-51.47
D comp_deductible 500=25:+34.59,50:+24.03,100:+14.79,200:+8.19,250:+3.70,500:+0.00,1000:-3.70,2000:-7.66,2500:-10.83
C farmers|Farmers Insurance Exchange|398.00
L BI:111.83,PD:73.33,UMBI:28.33,UMPD:1.50,MEDPAY:13.33,COMP:34.00,COLL:133.17,FEE:2.50
D bi 100/300=30/60:-23.83,50/100:-14.67,100/300:+0.00,250/500:+9.83,500/500:+23.83,500/1000:+29.83
D pd 100=15:-8.83,25:-5.00,50:-1.50,100:+0.00,250:+1.33,500:+3.17
D coll_deductible 500=250:+30.67,500:+0.00,750:-13.67,1000:-23.50,1500:-37.50,2500:-56.33,5000:-87.00
D comp_deductible 500=100:+23.67,250:+9.17,500:+0.00,750:-7.17,1000:-10.67,1500:-13.50,2500:-18.83,5000:-21.17
Q CA renters sel={"coverage_c":30000,"coverage_e":100000,"coverage_f":1000,"deductible":500}
assumptions: [{"assumed":5,"field":"property.protection_class","high_impact":false},{"assumed":"Single","field":"marital_status","high_impact":false},{"assumed":[],"field":"property.losses","high_impact":true}]
tighten_by: property.losses
not_priced: mercury:no filed-rate renters program served in CA yet
C farmers|Fire Insurance Exchange|29.88
L RENTERS_BASE:29.17,FEE:0.42,FEE:0.30
D deductible 500=100:+5.89,250:+1.85,500:+0.00,1000:-2.61,1500:-4.29,2500:-6.73
D coverage_c 30000=4000:-16.33,10000:-11.95,17000:-7.15,23000:-3.87,29000:-0.59,30000:+0.00,31000:+0.51,37000:+3.79,43000:+7.07,49000:+10.36,55000:+13.64,62000:+17.43,68000:+20.71,74000:+23.99,81000:+27.78,87000:+31.06,93000:+34.35,100000:+38.14,106000:+41.42,112000:+44.70,118000:+47.99,125000:+51.77,131000:+55.06,137000:+58.34,144000:+62.13,150000:+65.41
D coverage_e 100000=100000:+0.00,300000:+3.28,500000:+5.56,1000000:+10.69

---

Tool 2: live_carrier_quotes

Purpose: confirm quote estimates on the carriers' own quote sites.

This tool is idempotent: the first call commissions the computer use agents; calling again with the same arguments collects progress and results from the first call.

A live dispatch submits the user's real details to the carriers, who may perform a soft credit check. User's consent is gathered before the tool is called.

Foresee only collects quotes; it does not take payment or bind insurance.

Input Parameters

Parameter	Type	Required	Details
profile	object	yes	Same fields as quote_insurance — the rating facts
lines	object	yes	One key per line to walk, each value that line's ask (see below); several keys commission bundled walks
user_authorization	string	yes	The user's in-chat affirmation, verbatim (e.g. yes, go ahead)
identity	object	usually	The user's details.
carriers	string[]	no	Restrict the fan; defaults to every carrier with a validated walk for the lines + state

lines

Line	Ask	Why
auto	required — the same four axes as quote_insurance (bi, pd, coll_deductible, comp_deductible), as actual numbers	The limits and deductibles the agents ask the carriers' forms for
home	none — {"home": null}	The carrier's own form prices its package (dwelling amount from its replacement-cost estimate); the agents report what it chose. A supplied ask is refused loudly, not silently ignored
renters	required — coverage_c, coverage_e, coverage_f, deductible, as actual dollars	The agents type the user's numbers on the form instead of accepting its defaults; Foresee never invents them

Several keys at once commission bundled walks: each carrier that writes all the named lines is driven through its own multi-line quote flow and reports per-line premiums plus its own bundle total; a carrier writing only some of the lines is walked for those alone. Per-line ask rules are unchanged by bundling.

identity

Field	Type	Required	Details
first_name	string	yes	Legal first name
last_name	string	yes	Legal last name
dob	string, YYYY-MM-DD	yes
street	string	yes	Street address (line 1)
unit	string	no	Apartment/unit (line 2)
city	string	yes
zip_code	string	no	Only when it differs from the profile's
email	string	yes	Carriers send the quote here
phone	string	no

Response

Field	Meaning
status	in_progress / partial / complete — re-call with the same arguments to collect
agents	One entry per carrier (see below)
note	What to do next, e.g. re-call timing, or that a prior run's results were returned
authorization_recorded	On the receipt: the consent record was stored before any carrier saw the risk
skipped	Carriers NOT dispatched, each with the reason (no_deterministic_walk, missing_facts with the facts named)
not_dispatched	Engine-priced carriers this dispatch will not walk, with why (held: …, no_walk, not_walked, offline, not_sold) — a recommendation the walk lane cannot confirm never silently vanishes
needs	On a missing_facts refusal: per-carrier facts to collect from the user, with exact schema paths — and, for closed-vocabulary fields, the accepted values
assumptions	Unasserted minor form facts the walks resolved to declared no-claim answers: the profile path (field) and the value submitted (assumed) — relay every one with the results
error / detail	Every refusal is a structured {"error", "detail"} dict

Each agents entry:

Field	When	Meaning
carrier_key, carrier	always	Roster key + display name
status	always	in_progress / complete / failed
lines	always	The lines this walk covers — several on a bundled walk
stage, eta_seconds_remaining	in progress	Where the walk is; time left against the carrier's typical flow
quote.premium	quoted	Verbatim as the carrier's page printed it ("$857.80") — never parsed, rounded, or derived
quote.term_months	quoted	The term the printed premium covers
quote.premium_by_line	quoted, bundled walk	Each line's premium as the page printed it, beside the bundle total in quote.premium
quote.breakdown	quoted	The page's own line items, its own labels
quote.bound	quoted, newer walks	Cover read off the priced page — what the form actually bound, vs what was asked
quote.variants	quoted	Additional priced packages the page offered
quote.quote_number	quoted	The carrier's retrieval number, when the page shows one
quote.evidence_recorded	quoted	Screenshot evidence exists server-side (internal URIs never ride the wire)
declined: true + detail	declined	The carrier reviewed the details and refused to quote. An answer, not an error — relay it
detail	failed	The walk's own words for where and why it stopped

Refusals

Every refusal is a structured {"error", "detail"} object — nothing was submitted to any carrier unless the row below says otherwise.

Code	When	What to do
profile_required	Household facts sent at the top level, no profile wrapper	Re-call with the facts wrapped as shown in the refusal's example_arguments
authorization_required	Called without the user's go-ahead	Explain the consent facts, get a yes, pass it verbatim in user_authorization
bad_identity	A drivers_license_number shaped like an SSN	SSNs are never collected; send the licence number as printed on the licence
bad_profile	A profile field fails validation	detail names the field
one_line_per_dispatch	An empty lines map	Name at least one line to walk
unknown_line	A line with no walk (e.g. umbrella)	detail lists the lines live dispatch knows
coverage_selection_required	An auto or renters walk without full limits and deductibles	Re-call with the numbers — the walks type real values, never defaults
bad_ask	A home walk given a coverage ask	Send {"home": null} — the carrier's own form prices its package
missing_facts	No requested carrier's form can be filled from the profile	Ask the user for the needs[].fields[] facts (using their values where served) and re-call — see below
no_carriers	No carrier has a validated walk for that line + state	Fall back to quote_insurance
launch_failed	The agents couldn't start	Nothing reached any carrier — retrying is safe

---

Example: auto

A Fresno household confirming GEICO's own number. The profile carries the facts GEICO's form insists on (ownership, purchase timing, prior insurance, age first licensed…); identity is the real applicant; the ask is the same four axes as quote_insurance.

{
  "profile": {
    "zip_code": "93722",
    "dob": "1954-07-02",
    "gender": "Male",
    "marital_status": "Married",
    "education": "Bachelors",
    "employment_status": "Employed",
    "occupation": "Accountant or CPA",
    "home_ownership_status": "Own",
    "prior_insurance": {"insured": true, "limits": "not sure"},
    "auto": {
      "vehicles": [{
        "year": 2024, "make": "Ford", "model": "Maverick",
        "ownership": "Financed", "annual_mileage": 11000,
        "primary_use": "pleasure", "purchase_date": "2026-08"
      }],
      "drivers": [{
        "relation": "self", "age_first_licensed": 16,
        "years_licensed_outside_us": 0, "defensive_driving_course": true,
        "accidents": [], "violations": []
      }]
    }
  },
  "identity": {
    "first_name": "Cornelius", "last_name": "Beaumont", "dob": "1954-07-02",
    "street": "4381 W Spruce Ave", "city": "Fresno", "zip_code": "93722",
    "email": "cornelius.beaumont@example.com", "phone": "559-555-0164"
  },
  "lines": {"auto": {"bi": "100/300", "pd": 100, "coll_deductible": 500, "comp_deductible": 500}},
  "carriers": ["geico"],
  "user_authorization": "yes, go ahead and get me GEICO's real quote"
}

{
  "status": "in_progress",
  "authorization_recorded": true,
  "agents": [
    {
      "carrier_key": "geico",
      "carrier": "GEICO",
      "method": "browser_agent",
      "detail": "deterministic Foresee agent completing the carrier's own quote flow with the user's details",
      "eta_seconds": 480
    }
  ],
  "skipped": [],
  "note": "1 carrier(s) are being quoted live. Collect results by calling this tool again with the same arguments after a few minutes."
}

Re-calling with the same arguments later collects the finished walk. The premium is the page's own string; breakdown is the page's own labels (GEICO printed two packages side by side); term_months says what the number covers — $857.80 per 6 months, not per month.

{
  "status": "complete",
  "agents": [
    {
      "carrier_key": "geico",
      "carrier": "GEICO",
      "method": "browser_agent",
      "status": "complete",
      "quote": {
        "premium": "$857.80",
        "currency": "USD",
        "term_months": 6,
        "quote_number": null,
        "breakdown": {
          "Less Coverage": "$857.80",
          "More Coverage": "$870.70"
        },
        "evidence_recorded": true
      }
    }
  ]
}